{"as_of":"2026-08-14T15:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:74dc44fd6424ced9f3648794223857996e88c9e4ab3760eddd3aa81e77798669","coverage":[{"denominator":16,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":16,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:15:37.494929Z","state":"measured"},{"denominator":16,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":16,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.02694/citation-record","integrity":"/paper/2608.02694/integrity","json":"/paper/2608.02694/citation-record.json","paper":"/paper/2608.02694"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.27705","last_updated":"2026-05-26T21:27:16Z","snapshot_observed_at":"2026-08-10T23:32:40.486210Z","submitted_at":"2026-05-26T21:27:16Z","title":"AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.27705","snapshot_observed_at":"2026-08-07T00:15:35.474734Z","title":"Agenticvbench: Can ai agents complete real-world post-production tasks?arXiv preprint arXiv:2605.27705,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:35.474734Z"},"links":{"cited_paper":"/paper/2605.27705","citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:c354fb55b130af550913c1f7afa179cf7bccf4a0d2ea202d67b85851c6413383","observation_id":"f809dd67-1973-4f71-b8f2-3f8c4a266d72","resolution":{"observed_at":"2026-08-07T00:15:35.474734Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.10761","last_updated":"2025-09-13T00:27:02Z","snapshot_observed_at":"2026-08-13T05:35:07.660497Z","submitted_at":"2025-09-13T00:27:02Z","title":"EditDuet: A Multi-Agent System for Video Non-Linear Editing","version":1},"cited_work":{"arxiv_id":"2509.10761","doi":null,"metadata_source":"pith","pith_arxiv_id":"2509.10761","snapshot_observed_at":"2026-08-07T00:15:38.327304Z","title":"EditDuet: A Multi-Agent System for Video Non-Linear Editing","venue":"cs.CV","work_id":"f8414727-7a5c-4e32-b9f1-39ec2bda0594","year":2025},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:36.039515Z"},"links":{"cited_paper":"/paper/2509.10761","citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:c087346f55f21340ec8af030cf96724b4ce61c1048a05dc0071f350015d43482","observation_id":"80ef2456-8883-45d7-9a19-7559e698377b","resolution":{"observed_at":"2026-08-07T00:15:38.436827Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:15:36.341927Z","title":"Hindsight credit assignment for long-horizon llm agents.arXiv preprint arXiv:2603.08754,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:36.341927Z"},"links":{"citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:7e58ab9379b218b0c4887462e120514710edf173a0a22bf3ebf88c851c8c5e24","observation_id":"d930242b-08e7-4278-afdd-b316c80d61c6","resolution":{"observed_at":"2026-08-07T00:15:36.341927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-07T00:15:36.605853Z","title":"Mudit Verma and Katherine Metcalf","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:36.605853Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:274c2a6214686b26ebde33c05fb5c98c6a42c299f9237080d6358a74377f255b","observation_id":"f602c1ee-220b-4474-aa73-60324e2bbc50","resolution":{"observed_at":"2026-08-07T00:15:36.605853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.20732","last_updated":"2025-05-27T05:21:04Z","snapshot_observed_at":"2026-08-14T01:19:35.519123Z","submitted_at":"2025-05-27T05:21:04Z","title":"SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.20732","snapshot_observed_at":"2026-08-07T00:15:36.767536Z","title":"Spa-rl: Reinforcing llm agents via stepwise progress attribution.arXiv preprint arXiv:2505.20732,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:36.767536Z"},"links":{"cited_paper":"/paper/2505.20732","citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:cb271dfe0912ded62ae49a114a59b3c8a7c219d398272316a4521f5dcb53f232","observation_id":"9647de98-3586-4a95-92b8-becd9006b2e5","resolution":{"observed_at":"2026-08-07T00:15:36.767536Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:15:36.942476Z","title":"Agentprm: Process reward models for llm agents via step-wise promise and progress.arXiv preprint arXiv:2511.08325,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:36.942476Z"},"links":{"citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:f8b86f4ad22dba91f8eb305f17f243c0fd4492f595007753711b8efc3c52a741","observation_id":"0522718a-d98c-45ee-9760-6a5d30e53558","resolution":{"observed_at":"2026-08-07T00:15:36.942476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.12446","last_updated":"2025-06-28T14:16:58Z","snapshot_observed_at":"2026-08-10T01:13:57.356873Z","submitted_at":"2025-06-14T10:58:38Z","title":"From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time Alignment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.12446","snapshot_observed_at":"2026-08-07T00:15:37.083838Z","title":"From outcomes to processes: Guiding prm learning from orm for inference-time alignment.arXiv preprint arXiv:2506.12446,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:37.083838Z"},"links":{"cited_paper":"/paper/2506.12446","citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:93186f6e5f20b398c14a9699f9909bff0c32dccafb11f11486f394712adb7989","observation_id":"033c006d-117b-49b8-afbe-e84dce3a2697","resolution":{"observed_at":"2026-08-07T00:15:37.083838Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.09513","last_updated":"2024-12-12T17:59:28Z","snapshot_observed_at":"2026-08-11T16:56:26.362585Z","submitted_at":"2024-12-12T17:59:28Z","title":"Agent-based Video Trimming","version":1},"cited_work":{"arxiv_id":"2412.09513","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.09513","snapshot_observed_at":"2026-08-07T00:15:37.836889Z","title":"Agent-based Video