{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/estimate-tokens","entry":"estimate_tokens","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":11,"n_papers_ran":8,"n_papers_ran_no_instrument_failure":8,"n_papers_ran_instrument_only":0,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":10,"n_samples_ran":8,"n_samples_constructed":0,"n_samples_ran_checked":8,"n_samples_instrument":0,"n_samples_unverified":2,"n_samples_fingerprinted":8,"n_places":11,"n_places_pointer_only":3,"n_places_pointer_only_link_open":1,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":8,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":2},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2608.23473","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2608-23473","title":"METACASTER: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"D2I-Group/metacaster","path":"optimizer/core/compact.py","file_url":"https://github.com/D2I-Group/metacaster/blob/HEAD/optimizer/core/compact.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"cf53dda026754631","code_sha256_prefix":"cf53dda026754631","mcp_get_code":{"code_sha256":"cf53dda026754631"}},{"arxiv_id":"2608.01678","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2608-01678","title":"Progressive Agent Skill Generation via Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"ejhshen/skill-alpha","path":"src/skill_alpha_rl/evidence.py","file_url":"https://github.com/ejhshen/skill-alpha/blob/HEAD/src/skill_alpha_rl/evidence.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"42ec3fc2aa499953","code_sha256_prefix":"42ec3fc2aa499953","mcp_get_code":{"code_sha256":"42ec3fc2aa499953"}},{"arxiv_id":"2606.26105","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-26105","title":"Context Recycling for Long-Horizon LLM Inference A Hierarchical Memory Architecture for Managing Fixed Context Budgets Across Unbounded Sessions","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Betanu701/ContextForge","path":"contextforge/utils.py","file_url":"https://github.com/Betanu701/ContextForge/blob/HEAD/contextforge/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"7ce1a282af6f0cdf","code_sha256_prefix":"7ce1a282af6f0cdf","mcp_get_code":{"code_sha256":"7ce1a282af6f0cdf"}},{"arxiv_id":"2605.03824","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-03824","title":"Reproducing Complex Set-Compositional Information Retrieval","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"informagi/Complex-Set-Compositional-IR","path":"code/cost_estimates/estimate_reranking_costs.py","file_url":"https://github.com/informagi/Complex-Set-Compositional-IR/blob/HEAD/code/cost_estimates/estimate_reranking_costs.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, informagi/Complex-Set-Compositional-IR when it was checked","code_sha256":"f3eaa6a2a6acbc45","code_sha256_prefix":"f3eaa6a2a6acbc45","mcp_get_code":{"code_sha256":"f3eaa6a2a6acbc45"}},{"arxiv_id":"2605.00800","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-00800","title":"Generating Statistical Charts with Validation-Driven LLM Workflows","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"pavlin-policar/llm-chart-generation","path":"generation_pipeline/evaluation_online.py","file_url":"https://github.com/pavlin-policar/llm-chart-generation/blob/HEAD/generation_pipeline/evaluation_online.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"c06cfd129bafce2f","code_sha256_prefix":"c06cfd129bafce2f","mcp_get_code":{"code_sha256":"c06cfd129bafce2f"}},{"arxiv_id":"2512.03318","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2512-03318","title":"Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"google-deepmind/concordia","path":"concordia/language_model/profiled_language_model.py","file_url":"https://github.com/google-deepmind/concordia/blob/HEAD/concordia/language_model/profiled_language_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"fca5c365c153c9fb","code_sha256_prefix":"fca5c365c153c9fb","mcp_get_code":{"code_sha256":"fca5c365c153c9fb"}},{"arxiv_id":"2510.21891","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2510-21891","title":"Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"dhrupadb/semantic_isotropy","path":"lib/python/semantic_isotropy/llm/utils.py","file_url":"https://github.com/dhrupadb/semantic_isotropy/blob/HEAD/lib/python/semantic_isotropy/llm/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"57836e516ed482b0","code_sha256_prefix":"57836e516ed482b0","mcp_get_code":{"code_sha256":"57836e516ed482b0"}},{"arxiv_id":"2510.10454","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2510-10454","title":"Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"zengsihang/Traj-CoA","path":"model/run_coa_batch.py","file_url":"https://github.com/zengsihang/Traj-CoA/blob/HEAD/model/run_coa_batch.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"1da8decd4ccf7a5e","code_sha256_prefix":"1da8decd4ccf7a5e","mcp_get_code":{"code_sha256":"1da8decd4ccf7a5e"}},{"arxiv_id":"2508.06361","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2508-06361","title":"Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"Xtra-Computing/LLM-Deception","path":"src/llm/ask_openai.py","file_url":"https://github.com/Xtra-Computing/LLM-Deception/blob/HEAD/src/llm/ask_openai.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f325f37cde5f70c7","code_sha256_prefix":"f325f37cde5f70c7","mcp_get_code":{"code_sha256":"f325f37cde5f70c7"}},{"arxiv_id":"2408.14033","arxiv_id_is_arxiv":true,"paper":"/paper/mlr-copilot-autonomous-machine-learning","title":"MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents","date":"2024-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"du-nlp-lab/mlr-copilot","path":"reactagent/plot.py","file_url":"https://github.com/du-nlp-lab/mlr-copilot/blob/HEAD/reactagent/plot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, du-nlp-lab/mlr-copilot when it was checked","code_sha256":"9c55f0596ab5430b","code_sha256_prefix":"9c55f0596ab5430b","mcp_get_code":{"code_sha256":"9c55f0596ab5430b"}},{"arxiv_id":"2310.03302","arxiv_id_is_arxiv":true,"paper":"/paper/benchmarking-large-language-models-as-ai","title":"MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation","date":"2023-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"snap-stanford/mlagentbench","path":"MLAgentBench/plot.py","file_url":"https://github.com/snap-stanford/mlagentbench/blob/HEAD/MLAgentBench/plot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from du-nlp-lab/mlr-copilot, and GitHub detected no licence in that repository when it was checked","code_sha256":"9c55f0596ab5430b","code_sha256_prefix":"9c55f0596ab5430b","mcp_get_code":{"code_sha256":"9c55f0596ab5430b"}}],"record_sha256":"cc5e321da4d0bb49d14a331acabb7b0c15a5100dc9a7a0c6ba8f51bb704cbfe5","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}