Major milestones in AI for Mathematics — timeline-first, evidence-backed.https://charlie-wang-03.github.io/ai4math-chronicle/https://charlie-wang-03.github.io/ai4math-chronicle/en/events/openai-722-manuscript-mathematics-release/evt-2026-openai-math-releaseThe public repository includes an overview, a manuscript map, PDFs and sources, a Lean library and formalization catalogue, ten selected reasoning summaries and release-history commitments. OpenAI explicitly warns that some unformalized results may contain issues and says revisions will remain accessible. The release followed consultation with the independent Advisory Group on Mathematics and Artificial Intelligence. AGMAI publicly stated that its advice does not endorse the mathematics or OpenAI's process and characterized the release as the beginning of broader human understanding and community assessment.Tue, 06 Oct 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/claude-3sum-apsp-polynomial-speedup/evt-2026-claude-3sum-apspThe paper's methodology section says an Anthropic employee initially asked an internal research model to study a cryptographic question based on average-case Zero-k-Clique. Claude unexpectedly developed a new algorithm, first for the average-case setting and then for the worst case, during a session producing about 16 million output tokens with no human input. Anthropic shared the result with Alman and Vassilevska Williams, who reconstructed the argument, simplified it, improved constants and exponents, derived additional consequences and wrote the research paper. After the paper was complete, Anthropic used a research model to formalize major deterministic claims in Lean.Mon, 05 Oct 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/chatgpt-assisted-kls-proof/evt-2026-chatgpt-kls-proofIn the acknowledgements, the authors state that most proofs and mathematical ideas in the paper were found by ChatGPT. They identify the suspension idea as a notable human contribution and describe their role as understanding the model's proofs, checking and organizing the mathematics and improving the exposition. The paper is currently a very recent preprint; Chronicle has not located a public proof-assistant artifact or independent specialist review sufficient to move the event beyond a paper-released verification state.Sun, 04 Oct 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/meta-muse-spark-open-research/evt-2026-meta-muse-spark-open-researchMeta says human mathematicians selected and guided the research, a separate group of mathematicians reviewed the work, each paper marks passages primarily drafted by researchers versus AI, and prior or concurrent work is credited. Muse Spark's role varied by project: it helped test and revise calculations, generated a GAP search program that found a 384-element group counterexample, proposed counterexamples and proof strategies, and generated candidate proofs and technical sections. Meta also acknowledges that several questions were independently resolved by other teams, including one semiabelian-group counterexample reported by the Nilradical AI agent before Meta's publication.Fri, 02 Oct 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/agmai-responsible-release-ai-generated-mathematics/evt-2026-agmai-responsible-releaseAGMAI says the recommendations were informed by more than 600 responses from the mathematical community. The document distinguishes ordinary papers that a responsible mathematician fully understands from AI outputs that nobody yet understands. In the latter case it proposes technical release norms and a parallel obligation for labs to fund independent, community-led workshops, conferences, expository work and other activities needed to assimilate the mathematics. It also warns that unequal access to frontier systems could create a multi-tier mathematical community.Tue, 29 Sep 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/frenzymath-poincare-formalization/evt-2026-frenzymath-poincare-formalizationFrenzyMath reports about 3.2 million lines of Lean and less than USD 30,000 in LLM and compute costs for the project. The repository separates the Mathlib-only endpoint statements from the proof library and preserves Comparator configuration, verifier revisions, logs and source-provenance records. The announcement also notes that an independent team led by Ziyang Qin, Yuan Liao, Ayush Khaitan and Bennett Chow released another complete Poincaré Lean development earlier the same day; that separate arXiv paper records a full public build and says automated assistance was used for proofs and prose.Mon, 28 Sep 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/agmai-advisory-group/evt-2026-agmai-advisory-groupThe group says it formed after OpenAI approached some future members about creating an external advisory board; in agreement with OpenAI, those mathematicians instead formed an independent group and invited additional members. Its initial membership consists of François Charles, Camillo De Lellis, Timothy Gowers, Martin Hairer, Nikhil Srivastava, Ulrike Tillmann, Ravi Vakil, Edward Witten and Melanie Matchett Wood. The group's first stated task is to advise OpenAI on coordinating the release of a large number of significant mathematical results that OpenAI reports were produced by an internal model. OpenAI's announcement explicitly cites A Severe Misalignment of AI in Mathematics as part of the context for creating this bridge to the mathematical community.Mon, 21 Sep 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/lean-pool-ai-maintained-archive/evt-2026-lean-poolThe archive occupies a deliberately different position from Mathlib: it accepts independent completed formalization projects that may not fit Mathlib's tightly integrated library scope, while imposing automated maintenance and quality checks. The public repository reports that project imports are still selected by humans, while AI systems participate materially in review, maintenance and optimization. The corpus size changes continuously and is therefore not treated as a frozen historical claim in this Event.Mon, 21 Sep 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/formalflow-mipstarre/evt-2026-formalflow-mipstarreFormalFlow organizes long formalization projects around a shared blueprint and nested planning, proving and review loops. AI agents implement and review proof tasks while humans supervise the project, compare the formal development with the source mathematics and resolve semantic discrepancies. The public MIPStarRE repository preserves Lean sources, the active blueprint, source-paper material and CI-oriented proof-integrity infrastructure.Thu, 17 Sep 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/astra-liouville-goldbach/evt-2026-astra-liouville-goldbachThe public project supplies an authorless mathematical paper, a complete Lean 4 formalization against mathlib's Liouville function, pinned toolchain metadata, build and axiom audits, and proof-route checks. A separate audit repository independently rebuilt the frozen v1.0.0 artifact on Linux, matched the source hashes, repeated the axiom and route audits, and reported no sorry, custom theorem axiom, or native_decide. The public paper and repository do not preserve a detailed model–human derivation trace, so the precise division of intellectual labor remains source-attributed rather than independently reconstructed by the Chronicle.Wed, 16 Sep 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/severe-misalignment-ai-mathematics/evt-2026-severe-misalignment-ai-mathematicsThe