{"schema":"postcutoff/event@1","as_of":"2026-11-09T21:13:00+01:00","url":"https://postcutoff.com/e/2026-11-02-ai-assisted-results-november-2-listing/","md":"https://postcutoff.com/e/2026-11-02-ai-assisted-results-november-2-listing/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-11-02-ai-assisted-results-november-2-listing","date":"2026-11-02","date_precision":"day","short_title":"AI-assisted results, 2 Nov: arXiv of 2 Nov and Hexagon of 1–2 Nov","deck":null,"takeaway":"The 2 Nov sweep listed 319 arXiv papers that mention AI, 75 conjecture papers without an AI statement and 52 uncited Hexagon works. Three results got own entries: Colbrook's proof of the 1974 Kung–Traub conjecture (Lean, with ChatGPT 6), Yu–Yu's GPT-6 Astra counterexample to the Alon–Krivelevich conjecture, and Barra–Durante's AI-generated proof of the Hopfield thermodynamic limit. Listed here: Okayasu's answer to Haagerup's 1985 problem with Claude Opus 5.5, Suvrit Sra's proof of Petz's 1994 conjecture with GPT Pro, Qiyue Tang's claimed proof of Kamnitzer's ICM 2022 conjecture (after an AI reviewer found a fatal error that was then repaired), and Niels Feld's counterexamples to Morel's purity conjecture.","category":"science","category_label":"Science & math","importance":2,"confidence":"medium","status":{"key":"pending","labels":["Awaiting review"]},"sources":[{"n":1,"title":"arXiv 2610.41746: A solution to Haagerup's problem on decomposable maps (Okayasu)","url":"https://arxiv.org/abs/2610.41746","type":"paper","group":"primary","domain":"arxiv.org"},{"n":2,"title":"Hexagon 2610.00717: A proof of Petz's conjecture (Sra)","url":"https://hexagonmath.org/abs/2610.00717","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":3,"title":"Hexagon 2611.00006: Equality of the Mirković–Vilonen and theta bases (Tang)","url":"https://hexagonmath.org/abs/2611.00006","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":4,"title":"Hexagon 2611.00015: Positive polytopes and the full Fock–Goncharov conjecture (Tang)","url":"https://hexagonmath.org/abs/2611.00015","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":5,"title":"Hexagon 2611.00017: Gersten injectivity and Morel's purity conjecture (Feld)","url":"https://hexagonmath.org/abs/2611.00017","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":6,"title":"Hexagon 2610.00713: Claw-free perfect graphs are chromatic-choosable","url":"https://hexagonmath.org/abs/2610.00713","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":7,"title":"Hexagon 2611.00014: Korenblum's constant lower bound (Niedbala Giraudin)","url":"https://hexagonmath.org/abs/2611.00014","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":8,"title":"Hexagon 2610.00711: Deterministic integer factorization bound (Shunia)","url":"https://hexagonmath.org/abs/2610.00711","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":9,"title":"Hexagon 2610.00568: A proof Gauss might have found (van Dijk)","url":"https://hexagonmath.org/abs/2610.00568","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":10,"title":"arXiv 2610.40863: The Cranston–Li–Su–Wang–Xu conjecture is true","url":"https://arxiv.org/abs/2610.40863","type":"paper","group":"primary","domain":"arxiv.org"},{"n":11,"title":"arXiv 2610.40874: Proof of the entropic c-theorem","url":"https://arxiv.org/abs/2610.40874","type":"paper","group":"primary","domain":"arxiv.org"},{"n":12,"title":"formal-conjectures commit: Kourovka 19.25 negative answer","url":"https://github.com/google-deepmind/formal-conjectures/commit/b4e1d10ebb25481971fc56ac3845051aa47e8566","type":"code","group":"primary","domain":"github.com"},{"n":13,"title":"Hexagon 2610.00569","url":"https://hexagonmath.org/abs/2610.00569","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":14,"title":"Hexagon 2610.00570","url":"https://hexagonmath.org/abs/2610.00570","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":15,"title":"Hexagon 2610.00576","url":"https://hexagonmath.org/abs/2610.00576","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":16,"title":"Hexagon 2610.00581","url":"https://hexagonmath.org/abs/2610.00581","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":17,"title":"Hexagon 2610.00582","url":"https://hexagonmath.org/abs/2610.00582","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":18,"title":"Hexagon 2610.00587","url":"https://hexagonmath.org/abs/2610.00587","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":19,"title":"Hexagon 