{"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/get-output","entry":"get_output","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":19,"n_papers_ran":6,"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":15,"n_samples_ran":6,"n_samples_fingerprinted":1,"n_places":21,"n_places_pointer_only":8,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":4,"unverified":9},"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":"2604.00536","paper":"/paper/arxiv-2604-00536","title":"Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"FanZT6/OptimSyn","path":"training/influence/collect_grad_reps.py","file_url":"https://github.com/FanZT6/OptimSyn/blob/HEAD/training/influence/collect_grad_reps.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"808c09bce5840bb9","mcp_get_code":{"code_sha256":"808c09bce5840bb9"}},{"arxiv_id":"2602.08351","paper":"/paper/arxiv-2602-08351","title":"The Chicken and Egg Dilemma: Co-optimizing Data and Model Configurations for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"princeton-nlp/LESS","path":"less/data_selection/collect_grad_reps.py","file_url":"https://github.com/princeton-nlp/LESS/blob/HEAD/less/data_selection/collect_grad_reps.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"808c09bce5840bb9","mcp_get_code":{"code_sha256":"808c09bce5840bb9"}},{"arxiv_id":"2504.19095","paper":"/paper/efficient-reasoning-for-llms-through","title":"Efficient Reasoning for LLMs through Speculative Chain-of-Thought","date":"2025-04-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jikai0wang/speculative_cot","path":"speculative_cot.py","file_url":"https://github.com/jikai0wang/speculative_cot/blob/HEAD/speculative_cot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1bd40ab615e471b3","mcp_get_code":{"code_sha256":"1bd40ab615e471b3"}},{"arxiv_id":"2502.11986","paper":"/paper/selective-task-group-updates-for-multi-task","title":"Selective Task Group Updates for Multi-Task Optimization","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wooseong97/sel-update-mtl","path":"sel-update-mtl/utils/train_utils.py","file_url":"https://github.com/wooseong97/sel-update-mtl/blob/HEAD/sel-update-mtl/utils/train_utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a64ab65acb301c2d","mcp_get_code":{"code_sha256":"a64ab65acb301c2d"}},{"arxiv_id":"2411.12882","paper":"/paper/prosec-fortifying-code-llms-with-proactive","title":"ProSec: Fortifying Code LLMs with Proactive Security Alignment","date":"2024-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PurCL/ProSec","path":"influence_score/collect_grad_reps.py","file_url":"https://github.com/PurCL/ProSec/blob/HEAD/influence_score/collect_grad_reps.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"808c09bce5840bb9","mcp_get_code":{"code_sha256":"808c09bce5840bb9"}},{"arxiv_id":"2410.00485","paper":"/paper/a-hitchhikers-guide-to-fine-grained-face","title":"A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning","date":"2024-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NickyFot/HitchhikersGuide","path":"train_utils.py","file_url":"https://github.com/NickyFot/HitchhikersGuide/blob/HEAD/train_utils.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":"49df55f4e08b2e03","mcp_get_code":{"code_sha256":"49df55f4e08b2e03"}},{"arxiv_id":"2407.15235","paper":"/paper/tagcos-task-agnostic-gradient-clustered","title":"TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data","date":"2024-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"2003pro/tagcos","path":"data_selection/collect_grad_reps.py","file_url":"https://github.com/2003pro/tagcos/blob/HEAD/data_selection/collect_grad_reps.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"808c09bce5840bb9","mcp_get_code":{"code_sha256":"808c09bce5840bb9"}},{"arxiv_id":"2405.11290","paper":"/paper/mbias-mitigating-bias-in-large-language","title":"MBIAS: Mitigating Bias in Large Language Models While Retaining Context","date":"2024-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shainarazavi/mbias","path":"mbias/batch_inference.py","file_url":"https://github.com/shainarazavi/mbias/blob/HEAD/mbias/batch_inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6d2dc89f4906735d","mcp_get_code":{"code_sha256":"6d2dc89f4906735d"}},{"arxiv_id":"2403.00425","paper":"/paper/halc-object-hallucination-reduction-via","title":"HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding","date":"2024-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BillChan226/HALC","path":"models/preprocessor.py","file_url":"https://github.com/BillChan226/HALC/blob/HEAD/models/preprocessor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8122965ad6131653","mcp_get_code":{"code_sha256":"8122965ad6131653"}},{"arxiv_id":"2403.00425","paper":"/paper/halc-object-hallucination-reduction-via","title":"HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding","date":"2024-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BillChan226/HALC","path":"models/refiner.py","file_url":"https://github.com/BillChan226/HALC/blob/HEAD/models/refiner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3cc2c9efff7e5609","mcp_get_code":{"code_sha256":"3cc2c9efff7e5609"}},{"arxiv_id":"2402.16906","paper":"/paper/ldb-a-large-language-model-debugger-via","title":"Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"floridsleeves/llmdebugger","path":"programming/executors/py_executor.py","file_url":"https://github.com/floridsleeves/llmdebugger/blob/HEAD/programming/executors/py_executor.