declaration emerged from discussions among its initial signatories during a week of intense debate over rapidly improving AI systems and high-profile mathematical problem solving. It framed the central concern as a misalignment between benchmark-driven corporate incentives and the mathematical community's emphasis on understanding, communication, attribution, mentorship and durable knowledge. On 14 September, IMPA published the statement on its institutional news surface. On 15 September, the board of the French Mathematical Society cited it in an official position responding to the OpenAI Navier–Stokes announcement and its associated ethical controversy.Fri, 11 Sep 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/magenta-lean-verification-loop/evt-2026-magentaMagenta uses a statement judge to check whether a generated Lean statement preserves the original informal problem and an error-attribution judge to decide whether a failed attempt should return to mathematical re-derivation or local Lean repair. The paper reports that this feedback-guided correction loop outperforms independent resampling on difficult problems.Thu, 10 Sep 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/buckmaster-alpoge-fluid-blowup/evt-2026-buckmaster-alpoge-fluid-blowupThe researchers explicitly credit Diego Córdoba and Luis Martínez-Zoroa for the underlying forced-blowup research program and describe using LLMs to push that program from rougher forcing toward smooth forcing and related fluid equations. The public `fluid_lean` repository contains complete Lean developments for the Euler and Boussinesq theorems, with its documentation attributing the Lean code to Claude under Alpöge's direction.Tue, 08 Sep 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/openai-navier-stokes-solution-claim/evt-2026-openai-navier-stokesOpenAI says roughly 10,000 concurrent agents worked for about 88 hours on the successful search, followed by additional Lean formalization and verification. Independent reporting corroborated the publication event while also documenting disputes over attribution, provenance and priority involving contemporaneous work by Tristan Buckmaster and Levent Alpöge. OpenAI now says that, following an investigation, Buckmaster's Codex prompts during the two months before the 8 September release could not have influenced the system in any way, including through training. That direct statement narrows one provenance concern, while separate disputes over attribution, priority and the collaboration process remain part of the public record.Tue, 08 Sep 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/stochbench-stochastic-processes-lean/evt-2026-stochbenchThe benchmark covers Markov chains, renewal processes, random walks, martingales, stopping times, queues, Brownian motion, stochastic calculus, weak convergence, Poisson processes and continuous-time Markov processes. Its released dataset distinguishes 114 direct formalizations from 336 abstracted targets that expose assumptions explicitly when the required stochastic-process infrastructure is not available in the fixed Lean/Mathlib environment.Tue, 08 Sep 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/claude-fermat-last-theorem-formalization/evt-2026-claude-flt-formalizationClaude agents used Anthropic's Prove2Me workflow to build a dependency graph of formal subproblems and expand it into millions of lines of Lean code. The repository follows the classical Frey-Serre-Ribet-Wiles-Taylor-Wiles route and exposes the theorem graph, source attribution and reproducible verification procedures.Fri, 04 Sep 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/openai-gpt6-astra-prime-gaps-186/evt-2026-openai-prime-gaps-186The public PrimeGaps186 repository contains a Lean 4 development for DHL[40,2] and the 186 prime-gap consequence together with a Python/FLINT numerical certificate. The registered main Lean declarations contain no sorry, and OpenAI reports that Comparator, Nanoda and Lean's kernel accepted the conditional proofs. The formal development nevertheless depends on three explicit project axioms: a rank-three hyper-Kloosterman estimate, a rank-two Kloosterman correlation estimate, and a collection of physical-integral and cap bounds. The first two are attributed to established literature; the numerical input is checked by the companion certificate rather than proved inside Lean. OpenAI's own metadata labels the review self-assessed and states that no independent human semantic review had been completed.Sun, 30 Aug 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/palomar-lean-verified-mathematics-registry/evt-2026-palomar-registryPalomar was created in response to the increasing volume of machine-assisted and machine-generated mathematics and the difficulty of auditing claims scattered across repositories and announcements. Its public statement positions the service as analogous to a preprint or repository layer for formalizations: it provides an immutable, searchable and inspectable record of what was mechanically checked while leaving novelty, relevance and deeper mathematical judgment to the research community.Tue, 18 Aug 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/claude-riemann-zeta-lower-bound/evt-2026-claude-riemann-lower-boundClaude coordinated dozens of subagents, searched literature and numerical evidence, and produced a paper; Anthropic mathematicians reviewed the result and a Lean formalization passed comparator.Mon, 10 Aug 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/openai-ten-math-tcs-advances/evt-2026-openai-ten-advancesOpenAI states that an internal Astra model generated the mathematical arguments, humans prepared manuscripts with the model, and the model formalized each argument into a Lean certificate. Subsequent reporting documented attribution and training-data provenance concerns around the non-sofic-groups result, including Andreas Thom's unresolved question about whether unpublished mathematical discussions conducted through ChatGPT could have contributed indirectly through model-improvement data.Sat, 01 Aug 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/frontiermath-open-problems-50/evt-2026-frontiermath-open-problemsProblems are selected by mathematicians, paired with bespoke computational verifiers where possible, and categorized by the significance of a solution.Fri, 31 Jul 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/aimo-proof-pilot-open-models/evt-2026-aimo-proof-pilotThe pilot restricted participants to models whose intermediate checkpoints, training protocols and training data were public. Six teams produced evaluated outputs on six proof problems, and AIMO compared them under the same expert-grading procedure with open-weight and commercial frontier models while publishing the submissions and detailed grading data.Tue, 07 Jul 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/leiden-declaration-ai-mathematics/evt-2026-leiden-declarationThe declaration grew from a September 2025 Lorentz Center meeting of around 60 participants from 10 countries spanning mathematics, computer science, philosophy, history, social science, industry and government. A smaller working group developed the text over the following months with extensive community feedback. The declaration was archived on Zenodo with a DOI, endorsed by the IMU, later discussed at ICM 2026, and the subject of supportive editorials and reporting in major scientific publications.Tue, 02 Jun 