2610.00700","url":"https://hexagonmath.org/abs/2610.00700","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":20,"title":"Hexagon 2610.00701","url":"https://hexagonmath.org/abs/2610.00701","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":21,"title":"Hexagon 2610.00702","url":"https://hexagonmath.org/abs/2610.00702","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":22,"title":"Hexagon 2610.00703","url":"https://hexagonmath.org/abs/2610.00703","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":23,"title":"Hexagon 2610.00704","url":"https://hexagonmath.org/abs/2610.00704","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":24,"title":"Hexagon 2610.00705","url":"https://hexagonmath.org/abs/2610.00705","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":25,"title":"Hexagon 2610.00706","url":"https://hexagonmath.org/abs/2610.00706","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":26,"title":"Hexagon 2610.00707","url":"https://hexagonmath.org/abs/2610.00707","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":27,"title":"Hexagon 2610.00708","url":"https://hexagonmath.org/abs/2610.00708","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":28,"title":"Hexagon 2610.00709","url":"https://hexagonmath.org/abs/2610.00709","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":29,"title":"Hexagon 2610.00714","url":"https://hexagonmath.org/abs/2610.00714","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":30,"title":"Hexagon 2610.00715","url":"https://hexagonmath.org/abs/2610.00715","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":31,"title":"Hexagon 2610.00716","url":"https://hexagonmath.org/abs/2610.00716","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":32,"title":"Hexagon 2610.00718","url":"https://hexagonmath.org/abs/2610.00718","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":33,"title":"Hexagon 2610.00732","url":"https://hexagonmath.org/abs/2610.00732","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":34,"title":"Hexagon 2610.00733","url":"https://hexagonmath.org/abs/2610.00733","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":35,"title":"Hexagon 2610.00734","url":"https://hexagonmath.org/abs/2610.00734","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":36,"title":"Hexagon 2610.00735","url":"https://hexagonmath.org/abs/2610.00735","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":37,"title":"Hexagon 2611.00001","url":"https://hexagonmath.org/abs/2611.00001","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":38,"title":"Hexagon 2611.00002","url":"https://hexagonmath.org/abs/2611.00002","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":39,"title":"Hexagon 2611.00003","url":"https://hexagonmath.org/abs/2611.00003","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":40,"title":"Hexagon 2611.00004","url":"https://hexagonmath.org/abs/2611.00004","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":41,"title":"Hexagon 2611.00005","url":"https://hexagonmath.org/abs/2611.00005","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":42,"title":"Hexagon 2611.00007","url":"https://hexagonmath.org/abs/2611.00007","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":43,"title":"Hexagon 2611.00008","url":"https://hexagonmath.org/abs/2611.00008","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":44,"title":"Hexagon 2611.00009","url":"https://hexagonmath.org/abs/2611.00009","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":45,"title":"Hexagon 2611.00010","url":"https://hexagonmath.org/abs/2611.00010","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":46,"title":"Hexagon 2611.00011","url":"https://hexagonmath.org/abs/2611.00011","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":47,"title":"Hexagon 2611.00012","url":"https://hexagonmath.org/abs/2611.00012","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":48,"title":"Hexagon 2611.00013","url":"https://hexagonmath.org/abs/2611.00013","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":49,"title":"Hexagon 2611.00016","url":"https://hexagonmath.org/abs/2611.00016","type":"paper","group":"primary","domain":"hexagonmath.org"},{"n":50,"title":"Hexagon 2611.00019","url":"https://hexagonmath.org/abs/2611.00019","type":"paper","group":"primary","domain":"hexagonmath.org"}],"official":50,"filed":"2026-11-02","updated":"2026-11-02","orgs":["OpenAI","Anthropic","various researchers"],"title":"AI-assisted results in the 2 Nov 2026 sweep: Haagerup's 1985 problem, Petz's 1994 conjecture, Kamnitzer's MV = theta