Trimming","venue":"cs.CV","work_id":"35cf5533-77ae-463e-921d-2ed39ab86004","year":2024},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:37.247166Z"},"links":{"cited_paper":"/paper/2412.09513","citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:0af9f8bd60524c0424d0f93d1ad699d7a3c00334669180166cd26e52d19b515a","observation_id":"c55a0635-7ae2-46da-9a19-aee6f0a53216","resolution":{"observed_at":"2026-08-07T00:15:37.898420Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.10456","last_updated":"2026-04-12T04:39:09Z","snapshot_observed_at":"2026-08-14T07:37:19.031942Z","submitted_at":"2026-04-12T04:39:09Z","title":"A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.10456","snapshot_observed_at":"2026-08-07T00:15:37.367791Z","title":"A benchmark and multi-agent system for instruction-driven cinematic video compilation.arXiv preprint arXiv:2604.10456,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:37.367791Z"},"links":{"cited_paper":"/paper/2604.10456","citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:5cd4eebbe7e6c2a0f25b1f949f6e35e75723b91018b7813850342cef7ac075ba","observation_id":"f9367870-c554-4f7a-99db-b2c16435ec84","resolution":{"observed_at":"2026-08-07T00:15:37.367791Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:15:37.494929Z","title":"Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:37.494929Z"},"links":{"citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:f17be4547f03cec80d6a1402f91bac7764d5c4bc8478ed697abbf396a9bf0a28","observation_id":"acee3e06-ad7d-48e7-a4e1-8d1b5aaa9a65","resolution":{"observed_at":"2026-08-07T00:15:37.494929Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-07T00:15:36.234770Z","title":"Proximal policy optimization algorithms.arXiv preprint arXiv:1707.06347,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:36.234770Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:23f8de74bf644381830a616862be669442639cffe4ffb7fd514f650870b74632","observation_id":"709d63f1-033a-4573-9962-7d3321bc92f8","resolution":{"observed_at":"2026-08-07T00:15:36.234770Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01456","last_updated":"2025-09-26T09:25:31Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-03T15:43:48Z","title":"Process Reinforcement through Implicit Rewards","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01456","snapshot_observed_at":"2026-08-07T00:15:35.608768Z","title":"Process reinforcement through implicit rewards","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:35.608768Z"},"links":{"cited_paper":"/paper/2502.01456","citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:87dae1e0f68d1ca2a68c65449d61decb2202bd5e9677134cf80988069c4966a4","observation_id":"93369115-0353-4868-a9ee-63990e88ebd2","resolution":{"observed_at":"2026-08-07T00:15:35.608768Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.21631","last_updated":"2025-11-27T12:16:54Z","snapshot_observed_at":"2026-08-11T14:42:37.584016Z","submitted_at":"2025-11-26T17:59:08Z","title":"Qwen3-VL Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.21631","snapshot_observed_at":"2026-08-07T00:15:35.315107Z","title":"Qwen3-vl technical report.arXiv preprint arXiv:2511.21631,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:35.315107Z"},"links":{"cited_paper":"/paper/2511.21631","citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:e27ae39dbc3f91f88ba3fe97bfb5e402ea68a2ce67833dbc6ed582184aaaa728","observation_id":"673302fd-11d9-4208-9e20-8cb32dc36ace","resolution":{"observed_at":"2026-08-07T00:15:35.315107Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:15:38.667707Z","title":"From generation to judgment: Opportunities and challenges of llm-as-a-judge","venue":null,"work_id":"7178ab43-66f7-4144-b763-f55e0544838d","year":2025},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:35.748984Z"},"links":{"citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:d461b5df3b9cff7c227e106832f430c62c813f38bf318a3a2ffc0b83cc526d46","observation_id":"f553bbb2-2ba5-4fff-adc0-6703bc7a1a5f","resolution":{"observed_at":"2026-08-07T00:15:38.756569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.04875","last_updated":"2026-04-06T17:26:04Z","snapshot_observed_at":"2026-08-12T21:50:12.511166Z","submitted_at":"2026-04-06T17:26:04Z","title":"DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.04875","snapshot_observed_at":"2026-08-07T00:15:35.889254Z","title":"Ke Li, Maoliang Li, Jialiang Chen, Jiayu Chen, Zihao Zheng, Shaoqi Wang, and Xiang Chen","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:35.889254Z"},"links":{"cited_paper":"/paper/2604.04875","citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:4f202263eb8c28c4047024d5455fb9920d035456abdaccc1d315d2296e60af70","observation_id":"9f21af40-10cd-40b3-9c8d-f72427df1e62","resolution":{"observed_at":"2026-08-07T00:15:35.889254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2607.02770","last_updated":"2026-07-02T21:08:53Z","snapshot_observed_at":"2026-08-13T20:57:43.825707Z","submitted_at":"2026-07-02T21:08:53Z","title":"Gemma 4 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2607.02770","snapshot_observed_at":"2026-08-07T00:15:36.475892Z","title":"Gemma 4 technical report, 2026a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation","version":1},"reference_index":2026,"source":"pdf_text","source_observed_at":"2026-08-07T00:15:36.475892Z"},"links":{"cited_paper":"/paper/2607.02770","citing_paper":"/paper/2608.02694"},"observation_digest":"sha256:fe85edb27a3a28d8d10265986d5a02a17af681e250078736ff5c19b8eddf126f","observation_id":"297f81cf-7f25-4c34-8071-972f598745bd","resolution":{"observed_at":"2026-08-07T00:15:36.475892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.02694","last_updated":"2026-08-03T10:41:25Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-13T02:14:55.551560Z","submitted_at":"2026-08-03T10:41:25Z","title":"Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation"},"reference_resolution":{"displayed":16,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":13,"verified_exact":0,"verified_fuzzy":1},"total_outbound_references":16},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2608.02694."}