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/alphaproof-nexus-open-problem-proof-search/evt-2026-alphaproof-nexusAlphaProof Nexus organized frontier LLM subagents around the Lean compiler and escalated proof search with specialized tools and evolutionary search. The project released Lean proofs for successful Erdős, OEIS and research-collaboration cases together with human-readable proof writeups for selected results.Thu, 21 May 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/openai-unit-distance-conjecture-disproof/evt-2026-unit-distance-disproofThe model found a construction using tools from algebraic number theory; OpenAI released the proof and a companion paper by external mathematicians who checked and contextualized the argument.Wed, 20 May 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/sorrydb-real-world-lean-benchmark/evt-2026-sorrydbSorryDB crawls eligible public Lean repositories, records reproducible repository and toolchain coordinates for unresolved `sorry` statements, and asks proving systems to replace each proof hole in its original project context. A verifier rebuilds the relevant project and checks proposed replacements, while a nightly database refresh supplies new tasks over time.Tue, 03 Mar 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/openai-first-proof-research-challenge/evt-2026-first-proof-openaiThe internal model worked with limited human supervision; researchers sometimes requested retries or clarifications and selected among attempts.Fri, 20 Feb 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/m2f-project-scale-autoformalization/evt-2026-m2fM2F first translates long mathematical documents into dependency-ordered Lean declaration skeletons and repairs project-level structural inconsistencies, then freezes statement signatures and iteratively closes proof holes using verifier feedback. The companion ReasBook repository exposes generated formalizations from textbooks and research papers.Thu, 19 Feb 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/aletheia-autonomous-mathematics-research-agent/evt-2026-aletheiaAletheia couples an advanced Gemini Deep Think model with iterative verification, revision and intensive tool use intended for research settings where literature navigation and long proof chains matter. The authors explicitly separated levels of autonomy and novelty rather than treating all AI-assisted results as equivalent.Tue, 10 Feb 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/numina-lean-agent-general-coding-agent/evt-2026-numina-lean-agentThe system uses a general-purpose coding-agent loop as the controller for Lean work and extends it with theorem retrieval, informal proving, verification and auxiliary reasoning tools exposed through an MCP-oriented interface. Its public repository includes setup instructions, runnable agent tooling and links to the Putnam proof artifacts.Tue, 20 Jan 2026 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/gpt5-2-learning-curve-monotonicity/evt-2025-gpt5-2-learning-curvesThe paper studies whether expected prediction error for maximum-likelihood estimation improves monotonically as more data are observed. It proves forward-KL monotonicity for several Gaussian and Gamma settings and gives a reverse-KL argument for broad exponential families. OpenAI presented the work as a case study of GPT-5.2 Pro contributing directly to previously unsolved mathematical questions.Thu, 11 Dec 2025 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/gpt5-assisted-nesterov-point-convergence/evt-2025-gpt5-nag-open-problemGPT-5 proposed multiple directions and several key structural ideas; Ryu checked, reformulated and wrote the rigorous final proof with coauthor Uijeong Jang.Mon, 27 Oct 2025 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/aristotle-imo-level-formal-theorem-proving/evt-2025-aristotleThe architecture generates and formalizes useful lemmas, searches formal proofs and handles geometry through a specialist component.Wed, 01 Oct 2025 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/goedel-prover-v2-self-correction/evt-2025-goedel-prover-v2The system uses scaffolded data synthesis, verifier-guided iterative repair and model averaging.Tue, 05 Aug 2025 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/seed-prover-deep-broad-formal-reasoning/evt-2025-seed-proverThe system iteratively refines whole proofs from Lean feedback and uses test-time strategies for deep and broad search.Thu, 31 Jul 2025 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/gemini-deep-think-imo-2025-gold/evt-2025-gemini-imo-goldUnlike AlphaProof and AlphaGeometry 2 in 2024, the 2025 system consumed official problem statements directly and produced natural-language proofs without manual translation into Lean or another domain-specific formal language. It completed the task within the 4.5-hour competition limit.Mon, 21 Jul 2025 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/openai-imo-2025-gold-level/evt-2025-openai-imo-goldThe model worked from official natural-language problem statements without a proof assistant or internet access during the evaluation.Sat, 19 Jul 2025 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/leanconjecturer-formal-conjecture-generation/evt-2025-leanconjecturerThe pipeline extracts definitions and theorem context from Lean files, asks an LLM to propose new formal statements, checks generated statements through Lean and separates harder candidates for subsequent training. The paper also reports several non-trivial topology examples as evidence that the pipeline can produce mathematically useful statements rather than only superficial perturbations.Fri, 27 Jun 2025 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/mathesis-natural-language-formal-proving/evt-2025-mathesisMathesis translates an informal problem into a Lean 4 statement, scores candidate formalizations for syntactic and semantic quality, and uses downstream prover feedback to prefer statements that can support machine-checked proofs. Gaokao-Formal provides hundreds of challenging proof problems derived from Chinese college-entrance examinations for evaluating this full pipeline.Sun, 08 Jun 2025 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/matharena-live-math-competitions/evt-2025-matharenaMathArena evaluates models on recurring competitions soon after problems are released and records whether a model predates each competition. Its public pipeline supports final-answer parsing as well as proof-based competitions such as USAMO and IMO, where expert graders assess model-generated proofs.Thu, 29 May 2025 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/alphaevolve-algorithm-discovery/evt-2025-alphaevolveThe agent maintains populations of candidate programs, uses language models to propose edits and repeatedly scores outputs with executable evaluators. The accompanying technical report and results repository document mathematical cases where the evolved programs improved known constructions.Wed, 14 May 2025 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/deepseek-prover-v2-subgoal-rl/evt-2025-deepseek-prover-v2DeepSeek-V3 first decomposes problems into subgoals; successful subgoal proofs become cold-start reasoning traces for reinforcement learning.Wed, 30 Apr 2025 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/deepseek-r1-reinforcement-learning-reasoning/evt-2025-deepseek-r1R1-Zero used reinforcement learning without an SFT cold start, while R1 added multi-stage training and released several distilled open models.Wed, 22 Jan 2025 