{"as_of":"2026-08-22T07:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4baad0b9908a149c10f02d99326f68783f991b4d0675357b9f43ee4f60998e4a","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T11:49:08.680321Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2504.14535/citation-record","integrity":"/paper/2504.14535/integrity","json":"/paper/2504.14535/citation-record.json","paper":"/paper/2504.14535"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2204.03458","last_updated":"2022-06-22T20:22:29Z","snapshot_observed_at":"2026-08-17T13:08:14.312126Z","submitted_at":"2022-04-07T14:08:02Z","title":"Video Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.03458","snapshot_observed_at":"2026-08-16T11:49:08.505743Z","title":"Video diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.505743Z"},"links":{"cited_paper":"/paper/2204.03458","citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:358d21787f4e5a95904e9b79fc9d7a54173c977064aa22a926325e4f41fa8b1e","observation_id":"afdfdc04-9960-4a07-821a-e0333e59b222","resolution":{"observed_at":"2026-08-16T11:49:08.505743Z","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":"2026-08-16T11:49:09.272991Z","title":"Align your latents: High-resolution video syn- thesis with latent diffusion models","venue":null,"work_id":"1ec96478-cdda-4606-a3b1-0fdec28eec5e","year":2023},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.511373Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:044f0db7ff67268fd3589f3f6fe79eea5af5eaf1116be1bea67db9f686e94d26","observation_id":"e39bc3f7-676a-4b87-9b79-01b9bff50a33","resolution":{"observed_at":"2026-08-16T11:49:09.277884Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:49:09.258051Z","title":"Hierarchical patch diffusion models for high-resolution video generation","venue":null,"work_id":"5c33fae9-ddfa-467d-b44f-6b5f760743bc","year":2024},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.516550Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:7f35c5369e9edbb1bbf12087932f746188ca3303b41a6317ffae885e5d5f0f01","observation_id":"2cceb0d4-f9c2-4518-ba03-1530e156047b","resolution":{"observed_at":"2026-08-16T11:49:09.262788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:49:09.242893Z","title":"Struc- ture and content-guided video synthesis with diffusion models","venue":null,"work_id":"99f5c93a-7912-4cd6-a8ee-f3d90c6a96b6","year":2023},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.521252Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:0c200d930da5191ee6fc54f05b8820ab3811b305fb75809fdb5f22dadc99ac06","observation_id":"f7ab2310-f350-4ee5-99b0-083c060da13b","resolution":{"observed_at":"2026-08-16T11:49:09.247587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:49:09.227909Z","title":"Magicanimate: Temporally consis- tent human image animation using diffusion model","venue":null,"work_id":"2f00c099-936a-464b-aa3b-2f9e60aa3bd9","year":2024},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.526257Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:96a093b62f8e5487e5588920737f99e38673179f846f8aa3c03752335b41b17f","observation_id":"d48f7c0b-a2dc-41a0-89fa-a0f8a2b476a3","resolution":{"observed_at":"2026-08-16T11:49:09.232749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.06571","last_updated":"2023-08-12T13:53:10Z","snapshot_observed_at":"2026-08-14T13:59:50.878772Z","submitted_at":"2023-08-12T13:53:10Z","title":"ModelScope Text-to-Video Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.06571","snapshot_observed_at":"2026-08-16T11:49:08.531003Z","title":"Modelscope text-to- video technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.531003Z"},"links":{"cited_paper":"/paper/2308.06571","citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:3e1a2adfb08e02048f619aa3ed02c0ff54d96e73af8cba0dd43088525d13cf5c","observation_id":"782ddfce-9094-4dd9-bf90-4bfec8279a41","resolution":{"observed_at":"2026-08-16T11:49:08.531003Z","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":"2026-08-16T11:49:09.212666Z","title":"Onlyflow: Opti- cal flow based motion conditioning for video diffusion models, 2024","venue":null,"work_id":"0ea126fa-438b-4520-97a2-939156b65bfd","year":2024},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.536298Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:a4221ba6ed6b30a1d95a7aa602d84926fad1da8bfd674a47e3e35bc29ef4aa7b","observation_id":"85d137dd-d716-47fa-b804-8c46df0308b2","resolution":{"observed_at":"2026-08-16T11:49:09.217546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T11:49:08.540635Z","title":"Motion-i2v: Consistent and controllable image-to-video generation with explicit motion