{"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/iou-loss","entry":"iou_loss","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":17,"n_papers_ran":16,"n_papers_ran_no_instrument_failure":16,"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":11,"n_samples_ran":10,"n_samples_constructed":0,"n_samples_ran_checked":10,"n_samples_instrument":0,"n_samples_unverified":1,"n_samples_fingerprinted":2,"n_places":18,"n_places_pointer_only":9,"n_places_pointer_only_link_open":4,"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":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":10,"unverified":1},"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":"2606.06819","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-06819","title":"VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Dmmm1997/VideoSEG-O3","path":"projects/open_r1/trainer/sam_loss.py","file_url":"https://github.com/Dmmm1997/VideoSEG-O3/blob/HEAD/projects/open_r1/trainer/sam_loss.py","status":"ran","verification_level":1,"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":"e40a43378d8a1fb1","code_sha256_prefix":"e40a43378d8a1fb1","mcp_get_code":{"code_sha256":"e40a43378d8a1fb1"}},{"arxiv_id":"2602.20151","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-20151","title":"Conformal Risk Control for Non-Monotonic Losses","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"aangelopoulos/nonmonotonic-crc","path":"iou_tumor/utils.py","file_url":"https://github.com/aangelopoulos/nonmonotonic-crc/blob/HEAD/iou_tumor/utils.py","status":"ran","verification_level":1,"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, aangelopoulos/nonmonotonic-crc when it was checked","code_sha256":"16d3e709eafdd6fc","code_sha256_prefix":"16d3e709eafdd6fc","mcp_get_code":{"code_sha256":"16d3e709eafdd6fc"}},{"arxiv_id":"2512.23427","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2512-23427","title":"Towards Integrating Uncertainty for Domain-Agnostic Segmentation","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"JesseBrouw/UncertSAM","path":"src/loss_fns.py","file_url":"https://github.com/JesseBrouw/UncertSAM/blob/HEAD/src/loss_fns.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"AGPL-3.0, as GitHub detects it on this paper's repository, JesseBrouw/UncertSAM, is not in the permissive set Syntology serves inline","code_sha256":"b719420230af3c51","code_sha256_prefix":"b719420230af3c51","mcp_get_code":{"code_sha256":"b719420230af3c51"}},{"arxiv_id":"2510.11417","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2510-11417","title":"Robust Ego-Exo Correspondence with Long-Term Memory","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"juneyeeHu/LM-EEC","path":"training/loss_fns.py","file_url":"https://github.com/juneyeeHu/LM-EEC/blob/HEAD/training/loss_fns.py","status":"ran","verification_level":1,"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, juneyeeHu/LM-EEC when it was checked","code_sha256":"b8f501ca29e77f1a","code_sha256_prefix":"b8f501ca29e77f1a","mcp_get_code":{"code_sha256":"b8f501ca29e77f1a"}},{"arxiv_id":"2510.03853","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2510-03853","title":"UGround: Towards Unified Visual Grounding with Unrolled Transformers","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"rui-qian/UGround","path":"model/GSVA.py","file_url":"https://github.com/rui-qian/UGround/blob/HEAD/model/GSVA.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"af6fc3d42a9de09a","code_sha256_prefix":"af6fc3d42a9de09a","mcp_get_code":{"code_sha256":"af6fc3d42a9de09a"}},{"arxiv_id":"2503.09595","arxiv_id_is_arxiv":true,"paper":"/paper/pisa-experiments-exploring-physics-post","title":"PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop","date":"2025-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vision-x-nyu/pisa-experiments","path":"sam2/training/loss_fns.py","file_url":"https://github.com/vision-x-nyu/pisa-experiments/blob/HEAD/sam2/training/loss_fns.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from juneyeeHu/LM-EEC, and GitHub detected no licence in that repository when it was checked","code_sha256":"b8f501ca29e77f1a","code_sha256_prefix":"b8f501ca29e77f1a","mcp_get_code":{"code_sha256":"b8f501ca29e77f1a"}},{"arxiv_id":"2411.17576","arxiv_id_is_arxiv":true,"paper":"/paper/a-distractor-aware-memory-for-visual-object","title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","date":"2024-11-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jovanavidenovic/dam4sam","path":"training/loss_fns.py","file_url":"https://github.com/jovanavidenovic/dam4sam/blob/HEAD/training/loss_fns.py","status":"ran","verification_level":1,"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, jovanavidenovic/dam4sam when it was checked","code_sha256":"b8f501ca29e77f1a","code_sha256_prefix":"b8f501ca29e77f1a","mcp_get_code":{"code_sha256":"b8f501ca29e77f1a"}},{"arxiv_id":"2408.07931","arxiv_id_is_arxiv":true,"paper":"/paper/surgical-sam-2-real-time-segment-anything-in","title":"Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning","date":"2024-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinlab-imvr/surgical-sam-2","path":"training/loss_fns.py","file_url":"https://github.com/jinlab-imvr/surgical-sam-2/blob/HEAD/training/loss_fns.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from juneyeeHu/LM-EEC, and GitHub detected no licence in that repository when it was checked","code_sha256":"b8f501ca29e77f1a","code_sha256_prefix":"b8f501ca29e77f1a","mcp_get_code":{"code_sha256":"b8f501ca29e77f1a"}},{"arxiv_id":"2408.00714","arxiv_id_is_arxiv":true,"paper":"/paper/2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bowang-lab/medsam2","path":"training/loss_fns.py","file_url":"https://github.com/bowang-lab/medsam2/blob/HEAD/training/loss_fns.