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/ramanujan-library-integer-relations/evt-2024-ramanujan-libraryThe project represents mathematical constants as vertices and formulas as hyperedges, then searches for integer relations that can expand this graph. The associated LIReC software provides a public database and numerical relation-identification tools for inspecting and extending the library.Mon, 16 Dec 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/frontiermath-research-level-benchmark/evt-2024-frontiermathThe benchmark was developed with more than sixty mathematicians and emphasized problems requiring hours or days of expert work.Fri, 08 Nov 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/internlm-step-prover-expert-iteration/evt-2024-internlm-step-proverThe system performs expert iteration over large Lean datasets and uses a critic to prioritize easier problems and guide deeper proof searches.Mon, 21 Oct 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/omni-math-olympiad-benchmark/evt-2024-omni-mathThe benchmark was designed after frontier reasoning models approached saturation on older datasets such as MATH.Thu, 10 Oct 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/leanagent-lifelong-theorem-proving/evt-2024-leanagentLeanAgent repeatedly ingests new Lean repositories, traces theorem and premise data through LeanDojo, updates a dynamic database, progressively retrains premise retrieval and searches for proofs of `sorry` theorems. Successful proofs can be added back to the knowledge base for later learning.Tue, 08 Oct 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/gsm-symbolic-robustness-benchmark/evt-2024-gsm-symbolicThe benchmark derives controllable families of grade-school mathematics problems from symbolic templates. This lets evaluators vary numerical values, clause counts and distractors while preserving the underlying reasoning structure, testing whether model success is stable rather than tied to a fixed benchmark instance.Mon, 07 Oct 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/openai-o1-reasoning-aime/evt-2024-openai-o1The o1 series was trained to spend more inference-time computation on multi-step reasoning before producing an answer.Thu, 12 Sep 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/deepseek-prover-v1-5-lean-proof-search/evt-2024-deepseek-prover-v1-5The model was specialized for Lean 4 formal mathematics, refined with reinforcement learning from Lean feedback and paired with an intrinsic-reward Monte Carlo tree-search variant to explore diverse proof paths. DeepSeek released model weights and code for reproducing the proof-search setup.Thu, 15 Aug 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/minictx-long-context-theorem-proving/evt-2024-minictxThe benchmark draws theorems from real Lean projects and textbooks and includes tooling for extracting new project contexts.Mon, 05 Aug 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/ai-for-math-icml-workshop-series/evt-2024-ai-for-math-icmlThe workshop series was created specifically around AI technologies for mathematical reasoning and discovery. By its third edition, the venue reported hundreds of submissions and accepted papers, a multi-level program committee, paper awards and four challenge tracks covering autoformalization alignment, theoretical-computer-science proving, visual scientific reasoning and end-to-end Lean proof generation.Fri, 26 Jul 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/alphaproof-alphageometry2-imo-2024/evt-2024-alphaproof-alphageometry2-imoAlphaProof used reinforcement learning in Lean for formal proof search, while AlphaGeometry 2 handled the geometry problem with a faster neuro-symbolic system. The 2024 workflow required experts to translate problems into formal representations and used up to several days of computation.Thu, 25 Jul 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/putnambench-formal-undergraduate-competition/evt-2024-putnambenchInitial neural and symbolic provers solved only a handful of benchmark problems, making the collection a high-difficulty target for formal reasoning.Mon, 15 Jul 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/lean-star-thinking-and-proving/evt-2024-lean-starThe method generates retrospective thoughts from known tactics and then uses expert iteration on newly discovered verified proofs.Sun, 14 Jul 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/numinamath-aimo-progress-prize/evt-2024-numinamath-aimoThe winning system fine-tuned DeepSeekMath-Base 7B and combined chain-of-thought with Python tool execution, self-consistency and internal validation sets.Thu, 11 Jul 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/lean-workbook-synthetic-formalization-dataset/evt-2024-lean-workbookAn iterative generation-and-filtering pipeline translates natural-language math problems to Lean 4 statements and back.Thu, 06 Jun 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/deepseek-prover-synthetic-lean-data/evt-2024-deepseek-prover-v1Natural-language competition problems are translated into Lean statements, filtered, proved and recycled as synthetic training data.Thu, 23 May 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/olympiadbench-bilingual-multimodal/evt-2024-olympiadbenchThe benchmark was designed to remain difficult for frontier text and multimodal models and includes detailed evaluation methodology.Wed, 21 Feb 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/internlm-math-verifiable-reasoning/evt-2024-internlm-mathThe project encodes reasoning, reward modeling, formal tasks, data augmentation and code-interpreter behavior in a unified sequence-to-sequence format.Fri, 09 Feb 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/deepseekmath-grpo-open-math-model/evt-2024-deepseekmathThe model continued pretraining on 120B math-related tokens and then used supervised and reinforcement-learning stages for mathematical reasoning.Mon, 05 Feb 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/alphageometry-olympiad-geometry/evt-2024-alphageometryAlphaGeometry combines a neural language model trained on synthetic theorem/proof data with a symbolic deduction engine. The language model proposes auxiliary constructions and the symbolic engine checks deductions.Wed, 17 Jan 2024 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/funsearch-mathematical-discovery/evt-2023-funsearch-cap-setGoogle DeepMind paired a pretrained language model with an evaluator and evolutionary program search. The resulting system searched over executable programs rather than directly emitting final mathematical answers.Thu, 14 Dec 2023 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/math-shepherd-process-reward-model/evt-2023-math-shepherdThe verifier scores intermediate reasoning steps rather than only final answers and can be used for selection or reinforcement learning.Thu, 14 Dec 2023 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/llemma-open-math-language-model/evt-2023-llemmaThe project continued pretraining Code Llama on Proof-Pile-2, a mixture of mathematical web text, scientific papers and mathematical code.Mon, 16 Oct 2023 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/copra-in-context-formal-proof-agent/evt-2023-copraAt each step the agent proposed a tactic, executed it in the proof assistant, incorporated errors or new goals into the next prompt and maintained a search history for backtracking. The architecture showed how a frontier general model could be wrapped in a proof-oriented