modeling","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.540635Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:fa8bf33c04549894b825709e18a7cb028340dff739b2584760948f7a871c9ab0","observation_id":"f9d16964-4ac8-4b50-aba5-5e3dd1684d14","resolution":{"observed_at":"2026-08-16T11:49:08.540635Z","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":"2026-08-16T11:49:09.188375Z","title":"Optical-flow guided prompt optimization for co- herent video generation, 2025","venue":null,"work_id":"cb64fe91-6a17-441c-95e1-076bb774cc54","year":2025},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.545363Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:77ed7db89ac14bae3c166cf00b7982db46de8b010f9e8435414d657d5cfd612a","observation_id":"5b7d1489-27b7-4f54-aad1-768539c81a17","resolution":{"observed_at":"2026-08-16T11:49:09.193288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.08244","last_updated":"2025-03-25T00:18:07Z","snapshot_observed_at":"2026-08-09T00:50:37.157498Z","submitted_at":"2025-02-12T09:38:41Z","title":"FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.08244","snapshot_observed_at":"2026-08-16T11:49:08.549717Z","title":"Flovd: Optical flow meets video diffusion model for enhanced camera-controlled video synthesis","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.549717Z"},"links":{"cited_paper":"/paper/2502.08244","citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:cf477049fe2540d92f4d886ea50ef1d12cde280754b9b14d208e62ade02a4372","observation_id":"5daadc27-28ef-48f2-9a93-8051961969ca","resolution":{"observed_at":"2026-08-16T11:49:08.549717Z","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":"2026-08-16T11:49:09.173996Z","title":"Flowvid: Taming imperfect optical flows for consistent video-to-video synthesis, 2023","venue":null,"work_id":"f416d27d-f6e1-479f-8dda-380770bbf48d","year":2023},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.554662Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:0a2e4c0d78cb84d19cee3fec752dc5e2d80e9107ab9434f2a4fa0ac42f7b7ef1","observation_id":"6f4d88be-31fb-4466-816d-e728698673d7","resolution":{"observed_at":"2026-08-16T11:49:09.178858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:49:09.160483Z","title":"Conditional image-to-video generation with latent flow diffusion models","venue":null,"work_id":"5ff7c18c-e2b5-421e-94d9-d21c2c173a30","year":2023},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.558834Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:a07bcc802a09f78aae4f1764f442fa57d78138663c83d7854e4c25fd8d04d9b1","observation_id":"b7b45ff5-e337-47bf-aa6e-471d1b9891f1","resolution":{"observed_at":"2026-08-16T11:49:09.164486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15540","last_updated":"2025-03-23T07:34:32Z","snapshot_observed_at":"2026-08-20T04:24:41.569429Z","submitted_at":"2024-11-23T12:26:52Z","title":"Optical-Flow Guided Prompt Optimization for Coherent Video Generation","version":2},"cited_work":{"arxiv_id":"2411.15540","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.15540","snapshot_observed_at":"2026-08-16T11:49:08.852261Z","title":"Optical-Flow Guided Prompt Optimization for Coherent Video Generation","venue":"cs.CV","work_id":"d5e9922d-67ec-4fe9-b58c-c6737b3649be","year":2024},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.563012Z"},"links":{"cited_paper":"/paper/2411.15540","citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:c23833065b1237f7e188b64fe70836466ae20ea168af6130eed1c9a5cb023c0f","observation_id":"7bf2e7bb-11b0-4c38-81ac-8e4383bd8fb6","resolution":{"observed_at":"2026-08-16T11:49:08.858967Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:49:09.147082Z","title":"Learning video stabilization using optical flow","venue":null,"work_id":"3151a649-2c95-46c8-945d-ae7cfa2844c7","year":2020},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.567828Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:4e67ba9fd1e6a382462fa02091172401349b5ecde38a88bb44ac481df927eb22","observation_id":"eb404f66-dd79-46b4-83d6-8c9aac2ecfd4","resolution":{"observed_at":"2026-08-16T11:49:09.151154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:49:09.133678Z","title":"Adding conditional control to text-to-image diffusion models","venue":null,"work_id":"89af6bd4-7446-413a-bcee-db79cef57719","year":2023},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.571828Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:5a6b17914baa15c456dcaf2252ac9fa76c922e2287578c4d4a954ac348af666f","observation_id":"5166cad8-03ac-4d96-8c3e-37c0e4a78a74","resolution":{"observed_at":"2026-08-16T11:49:09.137704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.03847","last_updated":"2025-01-09T04:25:42Z","snapshot_observed_at":"2026-08-16T09:31:46.329467Z","submitted_at":"2025-01-07T15:01:58Z","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.03847","snapshot_observed_at":"2026-08-16T11:49:08.576059Z","title":"Diffusion