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":"a29cddda11d00bfe","mcp_get_code":{"code_sha256":"a29cddda11d00bfe"}},{"arxiv_id":"2402.04333","paper":"/paper/less-selecting-influential-data-for-targeted","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/less","path":"less/data_selection/collect_grad_reps.py","file_url":"https://github.com/princeton-nlp/less/blob/HEAD/less/data_selection/collect_grad_reps.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"808c09bce5840bb9","mcp_get_code":{"code_sha256":"808c09bce5840bb9"}},{"arxiv_id":"2310.16045","paper":"/paper/woodpecker-hallucination-correction-for","title":"Woodpecker: Hallucination Correction for Multimodal Large Language Models","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bradyfu/woodpecker","path":"models/preprocessor.py","file_url":"https://github.com/bradyfu/woodpecker/blob/HEAD/models/preprocessor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8122965ad6131653","mcp_get_code":{"code_sha256":"8122965ad6131653"}},{"arxiv_id":"2310.16045","paper":"/paper/woodpecker-hallucination-correction-for","title":"Woodpecker: Hallucination Correction for Multimodal Large Language Models","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bradyfu/woodpecker","path":"models/refiner.py","file_url":"https://github.com/bradyfu/woodpecker/blob/HEAD/models/refiner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3cc2c9efff7e5609","mcp_get_code":{"code_sha256":"3cc2c9efff7e5609"}},{"arxiv_id":"2310.10158","paper":"/paper/character-llm-a-trainable-agent-for-role","title":"Character-LLM: A Trainable Agent for Role-Playing","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"choosewhatulike/trainable-agents","path":"api_call_util.py","file_url":"https://github.com/choosewhatulike/trainable-agents/blob/HEAD/api_call_util.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":"5390fac97c1ea60e","mcp_get_code":{"code_sha256":"5390fac97c1ea60e"}},{"arxiv_id":"2307.02394","paper":"/paper/won-t-get-fooled-again-answering-questions","title":"Won't Get Fooled Again: Answering Questions with False Premises","date":"2023-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/FalseQA","path":"src/utils.py","file_url":"https://github.com/thunlp/FalseQA/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ff87150644a05b43","mcp_get_code":{"code_sha256":"ff87150644a05b43"}},{"arxiv_id":"2302.13406","paper":"/paper/gnndelete-a-general-strategy-for-unlearning","title":"GNNDelete: A General Strategy for Unlearning in Graph Neural Networks","date":"2023-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mims-harvard/gnndelete","path":"delete_gnn.py","file_url":"https://github.com/mims-harvard/gnndelete/blob/HEAD/delete_gnn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b2407dc1099e083e","mcp_get_code":{"code_sha256":"b2407dc1099e083e"}},{"arxiv_id":"2202.01020","paper":"/paper/mednerf-medical-neural-radiance-fields-for","title":"MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray","date":"2022-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abrilcf/mednerf","path":"graf-main/render_xray_G.py","file_url":"https://github.com/abrilcf/mednerf/blob/HEAD/graf-main/render_xray_G.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fe5e56bffc7fef7b","mcp_get_code":{"code_sha256":"fe5e56bffc7fef7b"}},{"arxiv_id":"1906.01378","paper":"/paper/distantly-supervised-named-entity-recognition","title":"Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning","date":"2019-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"v-mipeng/LexiconNER","path":"final_evl.py","file_url":"https://github.com/v-mipeng/LexiconNER/blob/HEAD/final_evl.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":"779dc0b23e846462","mcp_get_code":{"code_sha256":"779dc0b23e846462"}},{"arxiv_id":"aaai_32174","paper":null,"title":"arXiv:aaai_32174","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"VectorInstitute/GenerativeSSL","path":"data_generation/icgan/predict.py","file_url":"https://github.com/VectorInstitute/GenerativeSSL/blob/HEAD/data_generation/icgan/predict.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"567e5e16e8b1da99","mcp_get_code":{"code_sha256":"567e5e16e8b1da99"}},{"arxiv_id":"2021.acl-long.9","paper":null,"title":"arXiv:2021.acl-long.9","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"GaryYufei/ACL2021MF","path":"utils.py","file_url":"https://github.com/GaryYufei/ACL2021MF/blob/HEAD/utils.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":"38d651a46ae56a74","mcp_get_code":{"code_sha256":"38d651a46ae56a74"}}]}