{"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":"/paper/associating-objects-with-transformers-for","title":"Associating Objects with Transformers for Video Object Segmentation","arxiv_id":"2106.02638","date":"2021-06-04","proceeding":"NeurIPS 2021 12","authors":["Zongxin Yang","Yunchao Wei","Yi Yang"],"abstract":"This paper investigates how to realize better and more efficient embedding learning to tackle the semi-supervised video object segmentation under challenging multi-object scenarios. The state-of-the-art methods learn to decode features with a single positive object and thus have to match and segment each target separately under multi-object scenarios, consuming multiple times computing resources. To solve the problem, we propose an Associating Objects with Transformers (AOT) approach to match and decode multiple objects uniformly. In detail, AOT employs an identification mechanism to associate multiple targets into the same high-dimensional embedding space. Thus, we can simultaneously process multiple objects' matching and segmentation decoding as efficiently as processing a single object. For sufficiently modeling multi-object association, a Long Short-Term Transformer is designed for constructing hierarchical matching and propagation. We conduct extensive experiments on both multi-object and single-object benchmarks to examine AOT variant networks with different complexities. Particularly, our R50-AOT-L outperforms all the state-of-the-art competitors on three popular benchmarks, i.e., YouTube-VOS (84.1% J&F), DAVIS 2017 (84.9%), and DAVIS 2016 (91.1%), while keeping more than $3\\times$ faster multi-object run-time. Meanwhile, our AOT-T can maintain real-time multi-object speed on the above benchmarks. Based on AOT, we ranked 1st in the 3rd Large-scale VOS Challenge.","url_abs":"https://arxiv.org/abs/2106.02638v3","url_pdf":"https://arxiv.org/pdf/2106.02638v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"associating-objects-with-transformers-for","repo_url":"https://github.com/z-x-yang/AOT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"associating-objects-with-transformers-for","repo_url":"https://github.com/yoxu515/aot-benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"one-shot-visual-object-segmentation","task_name":"One-shot visual object segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vos","method_name":"VOS"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-20","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS (no YouTube-VOS training)","model":"AOT-S","rank_in_archive_order":3,"of":26,"metrics":{"D17 val (F)":"82.0","D17 val (G)":"79.2","D17 val (J)":"76.4","FPS":"40.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"SwinB-AOT-L","rank_in_archive_order":11,"of":78,"metrics":{"F-measure (Mean)":"93.3","J&F":"92.0","Jaccard (Mean)":"90.7","Speed (FPS)":"12.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"R50-AOT-L","rank_in_archive_order":21,"of":78,"metrics":{"F-measure (Mean)":"92.1","J&F":"91.1","Jaccard (Mean)":"90.1","Speed (FPS)":"18.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"AOT-L","rank_in_archive_order":29,"of":78,"metrics":{"F-measure (Mean)":"91.1","J&F":"90.4","Jaccard (Mean)":"89.6","Speed (FPS)":"18.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"AOT-L","rank_in_archive_order":31,"of":78,"metrics":{"F-measure (Mean)":"91.1","J&F":"89.9","Jaccard (Mean)":"88.7","Speed (FPS)":"29.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"AOT-S","rank_in_archive_order":34,"of":78,"metrics":{"F-measure (Mean)":"90.2","J&F":"89.4","Jaccard (Mean)":"88.6","Speed (FPS)":"40.