as shader: 3d-aware video diffusion for versatile video generation control","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.576059Z"},"links":{"cited_paper":"/paper/2501.03847","citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:68d5dc008ac3dcefd8f84780dfb5377b1c8a943efe730e908bf07c98aa1aee82","observation_id":"1fb0e08d-a99d-4d73-a412-3fded2cda480","resolution":{"observed_at":"2026-08-16T11:49:08.576059Z","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":"2026-08-16T11:49:09.119907Z","title":"Draganything: Motion control for anything using entity representation","venue":null,"work_id":"70f02387-c316-4638-a396-f8e1a15f2010","year":null},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.580918Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:b89a55737ad09b552cae52ff4c2dbefd6a879fd139135cc7d3e97eee695b0ec9","observation_id":"56c7bdc7-29a5-4377-b11d-66a570a02cac","resolution":{"observed_at":"2026-08-16T11:49:09.124590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:49:09.104490Z","title":"Image conductor: Precision control for interactive video synthesis","venue":null,"work_id":"8f7381ff-a11a-4037-ad11-ab566dd879df","year":2025},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.584930Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:25ed4cae9d2e5c38e744e3b9082231d3d187feaa45ccdb5c2e894cf453db5f4d","observation_id":"3ff3f426-e853-4a29-a049-c908907e1e45","resolution":{"observed_at":"2026-08-16T11:49:09.109554Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.02700","last_updated":"2025-03-27T21:38:09Z","snapshot_observed_at":"2026-08-17T17:55:41.151533Z","submitted_at":"2024-12-03T18:59:56Z","title":"Motion Prompting: Controlling Video Generation with Motion Trajectories","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.02700","snapshot_observed_at":"2026-08-16T11:49:08.588781Z","title":"Motion prompting: Controlling video generation with motion trajectories","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.588781Z"},"links":{"cited_paper":"/paper/2412.02700","citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:858c60446f389cece8f536c079347f92a3f27be9fbf381a5f269860c85da620d","observation_id":"15d331e9-2cac-4c36-9bf8-1b1c27da5c4e","resolution":{"observed_at":"2026-08-16T11:49:08.588781Z","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":"2026-08-16T11:49:09.088342Z","title":"Motionctrl: A unified and flexible motion con- troller for video generation","venue":null,"work_id":"d1133e63-3f27-4f4d-8536-0dd9896c7be1","year":2024},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.593064Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:aef00e08ab7cce735c1d2d0d62c306271c3c9c154e9a4249739b8d3c73f8c609","observation_id":"b1e90a1e-e17f-40a6-b977-d720c5bd9eb0","resolution":{"observed_at":"2026-08-16T11:49:09.093181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.05020","last_updated":"2025-03-10T10:46:31Z","snapshot_observed_at":"2026-08-11T01:07:29.677090Z","submitted_at":"2025-01-09T07:23:48Z","title":"Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.05020","snapshot_observed_at":"2026-08-16T11:49:08.597297Z","title":"Perception-as-control: Fine-grained controllable image animation with 3d-aware motion representation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.597297Z"},"links":{"cited_paper":"/paper/2501.05020","citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:5ff3ef606943e3fdf8db4afc8928072160ac524ee99b5011680db75fd060bb4c","observation_id":"b9db159b-ceaa-4cdf-8cf7-9d91c6f90420","resolution":{"observed_at":"2026-08-16T11:49:08.597297Z","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":"2026-08-16T11:49:09.072479Z","title":"Sparsectrl: Adding sparse controls to text-to-video diffusion models","venue":null,"work_id":"c472a5d7-89bc-4f6d-a643-d28eac41e3f1","year":2024},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.601457Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:f1f0863013910d34cac91f58b308a65c47b0e1285d3b3d50ff8cc2423c2d0935","observation_id":"4b883de0-f65c-4e7d-8ab8-712250b69dbc","resolution":{"observed_at":"2026-08-16T11:49:09.078274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08576","last_updated":"2023-10-12T17:59:23Z","snapshot_observed_at":"2026-08-16T14:52:35.031233Z","submitted_at":"2023-10-12T17:59:23Z","title":"Learning to Act from Actionless Videos through Dense Correspondences","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08576","snapshot_observed_at":"2026-08-16T11:49:08.605524Z","title":"Learning to