{"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/prepare-fa2-from-position-ids","entry":"prepare_fa2_from_position_ids","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-25T09:33:49+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":15,"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":6,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":15,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":4},"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":"2606.03066","paper":"/paper/arxiv-2606-03066","title":"CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"shen8424/CORE","path":"libs/transformers/modeling_flash_attention_utils.py","file_url":"https://github.com/shen8424/CORE/blob/HEAD/libs/transformers/modeling_flash_attention_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"93e50e3428eab46d","mcp_get_code":{"code_sha256":"93e50e3428eab46d"}},{"arxiv_id":"2605.07465","paper":"/paper/arxiv-2605-07465","title":"SEIF: Self-Evolving Reinforcement Learning for Instruction Following","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Rainier-rq1/SEIF","path":"verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/Rainier-rq1/SEIF/blob/HEAD/verl/models/transformers/flash_attention_utils.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":"4049cf08f994464e","mcp_get_code":{"code_sha256":"4049cf08f994464e"}},{"arxiv_id":"2603.02635","paper":"/paper/arxiv-2603-02635","title":"SaFeR-ToolKit: Structured Reasoning via Virtual Tool Calling for Multimodal Safety","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"hiyouga/EasyR1","path":"verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/hiyouga/EasyR1/blob/HEAD/verl/models/transformers/flash_attention_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":"72f505c72eeef3e8","mcp_get_code":{"code_sha256":"72f505c72eeef3e8"}},{"arxiv_id":"2602.12735","paper":"/paper/arxiv-2602-12735","title":"VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Alibaba-NLP/VRAG","path":"VRAG-RL/verl/models/transformers/qwen2_vl.py","file_url":"https://github.com/Alibaba-NLP/VRAG/blob/HEAD/VRAG-RL/verl/models/transformers/qwen2_vl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e89bd73550a8c08f","mcp_get_code":{"code_sha256":"e89bd73550a8c08f"}},{"arxiv_id":"2601.05167","paper":"/paper/arxiv-2601-05167","title":"RelayLLM: Efficient Reasoning via Collaborative Decoding","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Chengsong-Huang/RelayLLM","path":"RL_stage/verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/Chengsong-Huang/RelayLLM/blob/HEAD/RL_stage/verl/models/transformers/flash_attention_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"74621bb999fe25b1","mcp_get_code":{"code_sha256":"74621bb999fe25b1"}},{"arxiv_id":"2507.07966","paper":"/paper/scaling-rl-to-long-videos","title":"Scaling RL to Long Videos","date":"2025-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVlabs/Long-RL","path":"verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/NVlabs/Long-RL/blob/HEAD/verl/models/transformers/flash_attention_utils.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":"4049cf08f994464e","mcp_get_code":{"code_sha256":"4049cf08f994464e"}},{"arxiv_id":"2507.05386","paper":"/paper/reinforcement-fine-tuning-naturally-mitigates","title":"Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training","date":"2025-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhhvvv/rft_vs_sft","path":"EasyR1/verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/zhhvvv/rft_vs_sft/blob/HEAD/EasyR1/verl/models/transformers/flash_attention_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4049cf08f994464e","mcp_get_code":{"code_sha256":"4049cf08f994464e"}},{"arxiv_id":"2507.03038","paper":"/paper/cautious-next-token-prediction","title":"Cautious Next Token Prediction","date":"2025-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wyzjack/CNTP","path":"custom_transformers_packages/gsm8k_strategyqa/transformers/modeling_flash_attention_utils.py","file_url":"https://github.com/wyzjack/CNTP/blob/HEAD/custom_transformers_packages/gsm8k_strategyqa/transformers/modeling_flash_attention_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a77b72cc8d5c90f0","mcp_get_code":{"code_sha256":"a77b72cc8d5c90f0"}},{"arxiv_id":"2506.01908","paper":"/paper/reinforcement-learning-tuning-for-videollms","title":"Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency","date":"2025-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"appletea233/temporal-r1","path":"verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/appletea233/temporal-r1/blob/HEAD/verl/models/transformers/flash_attention_utils.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":"4049cf08f994464e","mcp_get_code":{"code_sha256":"4049cf08f994464e"}},{"arxiv_id":"2505.16282","paper":"/paper/arpo-end-to-end-policy-optimization-for-gui","title":"ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/arpo","path":"verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/dvlab-research/arpo/blob/HEAD/verl/models/transformers/flash_attention_utils.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":"4049cf08f994464e","mcp_get_code":{"code_sha256":"4049cf08f994464e"}},{"arxiv_id":"2504.05520","paper":"/paper/efficient-reinforcement-finetuning-via","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","date":"2025-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uscnlp-lime/verl","path":"verl/models/transformers/qwen2_vl.py","file_url":"https://github.com/uscnlp-lime/verl/blob/HEAD/verl/models/transformers/qwen2_vl.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":"e89bd73550a8c08f","mcp_get_code":{"code_sha256":"e89bd73550a8c08f"}},{"arxiv_id":"2503.17352","paper":"/paper/openvlthinker-an-early-exploration-to-complex","title":"OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement","date":"2025-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihedeng9/openvlthinker","path":"EasyR1/verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/yihedeng9/openvlthinker/blob/HEAD/EasyR1/verl/models/transformers/flash_attention_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":"72f505c72eeef3e8","mcp_get_code":{"code_sha256":"72f505c72eeef3e8"}},{"arxiv_id":"2502.19613","paper":"/paper/self-rewarding-correction-for-mathematical","title":"Self-rewarding correction for mathematical reasoning","date":"2025-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agentica-project/verl-pipeline","path":"verl/models/transformers/qwen2_vl.py","file_url":"https://github.com/agentica-project/verl-pipeline/blob/HEAD/verl/models/transformers/qwen2_vl.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":"e89bd73550a8c08f","mcp_get_code":{"code_sha256":"e89bd73550a8c08f"}},{"arxiv_id":"2502.13963","paper":"/paper/mudaf-long-context-multi-document-attention","title":"MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads","date":"2025-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NeosKnight233/MuDAF","path":"transformers/modeling_flash_attention_utils.py","file_url":"https://github.com/NeosKnight233/MuDAF/blob/HEAD/transformers/modeling_flash_attention_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":"a77b72cc8d5c90f0","mcp_get_code":{"code_sha256":"a77b72cc8d5c90f0"}},{"arxiv_id":"openreview_Y1PXB8HBV7","paper":null,"title":"arXiv:openreview_Y1PXB8HBV7","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"youwyouw/mirl-main","path":"verl/models/transformers/flash_attention_utils.py","file_url":"https://github.com/youwyouw/mirl-main/blob/HEAD/verl/models/transformers/flash_attention_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":"72f505c72eeef3e8","mcp_get_code":{"code_sha256":"72f505c72eeef3e8"}}]}