conjecture, Morel purity counterexamples, claw-free perfect graphs, plus 52 Hexagon works","summary":"Catalogue of AI-disclosing papers from the arXiv announcement of 2 Nov 2026 (submissions of 29–30 Oct), the Hexagon works of 1–2 Nov not cited before, and the result-repository commits of 1 Nov, beyond the items with their own entries. AI statements are quoted from PDFs or Hexagon provenance records (Hexagon does not judge correctness); none of these papers is refereed.","key_facts":["Own entries from this sweep: 2026-09-20-kung-traub-conjecture-proved-colbrook-lean-chatgpt (arXiv 2610.40660), 2026-10-30-alon-krivelevich-conjecture-disproved-gpt-6-astra-xean (arXiv 2610.42094), 2026-10-30-hopfield-model-thermodynamic-limit-barra-durante-claude-chatgpt (arXiv 2610.41938)","Operator algebras: Rui Okayasu (arXiv 2610.41746) proves a von Neumann algebra N is injective iff ‖T‖dec = ‖T‖cb for every map ℓ∞₃ → N, answering Haagerup's 1985 Problem 3.8 (recorded as open by Pisier). AI statement: 'This work was carried out in collaboration with an AI system (Claude Opus 5.5). The main argument was developed in discussions between the author and the AI system, and the manuscript was drafted mainly by the AI system. The author has verified all proofs'","Quantum information geometry: Suvrit Sra, 'A Proof of Petz's Conjecture on the Scalar Curvature of the Kubo–Mori Metric' (Hexagon 2610.00717): Petz (1994) conjectured the scalar curvature increases as the state becomes more mixed; Dittmann (2000) reduced it to concavity of a function h, proved here via a Stieltjes-function argument. Provenance: mixed, all parts understood by a human; 'developed with an AI assistant (OpenAI's GPT Pro). None of the claims were obtained zero-shot'. Sra posted 21 more Hexagon works on 1–2 Nov (Hexagon 2610.00718–2610.00732: q-Foulkes problem I–III, Macdonald (q,t)-permanent I–II, a Koteljanskii inequality for permanents, a sharp Brégman–Minc bound, Wigner–Yanase–Dyson metrics with monotone curvature, p-Bures–Wasserstein distance, lower bounds for the quantum permanent, Turán-ratio monotonicity, theta-kernel sign regularity, Jack/Macdonald majorization, Schur forms; GPT Pro, GPT-6 Astra, Claude Opus 5.5, Fable 5.1)","Representation theory: Qiyue Tang (Tsinghua), 'Equality of the Mirković–Vilonen and theta bases' (Hexagon 2611.00006) claims Kamnitzer's ICM 2022 conjecture. Provenance: seven ChatGPT-6-Pro conversations (~23 h), Pharos, Codex; 'This was the first time Rethlas-OSV identified a nontrivial error in my work that invalidated the proof of the main theorem'; ChatGPT-6-Pro repaired it in six hours, a second Rethlas-OSV review found further errors including 'one that again blocked the proof as written', which were corrected; only 'some parts' checked by a human. Also Tang: full Fock–Goncharov criterion via positive polytopes (Hexagon 2611.00015; the GHKK interior criterion, ChatGPT-6-Pro session of ~270 min), Huang–Wang conjectures on projected stated SL_n skein algebras (Hexagon 2611.00013), Markov–Euclid asymptotics (Hexagon 2611.00002); see also Hexagon 2610.00587 (Davison–Mandel Conjectures 1.4, 2.17, 3.13 and Davison's ICM 2026 two-wall conjecture, GPT-6-Astra-Pro, passed Rethlas-OSV)","Motivic homotopy: Niels Feld (Rennes), 'Gersten injectivity and Morel's purity conjecture' (Hexagon 2611.00017): failure of Gersten injectivity at a henselian regular local ring gives a counterexample to Morel's purity conjecture. Provenance: primarily AI-generated, all parts understood by a human; drafted with GPT-6 Astra, revised with Claude Opus 5.5, adversarial referee report by GPT-6 Astra","Graph colouring: Narayanan Narayanan, Suchismita Mishra, Umesh Shankar (IIT Madras), claw-free perfect graphs satisfy ch(G) = χ(G) = ω(G) (Hexagon 2610.00713; 'The proofs have been written by hand and verified by the authors'; Claude and GPT-6 helped formalize some arguments). Also arXiv: Cranston–Li–Su–Wang–Xu (2026) conjecture 'done overwhelmingly by AI models' (2610.40863); treedepth NP-hard on planar max-degree-3 graphs, 'The idea for the reduction was suggested by Claude Opus 5.5' (2610.42033)","Other arXiv items with AI statements: entropic c-theorem proof (hep-th 2610.40874; 'Claude and ChatGPT for development of arguments'); metric Zariski multiplicity conjecture in dimension 4 (2610.41954; Claude and Gemini 'to refine arguments'); Graham's rearrangement problem in finite abelian groups (2610.40712; ChatGPT for the absorption argument); maximal determinant of order 