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"AOT-T","rank_in_archive_order":45,"of":78,"metrics":{"F-measure (Mean)":"87.4","J&F":"86.8","Jaccard (Mean)":"86.1","Speed (FPS)":"51.4"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"SwinB-AOT-L","rank_in_archive_order":15,"of":59,"metrics":{"F-measure (Mean)":"85.1","FPS":"12.1","J&F":"81.2","Jaccard (Mean)":"77.3"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"R50-AOT-L","rank_in_archive_order":22,"of":59,"metrics":{"F-measure (Mean)":"83.3","FPS":"18.0","J&F":"79.6","Jaccard (Mean)":"75.9"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"AOT-L","rank_in_archive_order":25,"of":59,"metrics":{"F-measure (Mean)":"82.3","FPS":"18.7","J&F":"78.3","Jaccard (Mean)":"74.3"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"AOT-B","rank_in_archive_order":32,"of":59,"metrics":{"F-measure (Mean)":"79.3","FPS":"29.6","J&F":"75.5","Jaccard (Mean)":"71.6"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"AOT-S","rank_in_archive_order":36,"of":59,"metrics":{"F-measure (Mean)":"77.5","FPS":"40.0","J&F":"73.9","Jaccard (Mean)":"70.3"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-1","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"AOT-T","rank_in_archive_order":39,"of":59,"metrics":{"F-measure (Mean)":"75.7","FPS":"51.4","J&F":"72.0","Jaccard (Mean)":"68.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"SwinB-AOT-L","rank_in_archive_order":21,"of":81,"metrics":{"F-measure (Mean)":"88.4","J&F":"85.4","Jaccard (Mean)":"82.4","Params(M)":"65.4","Speed (FPS)":"12.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"R50-AOT-L","rank_in_archive_order":26,"of":81,"metrics":{"F-measure (Mean)":"87.5","J&F":"84.9","Jaccard (Mean)":"82.3","Params(M)":"14.9","Speed (FPS)":"18.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"AOT-L","rank_in_archive_order":31,"of":81,"metrics":{"F-measure (Mean)":"86.4","J&F":"83.8","Jaccard (Mean)":"81.1","Params(M)":"8.3","Speed (FPS)":"18.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"AOT-B","rank_in_archive_order":37,"of":81,"metrics":{"F-measure (Mean)":"85.2","J&F":"82.5","Jaccard (Mean)":"79.7","Params(M)":"8.3","Speed (FPS)":"29.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"AOT-S","rank_in_archive_order":42,"of":81,"metrics":{"F-measure (Mean)":"83.9","J&F":"81.3","Jaccard (Mean)":"78.7","Params(M)":"7.0","Speed (FPS)":"40.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-davis-2017","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2017 (val)","model":"AOT-T","rank_in_archive_order":46,"of":81,"metrics":{"F-measure (Mean)":"82.3","J&F":"79.9","Jaccard (Mean)":"77.4","Params(M)":"5.7","Speed (FPS)":"51.4"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-21","task":"Semi-Supervised Video Object Segmentation","dataset":"MOSE","model":"AOT","rank_in_archive_order":14,"of":17,"metrics":{"F":"61.3","J":"53.1","J&F":"57.2"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-15","task":"Semi-Supervised Video Object Segmentation","dataset":"VOT2020","model":"SwinB-AOT-L","rank_in_archive_order":9,"of":20,"metrics":{"EAO":"0.586","EAO (real-time)":"0.523"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-15","task":"Semi-Supervised Video Object Segmentation","dataset":"VOT2020","model":"AOT-L","rank_in_archive_order":11,"of":20,"metrics":{"EAO":"0.574","EAO (real-time)":"0.560"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-15","task":"Semi-Supervised Video Object Segmentation","dataset":"VOT2020","model":"R50-AOT-L","rank_in_archive_order":13,"of":20,"metrics":{"EAO":"0.569","EAO (real-time)":"0.540"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-15","task":"Semi-Supervised Video Object Segmentation","dataset":"VOT2020","model":"AOT-B","rank_in_archive_order":15,"of":20,"metrics":{"EAO":"0.541","EAO (real-time)":"0.533"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-15","task":"Semi-Supervised Video Object Segmentation","dataset":"VOT2020","model":"AOT-S","rank_in_archive_order":17,"of":20,"metrics":{"EAO":"0.512","EAO (real-time)":"0.499"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-15","task":"Semi-Supervised Video Object Segmentation","dataset":"VOT2020","model":"AOT-T","rank_in_archive_order":20,"of":20,"metrics":{"EAO":"0.435","EAO (real-time)":"0.433"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"R50-AOT-L (all frames)","rank_in_archive_order":10,"of":53,"metrics":{"F-Measure (Seen)":"89.5","F-Measure (Unseen)":"88.2","Jaccard (Seen)":"84.5","Jaccard (Unseen)":"79.6","Overall":"85.5","Params(M)":"14.9","Speed  (FPS)":"6.4"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"SwinB-AOT-L (all frames)","rank_in_archive_order":12,"of":53,"metrics":{"F-Measure (Seen)":"90.1","F-Measure (Unseen)":"86.9","Jaccard (Seen)":"85.1","Jaccard (Unseen)":"78.4","Overall":"85.1","Params(M)":"65.4","Speed  (FPS)":"5.2"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"SwinB-AOT-L","rank_in_archive_order":16,"of":53,"metrics":{"F-Measure (Seen)":"89.3","F-Measure (Unseen)":"86.4","Jaccard (Seen)":"84.3","Jaccard (Unseen)":"77.9","Overall":"84.5","Params(M)":"65.4","Speed  (FPS)":"9.3"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"AOT-L (all frames)","rank_in_archive_order":17,"of":53,"metrics":{"F-Measure (Seen)":"88.8","F-Measure (Unseen)":"87.1","Jaccard (Seen)":"83.7","Jaccard (Unseen)":"78.4","Overall":"84.5","Params(M)":"8.3","Speed  (FPS)":"6.5"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"R50-AOT-L","rank_in_archive_order":22,"of":53,"metrics":{"F-Measure (Seen)":"88.5","F-Measure (Unseen)":"86.1","Jaccard (Seen)":"83.7","Jaccard (Unseen)":"78.1","Overall":"84.1","Params(M)":"14.9","Speed  (FPS)":"14.9"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"AOT-B (all frames)","rank_in_archive_order":23,"of":53,"metrics":{"F-Measure (Seen)":"88.5","F-Measure (Unseen)":"86.5","Jaccard (Seen)":"83.6","Jaccard (Unseen)":"78.0","Overall":"84.1","Params(M)":"8.3","Speed  (FPS)":"20.5"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"AOT-L","rank_in_archive_order":26,"of":53,"metrics":{"F-Measure (Seen)":"87.9","F-Measure (Unseen)":"86.5","Jaccard (Seen)":"82.9","Jaccard (Unseen)":"77.7","Overall":"83.8","Params(M)":"8.3","Speed  (FPS)":"16.0"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"AOT-B","rank_in_archive_order":28,"of":53,"metrics":{"F-Measure (Seen)":"87.5","F-Measure (Unseen)":"86.0","Jaccard (Seen)":"82.6","Jaccard (Unseen)":"77.7","Overall":"83.5","Params(M)":"8.3","Speed  (FPS)":"20.5"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"AOT-S (all frames)","rank_in_archive_order":29,"of":53,"metrics":{"F-Measure (Seen)":"87.0","F-Measure (Unseen)":"85.7","Jaccard (Seen)":"82.2","Jaccard (Unseen)":"77.3","Overall":"83.0","Params(M)":"7.9","Speed  (FPS)":"27.1"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"AOT-S","rank_in_archive_order":32,"of":53,"metrics":{"F-Measure (Seen)":"86.7","F-Measure (Unseen)":"85.0","Jaccard (Seen)":"82.0","Jaccard (Unseen)":"76.6","Overall":"82.6","Params(M)":"7.9","Speed  (FPS)":"27.1"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"AOT-T (all frames)","rank_in_archive_order":39,"of":53,"metrics":{"F-Measure (Seen)":"84.7","F-Measure (Unseen)":"83.5","Jaccard (Seen)":"80.0","Jaccard (Unseen)":"75.2","Overall":"80.9","Params(M)":"5.3","Speed  (FPS)":"41.0"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos","task":"Semi-Supervised Video Object Segmentation","dataset":"YouTube-VOS 2018","model":"AOT-T","rank_in_archive_order":40,"of":53,"metrics":{"F-Measure (Seen)":"84.5","F-Measure (Unseen)":"82.2","Jaccard (Seen)":"80.1","Jaccard (Unseen)":"74.0","Overall":"80.2","Params(M)":"5.3","Speed  (FPS)":"41.0"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-davis-2017-test-1","task":"Video Object Segmentation","dataset":"DAVIS 2017 (test-dev)","model":"AOT","rank_in_archive_order":2,"of":10,"metrics":{"F-measure":"83.3","Jaccard":"75.9","Mean Jaccard & F-Measure":"79.6"},"uses_additional_data":true},{"leaderboard":"/sota/video-object-segmentation-on-youtube-vos-2019-2","task":"Video Object Segmentation","dataset":"YouTube-VOS 2019","model":"AOT","rank_in_archive_order":4,"of":10,"metrics":{"F-Measure (Seen)":"88.1","F-Measure (Unseen)":"86.3","Jaccard (Seen)":"83.5","Jaccard (Unseen)":"78.4","Mean Jaccard & F-Measure":"84.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-vot2022","task":"Visual Object Tracking","dataset":"VOT2022","model":"MS_AOT","rank_in_archive_order":3,"of":5,"metrics":{"EAO":"0.673"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.02638","atlas_url":"https://app.syntology.ai/?focus=2106.02638","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2106.02638"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2106.02638\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2106.02638"},"call":"get_concepts_for_paper(arxiv_id=\"2106.02638\")"}],"by_repo":[{"repo":"z-x-yang/AOT","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yoxu515/aot-benchmark","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"83008b333327867a06e4e284efa00cd656fbf2c5c95d09881af9bf8c91e736f8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}