agent harness without task-specific finetuning.Fri, 06 Oct 2023 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/mathvista-visual-math-benchmark/evt-2023-mathvistaThe benchmark combines visual perception with compositional mathematical reasoning. The initial study found a substantial gap between frontier multimodal models and human performance, while the public project provides dataset access, evaluation code and model-result tooling.Tue, 03 Oct 2023 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/lego-prover-growing-library/evt-2023-lego-proverThe system couples a prover and an evolver through a shared skill library. The prover constructs modular proofs from retrieved and newly generated lemmas, while the evolver transforms verified skills to increase their generality, reuse and complexity.Sun, 01 Oct 2023 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/tora-tool-integrated-math-reasoning/evt-2023-toraThe agents learn interactive tool-use trajectories involving computation libraries and symbolic solvers rather than relying on text-only chain-of-thought.Fri, 29 Sep 2023 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/ams-ai-advisory-group/evt-2023-ams-ai-advisoryThe AMS response developed during the first year of widespread generative-AI use. A Notices article records that the Society had already amended its Ethical Guidelines and Journal Policies in June 2023 to adopt the COPE position that AI tools cannot be authors and AI use must be disclosed. The July advisory group then broadened the response from immediate journal rules to sustained governance questions for mathematical research and the profession. Its 2024 white papers were explicitly intended as living resources for AMS policy committees and the wider community.Mon, 10 Jul 2023 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/leandojo-retrieval-augmented-theorem-proving/evt-2023-leandojoThe project extracts proof states, tactics and premise information from Lean repositories and exposes a programmatic proof environment. ReProver retrieves relevant premises before generating tactics, directly addressing the library-scale premise-selection problem.Tue, 27 Jun 2023 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/alphadev-sorting-algorithms/evt-2023-alphadevThe system searches directly over assembly instructions using an AlphaZero-style learning and search procedure. DeepMind reported speedups up to 70% for short sequences and about 1.7% for very long sequences, while releasing pseudocode and discovered assembly programs with correctness tests.Wed, 07 Jun 2023 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/process-supervision-prm800k/evt-2023-process-supervision-prm800kRather than rewarding only a final answer, the project collected human judgments on intermediate reasoning steps and trained process reward models from those labels. PRM800K exposes the annotations, labeling instructions and scored model samples used in the study.Wed, 31 May 2023 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/baldur-whole-proof-generation-repair/evt-2023-baldurInstead of predicting one proof step and searching over continuations, Baldur fine-tuned language models to generate an entire proof in one pass. A separate repair model then received a failed proof attempt together with proof-assistant error feedback and proposed a corrected proof.Wed, 08 Mar 2023 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/proofnet-autoformalization-benchmark/evt-2023-proofnetThe benchmark covers analysis, linear algebra, abstract algebra, topology and other textbook mathematics.Fri, 24 Feb 2023 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/draft-sketch-prove-informal-guidance/evt-2022-draft-sketch-proveLanguage models produce a high-level formal sketch whose subgoals are then discharged by an automated prover.Fri, 21 Oct 2022 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/alphatensor-matrix-multiplication-algorithms/evt-2022-alphatensorDeepMind represented matrix multiplication as a tensor-decomposition game and trained an AlphaZero-style reinforcement-learning agent to search the enormous space of factorizations. Released artifacts include discovered factorizations, benchmarking code and checks of algorithmic properties.Wed, 05 Oct 2022 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/minerva-quantitative-reasoning-language-model/evt-2022-minervaGoogle Research continued pretraining a large language model on scientific papers and mathematical web content, then evaluated chain-of-thought-style solutions across mathematics, physics and other quantitative domains. The system operated in natural language rather than a proof assistant.Wed, 29 Jun 2022 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/autoformalization-large-language-models/evt-2022-autoformalization-llmResearchers used few-shot prompting to ask large language models to translate informal mathematical statements into Isabelle/HOL. The generated formalizations were then used as additional training data for a neural theorem prover, linking informal-language translation with formal proof search in one pipeline.Wed, 25 May 2022 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/naturalprover-grounded-proof-generation/evt-2022-naturalproverNaturalProver conditions language-model proof generation on mathematical background references such as definitions and theorems, either retrieved automatically or supplied by humans. The project studied both next-step suggestion and full-proof generation and released the NaturalProofs-Gen data, training and generation code, evaluation tooling and model assets.Wed, 25 May 2022 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/hypertree-proof-search/evt-2022-htpsThe system learns from its own proof searches and uses a hyper-tree search algorithm inspired by Monte Carlo tree search and AlphaZero.Mon, 23 May 2022 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/thor-language-model-hammer-integration/evt-2022-thorThe framework uses theorem-prover hammers for premise selection while leaving other proof decisions to the language model.Sun, 22 May 2022 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/lean-statement-curriculum-learning/evt-2022-statement-curriculum-learningThe prover alternated proof search with retraining on newly discovered proofs over statements of varied difficulty.Wed, 02 Feb 2022 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/her-incremental-first-order-theorem-prover/evt-2021-her-proverClauses are encoded as graphs and scored by transformer-based models. Training proceeds incrementally, while hindsight replay turns intermediate states from unsuccessful searches into additional learning targets instead of discarding those trajectories.Mon, 20 Dec 2021 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/deepmind-ml-guided-pure-math-discovery/evt-2021-deepmind-math-discoveryThe project used supervised machine learning to search large mathematical datasets for predictive relationships and attribution methods to expose which variables drove those predictions. Mathematicians then interpreted the signals, reformulated them as mathematical statements, tested counterexamples and supplied conventional mathematical arguments. The Nature article demonstrated the workflow on hyperbolic knots and Kazhdan-Lusztig polynomials, alongside public notebooks and datasets for both case studies.Wed, 01 Dec 2021 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/gsm8k-verifier-math-reasoning/evt-2021-gsm8kThe work paired a