{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/bootstrap-ci","entry":"bootstrap_ci","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+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.","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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":21,"n_papers_ran":11,"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":22,"n_samples_ran":11,"n_samples_fingerprinted":1,"n_places":22,"n_places_pointer_only":11,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":10,"unverified":11},"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":"2609.01737","paper":"/paper/arxiv-2609-01737","title":"SpeakPay: Domain-Adaptive LoRA Fine-Tuning of Whisper for Low-Resource Nepali Financial Speech Recognition","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"subedibiraj/speakpay","path":"analysis/paired_stats.py","file_url":"https://github.com/subedibiraj/speakpay/blob/HEAD/analysis/paired_stats.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"1f508fe30be24829","mcp_get_code":{"code_sha256":"1f508fe30be24829"}},{"arxiv_id":"2608.08212","paper":"/paper/arxiv-2608-08212","title":"Harmful Content Is Not Enough: Continuation Framing Moderates In-Context Emergent Misalignment","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"PeiYangLiu/icl-em-format-control","path":"run_format_ladder.py","file_url":"https://github.com/PeiYangLiu/icl-em-format-control/blob/HEAD/run_format_ladder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6a64b07ad6ec3174","mcp_get_code":{"code_sha256":"6a64b07ad6ec3174"}},{"arxiv_id":"2608.02376","paper":"/paper/arxiv-2608-02376","title":"Token-Native Storage: Read and Write in your Agent's Language","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"kshivendu/token-storage","path":"tnbench.py","file_url":"https://github.com/kshivendu/token-storage/blob/HEAD/tnbench.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"110289b21bbb0650","mcp_get_code":{"code_sha256":"110289b21bbb0650"}},{"arxiv_id":"2608.00198","paper":"/paper/arxiv-2608-00198","title":"AutoCause: A Python framework that automates expert decisions in environmental time-series causal discovery","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"marcoruizrueda/autocause","path":"experiments/make_figures.py","file_url":"https://github.com/marcoruizrueda/autocause/blob/HEAD/experiments/make_figures.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"d896e199cf6742f2","mcp_get_code":{"code_sha256":"d896e199cf6742f2"}},{"arxiv_id":"2608.00107","paper":"/paper/arxiv-2608-00107","title":"MetaRoute-Bench: Evaluating Meta-Decision Policies for Agentic Workflows","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"anote-ai/research-coageneration","path":"src/coageneration/evaluate.py","file_url":"https://github.com/anote-ai/research-coageneration/blob/HEAD/src/coageneration/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ab36e1f9e98f916e","mcp_get_code":{"code_sha256":"ab36e1f9e98f916e"}},{"arxiv_id":"2607.12166","paper":"/paper/arxiv-2607-12166","title":"From Geometric Recovery to Causal Validation: A Reproducible Audit of Sparse Autoencoder Features, from Superposition Geometry to Causal Inertness","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"mohamed-bal/sae-causal-audit","path":"src/sae_causal_audit/stats.py","file_url":"https://github.com/mohamed-bal/sae-causal-audit/blob/HEAD/src/sae_causal_audit/stats.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cd4f9aebcb38b4ea","mcp_get_code":{"code_sha256":"cd4f9aebcb38b4ea"}},{"arxiv_id":"2607.04926","paper":"/paper/arxiv-2607-04926","title":"Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"otanl/microground","path":"src/mg/stats.py","file_url":"https://github.com/otanl/microground/blob/HEAD/src/mg/stats.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"04ba6354ee69f1e7","mcp_get_code":{"code_sha256":"04ba6354ee69f1e7"}},{"arxiv_id":"2606.19542","paper":"/paper/arxiv-2606-19542","title":"Tracking Representation Dynamics in Large Language Models with Persistent Homology","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"malhotranaman/tracking-representation-dynamics-with-persistent-homology","path":"src/phlatent/analysis/stats.py","file_url":"https://github.com/malhotranaman/tracking-representation-dynamics-with-persistent-homology/blob/HEAD/src/phlatent/analysis/stats.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"51eac5b0969514f0","mcp_get_code":{"code_sha256":"51eac5b0969514f0"}},{"arxiv_id":"2605.28639","paper":"/paper/arxiv-2605-28639","title":"The Attentional White Bear Effect in Transformer Language Models","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"rramnauth2220/representational-suppression","path":"exp3_leakage.py","file_url":"https://github.com/rramnauth2220/representational-suppression/blob/HEAD/exp3_leakage.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4feb492ff1638591","mcp_get_code":{"code_sha256":"4feb492ff1638591"}},{"arxiv_id":"2605.25894","paper":"/paper/arxiv-2605-25894","title":"Predicting Stock Price Direction on Earnings Announcement Days using Multi-modal Deep Learning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Marc0-Pol0/dl-project","path":"src/models/analysis.py","file_url":"https://github.com/Marc0-Pol0/dl-project/blob/HEAD/src/models/analysis.