15 over third roots of unity (2610.40679); Haiman's conjecture for n ≤ 10 by computation (2610.41555); a Tasaki LLM-generated extension cited in a weak-Gibbsianity counterexample (2610.41871); a Nagata–Biran–Szemberg note written while studying OpenAI manuscripts (2610.41931); Novikov-conjecture paper used ChatGPT only for language (2610.40062)","Hexagon, AI-run deposits with no human check ('understanding: none'), stated as claims only: David Niedbala Giraudin, Korenblum's constant c₂ ≥ 0.446 (2611.00014), trefoil distortion bound (2611.00012), Vitorino–Vukusic Problem 5 (2611.00009), torus-knot ropelength (2611.00008), q-Markoff coincidences answering Labbé–Lapointe–Steiner (2611.00005), Chvátal–Sankoff upper bounds (2610.00709), Yamada's constant 283 lowered to 69 (2610.00707) and three p-adic linear-forms papers (2610.00704, 2610.00706, 2610.00708); Qidong He, hard-sphere density coexistence (2610.00734); Alon Schechter, illumination bounds (2611.00007, 2611.00010, 2611.00011); Daniel Adam Pyle with 'Lyra' (2610.00700, 2610.00701)","Hexagon, other: Teo Banica, the S_N ⊂ S_N^+ maximality conjecture revisited, 'Written by Claude Opus' (2611.00001, survey-type, no claimed proof); Jason Davies, the ten minimum universal sets of MacMahon cubes, Lean (2611.00016); Peter W. Murphy, de Bruijn–Newman constant ≤ 9/32 for real primitive Dirichlet L-functions in Lean, 'The mathematics is not new' (2610.00714); Mihaly Csirik, Pauli–Fierz density functionals in Lean (2610.00715); Troy Winarski, 7/8 zero-free half-plane for angular Hecke L-functions (2610.00716); Troy Tri Nguyen, sublinear treewidth exponent for binary CSP (2611.00004); Joseph Shunia, deterministic factorization in 2^{O(n/√log n)} building on 'OpenAI's quantitative Boolean tensor-contraction theorem' (2610.00711); Shuta Iwai, counterexamples to Guy's mex problem E27, Claude for computation only (2610.00735); Khai-Hoan Nguyen-Dang (2611.00019); Arhancet, Haagerup VOAs at c = 8 (2610.00733); Ilmar Gahramanov (2610.00705); Frank Vega, Robin/Nicolas inequality partial results and an MIS algorithm, not proofs of RH or P = NP (2610.00702, 2610.00703); human-written: K. Mahesh Krishna (2611.00003)","Hexagon backlog (8 lines processed): Lucas Almeida, answering Camargo–Ordoñez–Ramírez with a continuum whose regular-subcontinua hyperspace is the irrationals, Lean, 'No independent expert has yet verified' (2610.00570); Bogdan Grechuk, polynomial parametrizations for two classes of Diophantine equations with ChatGPT/Codex (2610.00569); Roelof van Dijk, a proof of Gauss's class-number-one conjecture from mathematics Gauss could have known, answering Ben Green's variant of Tao's challenge, with GPT-6 Astra and Opus 5.5, understanding 'none' (2610.00568); Hangang Wang, type-D braid deformations (2610.00581); Sida He (2610.00582, unchecked); K. Mahesh Krishna (2610.00576, human); Qiyue Tang (2610.00587, above)","Result repositories (1 Nov): google-deepmind/formal-conjectures recorded a negative answer to Kourovka 19.25, a normal-subgroup counterexample for Kourovka 20.76, an increasing counterexample for Erdős 263, negated OEIS A51903 conjecture 2, added statements of Erdős 831, 963 and 1152, and linked formal proofs for the Poisson conjecture (already in the 1 Nov listing). No new openai/math or anthropics/formal-math families. GitHub: google-deepmind/gbench, detectorscope and QwenLM/BlenderWorld are tooling, no results","Checked, no AI statement in the list of conjecture papers: Berger conjecture in dimension 3 (2610.41006), Segal conjecture papers (2610.40209, 2610.39440), Terao's conjecture for ≤ 9 planes (2610.40028), Michael's problem (2610.39260), Carlet–Solé counterexample (2610.36687), Hofbauer–Kon–Saito counterexample (2610.38374), Hibi–Li conjecture (2610.40703)"],"key_numbers":[],"tags":["math","physics","arxiv","hexagon","catalogue","chatgpt","gpt-6-astra","gpt-6-pro","gpt-6-1-sol","claude","claude-opus-5-5","claude-fable-5-1","codex","lean"],"science":{"field":"mathematics","subfield":"multiple (operator algebras, representation theory, motivic homotopy, graph theory, number theory, quantum information)","problem":"See list","result":"Catalogue of AI-disclosing papers of 1–2 Nov beyond those with their own entries","open_since":"","ai_system":["ChatGPT","GPT Pro","GPT-6 Astra","GPT-6 Pro","GPT-6.1 Sol","Codex","Claude Opus 5.5","Claude Fable 5.1","Gemini"],"human_role":"From human proofs with AI help (Narayanan et al., Sra) to unchecked AI output (Niedbala Giraudin, He, Pyle)","verification":{"key":"lean","label":"Lean-verified","text":"Unrefereed preprints and Hexagon deposits; Lean for some"},"status":"pending","shock":"","verified_by":["preprint","lean"],"kind":"batch"},"body_md":"## What happened\n\nSee key facts. The items of note beyond the three own entries are Okayasu's answer to Haagerup's problem (manuscript \"drafted mainly by the AI system\"), Sra's proof of Petz's conjecture, and Tang's claimed MV = theta equality, whose provenance record documents an AI reviewer (Rethlas-OSV) twice finding errors that blocked the main proof before it passed.