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from juneyeeHu/LM-EEC, and GitHub detected no licence in that repository when it was checked","code_sha256":"b8f501ca29e77f1a","code_sha256_prefix":"b8f501ca29e77f1a","mcp_get_code":{"code_sha256":"b8f501ca29e77f1a"}},{"arxiv_id":"2312.10103","arxiv_id_is_arxiv":true,"paper":"/paper/gsva-generalized-segmentation-via-multimodal","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models","date":"2023-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leaplabthu/gsva","path":"model/losses.py","file_url":"https://github.com/leaplabthu/gsva/blob/HEAD/model/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"af6fc3d42a9de09a","code_sha256_prefix":"af6fc3d42a9de09a","mcp_get_code":{"code_sha256":"af6fc3d42a9de09a"}},{"arxiv_id":"2310.14532","arxiv_id_is_arxiv":true,"paper":"/paper/practical-deep-dispersed-watermarking-with","title":"Practical Deep Dispersed Watermarking with Synchronization and Fusion","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/dwsf","path":"train_seg.py","file_url":"https://github.com/bytedance/dwsf/blob/HEAD/train_seg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, bytedance/dwsf (NOASSERTION)","code_sha256":"71bc87e62bf2a521","code_sha256_prefix":"71bc87e62bf2a521","mcp_get_code":{"code_sha256":"71bc87e62bf2a521"}},{"arxiv_id":"2302.01872","arxiv_id_is_arxiv":true,"paper":"/paper/mose-a-new-dataset-for-video-object","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","date":"2023-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"henghuiding/MOSE-api","path":"MOSEv2/sam2_rcms/training/loss_fns.py","file_url":"https://github.com/henghuiding/MOSE-api/blob/HEAD/MOSEv2/sam2_rcms/training/loss_fns.py","status":"ran","verification_level":1,"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 juneyeeHu/LM-EEC, and GitHub detected no licence in that repository when it was checked","code_sha256":"b8f501ca29e77f1a","code_sha256_prefix":"b8f501ca29e77f1a","mcp_get_code":{"code_sha256":"b8f501ca29e77f1a"}},{"arxiv_id":"2204.01680","arxiv_id_is_arxiv":true,"paper":"/paper/tallformer-temporal-action-localization-with","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","date":"2022-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"klauscc/tallformer","path":"AFSD/anet_video_cls/multisegment_loss.py","file_url":"https://github.com/klauscc/tallformer/blob/HEAD/AFSD/anet_video_cls/multisegment_loss.py","status":"ran","verification_level":1,"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":"e1f7c9eb71128188","code_sha256_prefix":"e1f7c9eb71128188","mcp_get_code":{"code_sha256":"e1f7c9eb71128188"}},{"arxiv_id":"2006.05683","arxiv_id_is_arxiv":true,"paper":"/paper/tubetk-adopting-tubes-to-track-multi-object-1","title":"TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model","date":"2020-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BoPang1996/TubeTK","path":"network/utils.py","file_url":"https://github.com/BoPang1996/TubeTK/blob/HEAD/network/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"1bcb91317c367710","code_sha256_prefix":"1bcb91317c367710","mcp_get_code":{"code_sha256":"1bcb91317c367710"}},{"arxiv_id":"2004.08790","arxiv_id_is_arxiv":true,"paper":"/paper/unet-3-a-full-scale-connected-unet-for","title":"UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation","date":"2020-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hamidriasat/UNet-3-Plus","path":"losses/loss.py","file_url":"https://github.com/hamidriasat/UNet-3-Plus/blob/HEAD/losses/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"013ffa32c7802109","code_sha256_prefix":"013ffa32c7802109","mcp_get_code":{"code_sha256":"013ffa32c7802109"}},{"arxiv_id":"1904.01355","arxiv_id_is_arxiv":true,"paper":"/paper/fcos-fully-convolutional-one-stage-object","title":"FCOS: Fully Convolutional One-Stage Object Detection","date":"2019-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"srihari-humbarwadi/tensorflow_fcos","path":"tensorflow_fcos/models/fcos/losses.py","file_url":"https://github.com/srihari-humbarwadi/tensorflow_fcos/blob/HEAD/tensorflow_fcos/models/fcos/losses.py","status":"ran","verification_level":1,"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":"5e47641ad906ae7b","code_sha256_prefix":"5e47641ad906ae7b","mcp_get_code":{"code_sha256":"5e47641ad906ae7b"}},{"arxiv_id":"1904.01355","arxiv_id_is_arxiv":true,"paper":"/paper/fcos-fully-convolutional-one-stage-object","title":"FCOS: Fully Convolutional One-Stage Object Detection","date":"2019-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xytpai/fcos","path":"libs/iou_loss.py","file_url":"https://github.com/xytpai/fcos/blob/HEAD/libs/iou_loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"dbd9612822534e83","code_sha256_prefix":"dbd9612822534e83","mcp_get_code":{"code_sha256":"dbd9612822534e83"}},{"arxiv_id":"Xia_GSVA_Generalized_Segmentation_via_Multimodal_Large_Language_Models_CVPR_2024_paper","arxiv_id_is_arxiv":false,"paper":null,"title":"CVF open access id Xia_GSVA_Generalized_Segmentation_via_Multimodal_Large_Language_Models_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LeapLabTHU/GSVA","path":"model/losses.py","file_url":"https://github.com/LeapLabTHU/GSVA/blob/HEAD/model/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"af6fc3d42a9de09a","code_sha256_prefix":"af6fc3d42a9de09a","mcp_get_code":{"code_sha256":"af6fc3d42a9de09a"}}],"record_sha256":"a3db4f476d4ba6d4e1439962028127661a7fd7595848c715087b0c928db1201d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}