human-written math reasoning dataset with a generator-verifier pipeline. A language model generated many candidate solutions, while a separately trained verifier scored those solutions and selected the most promising answer.Wed, 27 Oct 2021 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/minif2f-formal-olympiad-benchmark/evt-2021-minif2fThe benchmark translated problems from AIME, AMC, IMO and educational sources into formal languages. Its goal was not a new mathematical theorem but a reproducible common target on which learned theorem provers could be trained and compared.Tue, 31 Aug 2021 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/math-ai-workshop-series/evt-2021-math-ai-workshopMATH-AI began as a cross-disciplinary workshop asking how mathematical reasoning could illuminate general AI. The inaugural program combined invited talks, contributed papers, poster sessions and a discussion panel, while its review process used anonymized submissions. Across later editions the series evolved with the field toward large language models, theorem proving, autoformalization, mathematical discovery and agentic AI while retaining a dedicated mathematical-reasoning identity.Fri, 07 May 2021 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/math-competition-problem-benchmark/evt-2021-math-benchmarkThe benchmark covered algebra, geometry, number theory, probability and other competition topics and provided full solution derivations.Fri, 05 Mar 2021 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/tacticzero-deep-rl-theorem-proving/evt-2021-tacticzeroThe system represents proof search as an end-to-end reinforcement-learning problem and introduces backtracking that lets the agent abandon predicted dead ends and resume from promising alternatives. The resulting proofs are constructed inside HOL4 and therefore remain subject to the proof assistant's kernel checking.Fri, 19 Feb 2021 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/pact-proof-artifact-cotraining/evt-2021-pactThe method extracts self-supervised objectives from kernel-level proof terms and trains them alongside tactic prediction.Thu, 11 Feb 2021 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/gpt-f-metamath-theorem-proving/evt-2020-gpt-fOpenAI researchers Stanislas Polu and Ilya Sutskever trained generative models over formal mathematical text and integrated them into proof search for the Metamath language. The work framed theorem proving as sequence generation and showed that learned generation could contribute usable proof artifacts to an established formal library.Mon, 07 Sep 2020 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/tactician-coq-tactic-learning/evt-2020-tacticianThe project combines online tactic learning, proof search and package-aware instrumentation so machine-learning assistance lives inside the proof assistant rather than as a detached benchmark-only experiment.Fri, 31 Jul 2020 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/int-generalization-theorem-proving/evt-2020-intThe benchmark generates synthetic inequality proofs from axioms and varies properties of training and test distributions so researchers can distinguish memorization-like success from different forms of out-of-distribution theorem-proving generalization.Mon, 06 Jul 2020 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/isarstep-high-level-reasoning/evt-2020-isarstepIsarStep converts declarative Isar proofs into sequence-to-sequence examples where a proof fragment has an intermediate proposition removed. The task tests whether a model can reconstruct a semantically useful bridge between surrounding proof states, and the authors evaluated Transformer-based baselines including a hierarchical architecture designed for long proof context.Sat, 13 Jun 2020 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/skip-tree-self-supervised-math/evt-2020-skip-treeRather than masking only a flat token span, skip-tree training removes a subtree from a structured mathematical expression and trains a model to reconstruct it, encouraging representations that reflect the compositional structure of formal mathematics.Mon, 08 Jun 2020 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/natural-language-premise-selection/evt-2020-nl-premise-selectionThe work treated mathematical discourse as a retrieval problem rather than only an answer-generation problem. Its dataset captures links among conjectures, definitions and supporting propositions in ProofWiki, while accompanying baselines and later graph-based experiments measured how effectively models could recover proof-relevant references.Thu, 30 Apr 2020 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/metagen-synthetic-theorem-generation/evt-2020-metagenThe system learns from existing formal mathematics, generates additional theorem-proof pairs, and feeds the synthetic corpus back into prover training rather than relying only on scarce human-authored proof traces.Mon, 17 Feb 2020 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/coqgym-astactic-theorem-proving/evt-2019-coqgymCoqGym extracted proof states, environments, goals, tactics and proof trees from open-source Coq projects and exposed them through a programmatic interaction layer. ASTactic learned proof-step generation from this corpus and composed tactics from runtime syntax rather than relying only on a predetermined list of complete tactics.Tue, 21 May 2019 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/holist-deephol-theorem-proving/evt-2019-holistHOList instrumented HOL Light so learning systems could interact with proof states and tactics through a machine-learning environment. The benchmark packaged theorem statements from core, complex and Flyspeck corpora with train, validation and test labels, while DeepHOL supplied a neural prover and reinforcement-learning loop for generating additional successful proof traces.Fri, 05 Apr 2019 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/mathematics-dataset-neural-reasoning/evt-2019-mathematics-datasetThe original release provided millions of generated question-answer pairs per module and evaluated contemporary sequence-to-sequence neural architectures on both ordinary test splits and extrapolation settings. The accompanying open-source generator made it possible to reproduce and extend the task distribution rather than treating the benchmark as a fixed static question list.Tue, 02 Apr 2019 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/gamepad-coq-learning-environment/evt-2018-gamepadGamePad instruments Coq so proof states, proof steps, mid-level and kernel-level terms and proof trees can be represented as Python data structures. A lightweight coqtop wrapper lets learning code send tactics and receive parsed proof states, while released tooling supports extracting data from the Mathematical Components odd-order development.Sat, 02 Jun 2018 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/reinforcement-learning-theorem-proving/evt-2018-rl-theorem-provingThe system repeatedly performs proof-search simulations, turns successful and failed attempts into learning signals, and retrains guidance used in subsequent searches. The approach was evaluated over a large formal-mathematics problem corpus, emphasizing learned search control rather than theorem-specific handwritten heuristics.Sat, 19 May 2018 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/neural-mizar-autoformalization/evt-2018-neural-mizar-autoformalizationThe authors constructed a large aligned corpus by informalizing