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6d3e065903114032","mcp_get_code":{"code_sha256":"6d3e065903114032"}},{"arxiv_id":"2605.02520","paper":"/paper/arxiv-2605-02520","title":"Benchmarking Retrieval Strategies for Biomedical Retrieval-Augmented Generation: A Controlled Empirical Study 1","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"deviprasadbal/RAGHealthcareRetrievalStrategies","path":"src/evaluation/statistics.py","file_url":"https://github.com/deviprasadbal/RAGHealthcareRetrievalStrategies/blob/HEAD/src/evaluation/statistics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3680d2d091fad4d9","mcp_get_code":{"code_sha256":"3680d2d091fad4d9"}},{"arxiv_id":"2604.12076","paper":"/paper/arxiv-2604-12076","title":"Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Starscream-11813/IVE-LLM","path":"analysis/statistical_tests.py","file_url":"https://github.com/Starscream-11813/IVE-LLM/blob/HEAD/analysis/statistical_tests.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87a3a02837b502be","mcp_get_code":{"code_sha256":"87a3a02837b502be"}},{"arxiv_id":"2604.06199","paper":"/paper/arxiv-2604-06199","title":"Emergent decentralized regulation in a purely synthetic society","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"manikm-114/OpenClaw_V2","path":"codes/event_aligned_bootstrap_ci.py","file_url":"https://github.com/manikm-114/OpenClaw_V2/blob/HEAD/codes/event_aligned_bootstrap_ci.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"353ebc667dc54ac3","mcp_get_code":{"code_sha256":"353ebc667dc54ac3"}},{"arxiv_id":"2604.04756","paper":"/paper/arxiv-2604-04756","title":"Darkness Visible: Reading the Exception Handler of a Language Model","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"pbalogh/transparent-gpt2","path":"code/bootstrap_crossover.py","file_url":"https://github.com/pbalogh/transparent-gpt2/blob/HEAD/code/bootstrap_crossover.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e89cb415771641de","mcp_get_code":{"code_sha256":"e89cb415771641de"}},{"arxiv_id":"2603.25960","paper":"/paper/arxiv-2603-25960","title":"When Chain-of-Thought Backfires: Evaluating Prompt Sensitivity in Medical Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"UNHSAILLab/MedMCQA-Robustness-Study","path":"src/evaluation/significance.py","file_url":"https://github.com/UNHSAILLab/MedMCQA-Robustness-Study/blob/HEAD/src/evaluation/significance.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3d7619274b44eb70","mcp_get_code":{"code_sha256":"3d7619274b44eb70"}},{"arxiv_id":"2603.19532","paper":"/paper/arxiv-2603-19532","title":"EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Wizaaard/EvidenceRL","path":"paper_metrics.py","file_url":"https://github.com/Wizaaard/EvidenceRL/blob/HEAD/paper_metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f24bdeccaef4e732","mcp_get_code":{"code_sha256":"f24bdeccaef4e732"}},{"arxiv_id":"2603.19532","paper":"/paper/arxiv-2603-19532","title":"EvidenceRL: Reinforcing Evidence Consistency for Trustworthy Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Wizaaard/EvidenceRL","path":"paper_metrics_barexam.py","file_url":"https://github.com/Wizaaard/EvidenceRL/blob/HEAD/paper_metrics_barexam.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ee03322d6a1ef5c","mcp_get_code":{"code_sha256":"3ee03322d6a1ef5c"}},{"arxiv_id":"2601.20336","paper":"/paper/arxiv-2601-20336","title":"Are Whitepaper Claims Reflected in Market Structure? A Contamination-Aware Pipeline and a Power-Limited Null","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"studiofarzulla/whitepaper-claims","path":"src/alignment/matched_dimension_analysis.py","file_url":"https://github.com/studiofarzulla/whitepaper-claims/blob/HEAD/src/alignment/matched_dimension_analysis.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a23f3839108f6ef6","mcp_get_code":{"code_sha256":"a23f3839108f6ef6"}},{"arxiv_id":"2505.19212","paper":"/paper/when-ethics-and-payoffs-diverge-llm-agents-in","title":"When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas","date":"2025-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sbackmann/moralsim","path":"src/moralsim/analysis/importance.py","file_url":"https://github.com/sbackmann/moralsim/blob/HEAD/src/moralsim/analysis/importance.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f7a82919e34e71e3","mcp_get_code":{"code_sha256":"f7a82919e34e71e3"}},{"arxiv_id":"2503.01838","paper":"/paper/grain-exact-graph-reconstruction-from","title":"GRAIN: Exact Graph Reconstruction from Gradients","date":"2025-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"insait-institute/grain","path":"src/extract_neptune.py","file_url":"https://github.com/insait-institute/grain/blob/HEAD/src/extract_neptune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fda60abed9a9f350","mcp_get_code":{"code_sha256":"fda60abed9a9f350"}},{"arxiv_id":"2309.06490","paper":"/paper/leveraging-large-language-models-for-1","title":"Leveraging Large Language Models for Automated Dialogue Analysis","date":"2023-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"emorynlp/gpt-abceval","path":"gpt_interface/metric_utils.py","file_url":"https://github.com/emorynlp/gpt-abceval/blob/HEAD/gpt_interface/metric_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5147c781ddd64cf8","mcp_get_code":{"code_sha256":"5147c781ddd64cf8"}},{"arxiv_id":"2306.01711","paper":"/paper/omni-open-endedness-via-models-of-human","title":"OMNI: Open-endedness via Models of human Notions of Interestingness","date":"2023-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jennyzzt/omni","path":"generate_plots.py","file_url":"https://github.com/jennyzzt/omni/blob/HEAD/generate_plots.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54605b21a391ad5d","mcp_get_code":{"code_sha256":"54605b21a391ad5d"}}]}