\n\n## Why it matters\n\nThe share of senior authors crediting models with central arguments keeps growing; Hexagon deposits with no human check also keep growing, and we list those as claims only.","disputed":[{"label":"Verification","text":"Unrefereed preprints and Hexagon deposits; Lean for some","sources":[]}],"related":[{"id":"2026-11-01-ai-assisted-results-november-1-listing","url":"https://postcutoff.com/e/2026-11-01-ai-assisted-results-november-1-listing/","date":"2026-11-01","date_precision":"day","short_title":"AI-assisted results, 1 Nov: arXiv leftovers and result repos","deck":null,"takeaway":"The 1 Nov sweep listed 325 arXiv papers that mention AI (mostly already-skimmed submissions of 26–29 Oct) and 66 conjecture papers without an AI statement. No new result reached own-entry level. Listed here: Chao Liu's f(k) = k²/2 + O(k log k) for subset sums of zero-sum-free sets ('AI tools developed by OpenAI were used'), Bednorz–Łochowski's proof of the Das–Łochowski–Matsuda–Perkowski fBm conjecture with ChatGPT proof strategies, Gao–Zhao on Duke–Erdős–Rödl, and a Lean proof (drafted with Claude Code) of Long's ChatGPT-assisted Poisson conjecture counterexample.","category":"science","category_label":"Science & math","importance":2,"confidence":"medium","status":{"key":"pending","labels":["Awaiting review"]},"sources":13,"official":13,"filed":"2026-11-01","updated":"2026-11-01","orgs":["OpenAI","Anthropic","Google","various researchers"]},{"id":"2026-10-31-ai-assisted-results-october-31-listing","url":"https://postcutoff.com/e/2026-10-31-ai-assisted-results-october-31-listing/","date":"2026-10-31","date_precision":"day","short_title":"AI-assisted results, 31 Oct: arXiv of 30 Oct and Hexagon of 29–31 Oct","deck":null,"takeaway":"The 31 Oct sweep listed 344 arXiv papers that mention AI, 75 conjecture papers with no AI statement and 48 uncited Hexagon works. We skimmed every AI statement and read about 70 PDFs or Hexagon records. Seven results got their own entries. Two come from senior authors: Panchenko's Mézard–Parisi formula ('found by ChatGPT Astra') and Bhargava's positive-density cyclicity of elliptic curves, written with GPT-6. The other five are Tianchi Yang's count of C₄-free graphs, Kolpakov's sharp dimension bounds for right-angled hyperbolic polytopes, the generalized Lax conjecture (Kummer–Netzer's AI-found generic case and OpenAI's counterexample), Diening–Storn's AFEM optimality for every bulk parameter, and an unverified GPT-6 Astra claim on Onsager's hard rods. The rest are listed here, among them Pongrácz's R(5,6) ≤ 84 certificate with GPT-6 Astra and Bowler–Pitz's negative answers to Halin-type questions, where Claude found key lemmas.","category":"science","category_label":"Science & math","importance":2,"confidence":"medium","status":{"key":"pending","labels":["Awaiting review"]},"sources":44,"official":42,"filed":"2026-10-31","updated":"2026-10-31","orgs":["OpenAI","Anthropic","Google","various researchers"]}],"people":[{"id":"terence-tao","name":"Terence Tao","url":"https://postcutoff.com/person/terence-tao/"},{"id":"hal-tasaki","name":"Hal Tasaki","url":"https://postcutoff.com/person/hal-tasaki/"}],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-11-03","type":"edit","text":"Added Hexagon links for works named only in text"},{"date":"2026-11-02","type":"filed","text":"Created from the 2 Nov sweep"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-11-02","run":null,"sources_read":"The 2 Nov sweep","updated":"2026-11-02","human_review":null,"version":{"date":"2026-11-03"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":186,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":125,"in_training_data":false},{"model_id":"gemini-4-argon","name":"Gemini 4 Argon","cutoff":"2026-03","days_after":216,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":155,"in_training_data":false}],"short_url":null}