Mizar statements into LaTeX-like mathematical text and trained sequence-to-sequence translation models to reconstruct the formal language. The study evaluated multiple neural translation configurations and used case studies to examine which mathematical structures could be recovered correctly.Thu, 10 May 2018 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/mathlib3-formal-mathematics-library/evt-2017-mathlib3Mathlib organized community-authored Lean definitions, theorems, proofs and tactics into a common mathematical library spanning algebra, analysis, topology, number theory and other areas. Shared APIs and review practices made formal developments composable rather than isolated project artifacts.Fri, 21 Jul 2017 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/tactictoe-hol4-tactic-learning/evt-2018-tactictoeTacticToe records tactic-level proof information from HOL4, learns which proof actions are promising in a new goal state, and searches over complete tactic sequences directly in higher-order logic rather than translating every problem to first-order logic. The 2017 system used a modified A*-style search with tactic prediction and small-scale hammering; the later expanded implementation developed the search machinery further and remains available in the HOL4 repository.Thu, 04 May 2017 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/holstep-machine-learning-dataset/evt-2017-holstepHolStep extracts intermediate statements and conjectures from HOL Light proofs, canonicalizes their textual representation and pairs useful proof steps with negative examples. The release defines conditioned and unconditioned proof-step classification tasks and provides baseline code so researchers can compare learned representations and relevance models on a common formal-mathematics corpus.Wed, 01 Mar 2017 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/deep-network-guided-proof-search/evt-2017-deep-network-guided-proof-searchThe system learns from clause-level traces of successful automated proofs and ranks generated clauses during saturation-style proof search. Because neural evaluation is slower than hand-engineered heuristics, the authors used hybrid guidance and a two-phase search strategy that lets the learned model improve the search trajectory before faster conventional heuristics finish the proof attempt.Tue, 24 Jan 2017 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/semantic-parsing-mathematics/evt-2016-semantic-parsing-mathThe system learns how ambiguous mathematical notation is parsed from aligned corpora and then uses formal semantic constraints to reject syntactically plausible but mathematically ill-typed or unsupported interpretations. This creates a hybrid statistical-symbolic pipeline in which learning proposes formal structures and theorem-proving machinery helps validate them.Tue, 29 Nov 2016 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/holophrasm-neural-theorem-prover/evt-2016-holophrasmHolophrasm parses Metamath statements into tree structures, learns neural models for proof-step generation and proof-state evaluation, and combines them with search over candidate proof trees. The public release includes model-training and proof-search code, saved proof outputs, and instructions for replaying generated proofs through Metamath's verifier.Mon, 08 Aug 2016 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/deepmath-premise-selection/evt-2016-deepmathDeepMath encodes conjectures and candidate premises with recurrent and convolutional neural architectures and learns whether a premise is useful for a target theorem. The release turned large formal proof corpora into training data for neural relevance models, making representation learning a central component of automated theorem-proving pipelines.Tue, 14 Jun 2016 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/aitp-conference-inaugural/evt-2016-aitpAITP 2016 explicitly positioned itself as a forum for combining AI and reasoning methods over large mathematical and scientific corpora. The inaugural program included focused sessions on AI for ATP/ITP and mathematics, informal and semi-formal mathematical understanding, modern AI methods, and contributed talks. Its official series record documents yearly meetings from 2016 through 2026.Sun, 03 Apr 2016 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/ai4reason-project-launch/evt-2015-ai4reasonThe project focused on large and complex theories, learning from reasoning traces, feedback loops between deduction and learning, and knowledge accumulation across multiple mathematical representation styles.Tue, 01 Sep 2015 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/lean-theorem-prover-cade-2015/evt-2015-leanLean combined a small proof-checking kernel, an expressive dependent type theory, interactive proof development and extensible automation in one open platform intended for formalized mathematics as well as verification.Fri, 07 Aug 2015 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/flyspeck-kepler-completion/evt-2014-flyspeck-completionThe completed development formalized both the mathematical text and the large computational components needed for the Kepler-conjecture proof.Sun, 10 Aug 2014 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/mizar40-ai-atp/evt-2013-mizar40The system scaled fast learned relevance methods over roughly 150,000 MML formulas and deployed them within the MizAR online reasoning service.Thu, 10 Oct 2013 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/holyhammer-hol-light-ai-atp/evt-2013-holyhammerUsers could upload HOL Light developments and ask the service to attack new conjectures using learned relevance models, parallel ATP combinations and decision procedures.Thu, 19 Sep 2013 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/odd-order-theorem-coq/evt-2013-odd-order-coqThe project formalized the theorem together with a substantial mathematical library spanning group theory, linear algebra, Galois theory and real/complex algebraic numbers.Mon, 22 Jul 2013 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/sledgehammer-isabelle-atp/evt-2010-sledgehammerSledgehammer selects relevant Isabelle facts, translates proof obligations to external ATPs and uses the returned information to help construct proof-assistant-checked proofs.Wed, 14 Jul 2010 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/mptp-large-theory-challenge/evt-2007-mptp-challengeThe challenge supplied common Mizar-derived problems, public rules and a total resource budget intended to make learning, premise selection and other large-theory reasoning strategies directly comparable.Mon, 16 Jul 2007 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/malarea-learning-reasoning-loop/evt-2007-malareaThe system repeatedly trains relevance models from existing proofs, invokes automated provers on selected premises and incorporates newly found proofs into subsequent learning rounds.Wed, 27 Jun 2007 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/four-colour-theorem-coq/evt-2005-four-colour-coqThe formal development encoded the combinatorial argument and computational case checking inside Coq so that correctness reduced to the proof assistant's general verification mechanisms rather than theorem-specific external programs.Thu, 21 Apr 2005 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/flyspeck-project-launch/evt-2003-flyspeck-launchThe project aimed to formalize both the written mathematical argument and the computer calculations underlying Hales's proof, eventually using HOL Light and Isabelle.Wed, 15 Jan 2003 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/hr-automated-theory-formation/evt-1998-hrHR searches a space of mathematical concepts, evaluates their interest and uses generated concepts to drive further examples, classifications and conjectures.Sun, 26 Jul 1998 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/robbins-conjecture-eqp/evt-1996-robbins-eqpThe automated search produced a compact equational derivation in a problem that had resisted prior human and machine efforts for decades.Thu, 10 Oct 1996 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/cade-atp-system-competition/evt-1996-cascSystems were evaluated in a shared computational environment on standardized theorem-proving problems, making performance comparisons more reproducible and visible.Thu, 01 Aug 1996 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/qed-manifesto/evt-1994-qed-manifestoQED was a field-building vision rather than a single software release, calling for broad cooperation around shared formal mathematical knowledge.Sun, 15 May 1994 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/tptp-problem-library/evt-1993-tptpTPTP collected ATP test problems into standardized formats with domain classification and release/version discipline so theorem provers could be tested on comparable inputs.Fri, 12 Nov 1993 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/metamath-formal-language/evt-1992-metamathMetamath separates a very small verifier from explicit proof objects, allowing a large body of formal mathematics to be checked with a minimal trusted mechanism.Wed, 30 Sep 1992 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/isabelle-generic-theorem-prover/evt-1988-isabelleIsabelle used higher-order unification and a generic meta-level architecture to encode and reason within several object logics, with tactics and tacticals providing automation.Mon, 23 May 1988 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/hol-proof-generating-system/evt-1988-holHOL combined a small trusted logical basis, ML programming and tactics/tacticals for goal-directed interactive proof in higher-order logic.Fri, 01 Jan 1988 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/nuprl-constructive-proof-development/evt-1986-nuprlNuprl combined constructive type theory, refinement-style proof development, tactics and computational interpretation of proofs. Complete proofs could be used to obtain programs meeting formal specifications, linking theorem proving, formal mathematics and verified programming in a single environment.Tue, 01 Jul 1986 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/graffiti-automated-conjecturing/evt-1986-graffitiGraffiti evaluated candidate relations between graph invariants, retained statements without known counterexamples and used heuristics to suppress trivial or redundant conjectures.Sun, 01 Jun 1986 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/coq-early-proof-checker/evt-1984-coqThe system provided machine checking for proofs in the Calculus of Constructions and evolved through successive implementations into Coq and later Rocq.Sat, 22 Dec 1984 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/edinburgh-lcf-trusted-kernel-tactics/evt-1979-edinburgh-lcfEdinburgh LCF avoided retaining complete proof objects by exposing theorem values through a restricted abstract interface whose constructors corresponded to axioms and inference rules. Users could write higher-level proof procedures in the typed functional language ML, while tactics and tacticals supported reusable backward proof strategies.Sat, 01 Dec 1979 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/am-automated-mathematician/evt-1977-amAM maintained an agenda of potentially interesting mathematical tasks and used general heuristics to decide which concepts, examples and conjectures to explore next.Mon, 22 Aug 1977 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/wu-method-geometry-theorem-proving/evt-1977-wu-methodThe method algebraizes elementary geometry: geometric configurations are encoded as polynomial equations and theorem proving is reduced to symbolic polynomial reasoning. Wu developed the route from Ritt-style characteristic-set ideas and constructive elimination, enabling mechanical proof procedures and explicit treatment of degenerate cases. Later computer implementations proved non-trivial geometry theorems and helped establish algebraic automated deduction in geometry as a durable research program.Fri, 18 Feb 1977 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/mizar-ideology/evt-1973-mizarMizar developed a formal mathematical language, checker and library model aimed at building a cumulative body of computer-verifiable mathematics.Wed, 14 Nov 1973 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/pltp-boyer-moore-induction/evt-1973-pltpPLTP targeted properties of recursively defined programs that resolution-based first-order provers handled poorly, using domain-specific proof procedures centered on simplification and induction.Mon, 20 Aug 1973 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/lcf-proof-checker/evt-1972-lcfStanford LCF let users state proof goals, decompose them into subgoals and apply simplification and inference commands while the machine checked the resulting formal derivations. It predated the extensible ML metalanguage, abstract theorem type and programmable tactics that characterized Edinburgh LCF.Sat, 01 Jan 1972 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/macsyma-symbolic-mathematics/evt-1971-macsymaMACSYMA integrated rational functions, algebraic simplification, calculus and related symbolic operations within an interactive extensible system.Tue, 23 Mar 1971 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/automath-language/evt-1968-automathAutomath represented definitions, propositions and proofs in a highly explicit typed formal language so a computer could verify the correctness of derivations.Mon, 16 Dec 1968 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/resolution-principle/evt-1965-resolution-principleThe method combines substitution through unification with a single resolution inference scheme, replacing less efficient alternating procedures used in earlier machine theorem proving.Fri, 01 Jan 1965 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/saint-symbolic-integration/evt-1961-saintSAINT represented integration as a search problem, using rules of thumb to choose transformations and substitutions that reduced an integral toward solvable forms.Wed, 10 May 1961 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/geometry-theorem-machine/evt-1960-geometry-theorem-machineThe system combined symbolic deduction with geometric information to prune implausible proof paths, demonstrating an early form of domain-informed heuristic reasoning.Tue, 03 May 1960 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/logic-theorist/evt-1956-logic-theoristThe system encoded logical expressions and searched a space of permissible transformations, prioritizing promising branches with heuristics rather than exhaustive enumeration.Mon, 10 Sep 1956 00:00:00 GMThttps://charlie-wang-03.github.io/ai4math-chronicle/en/events/dartmouth-ai-proposal/evt-1955-dartmouth-ai-proposalThe proposal did not establish AI4Math as a separate field. It established the broader AI research frame within which mathematical reasoning became one of the earliest domains for testing machine intelligence.Wed, 31 Aug 1955 00:00:00 GMT