act from ac- tionless videos through dense correspondences","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.605524Z"},"links":{"cited_paper":"/paper/2310.08576","citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:d8d644b06d24abfa66b53e01f699e669443504c07d754b7bc62ab16cd489b379","observation_id":"86b2ded8-4b73-4ca4-be49-b9ee6debf133","resolution":{"observed_at":"2026-08-16T11:49:08.605524Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.05530","last_updated":"2025-05-18T04:20:01Z","snapshot_observed_at":"2026-08-16T13:36:21.355035Z","submitted_at":"2024-07-08T00:28:41Z","title":"This&That: Language-Gesture Controlled Video Generation for Robot Planning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.05530","snapshot_observed_at":"2026-08-16T11:49:08.609961Z","title":"This&that: Language-gesture controlled video generation for robot planning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.609961Z"},"links":{"cited_paper":"/paper/2407.05530","citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:75bb5ee45033b3d0ae62b8e6c2687ca58bbc71ae164fd5483318486757b79b21","observation_id":"24600266-4422-4441-bc11-111d4b261db0","resolution":{"observed_at":"2026-08-16T11:49:08.609961Z","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":"2026-08-16T11:49:09.057752Z","title":"Learning universal policies via text-guided video generation","venue":null,"work_id":"3dccd4a9-604f-4c84-ac68-fb6f979b3f15","year":2023},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.614746Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:b4ecea1b81143708e19636b99b8584d419d136306c58357488fa19a9fd973c10","observation_id":"af71635e-d804-48e4-9186-77757806461b","resolution":{"observed_at":"2026-08-16T11:49:09.062712Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:49:09.043194Z","title":"Unisim: A neural closed-loop sensor sim- ulator","venue":null,"work_id":"e4cae658-49f2-45c5-a00c-cee5f7d21ec2","year":2023},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.619365Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:f9653ac76d7a1214e1d0a2dc4f23689ebceaa7de62e64807e729fe89c6155257","observation_id":"881c7825-bc12-4680-a7ea-8dd7c527b47c","resolution":{"observed_at":"2026-08-16T11:49:09.047804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10076","last_updated":"2025-02-09T05:57:42Z","snapshot_observed_at":"2026-08-18T15:03:20.669874Z","submitted_at":"2024-10-14T01:39:56Z","title":"VideoAgent: Self-Improving Video Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10076","snapshot_observed_at":"2026-08-16T11:49:08.623756Z","title":"Videoagent: Self-improving video gener- ation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.623756Z"},"links":{"cited_paper":"/paper/2410.10076","citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:29478d9204f795b091986b6051b9f58bebd81a8bc8715f264c9084d1f7057583","observation_id":"6be90b29-d3d8-4e7b-9f61-ba1ff139b3b3","resolution":{"observed_at":"2026-08-16T11:49:08.623756Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1504.06852","last_updated":"2015-05-04T08:50:57Z","snapshot_observed_at":"2026-08-14T22:50:59.749148Z","submitted_at":"2015-04-26T17:30:32Z","title":"FlowNet: Learning Optical Flow with Convolutional Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1504.06852","snapshot_observed_at":"2026-08-16T11:49:08.628406Z","title":"Flownet: Learning optical flow with convolutional net- works","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.628406Z"},"links":{"cited_paper":"/paper/1504.06852","citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:a75a73cdf0faa7ec22c5b52f42f359bd811cf1401709bda751f4e3729660d537","observation_id":"afff4eac-caed-452b-8041-76fbfcf32cde","resolution":{"observed_at":"2026-08-16T11:49:08.628406Z","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":"2026-08-16T11:49:09.027686Z","title":"Efficient sparse- to-dense optical flow estimation using a learned basis and layers","venue":null,"work_id":"736bb470-db6a-4ad6-b232-bb52427d2bdb","year":2015},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.633424Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:4e319fd8bda93740f7e88aa00127bfe1ac80ca8515f46eb6df5ef5ac81328336","observation_id":"83b095d8-1bf3-410d-b752-a891cb7af63b","resolution":{"observed_at":"2026-08-16T11:49:09.032547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-16T11:49:08.638338Z","title":"Elucidating the design space of diffusion-based generative models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.638338Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:23d51bc779c5239558da8564d55fb3160c8b381198782af7cac2a00e53c9f282","observation_id":"8bd5cf96-7da1-4653-8ce6-aeb9ccb36221","resolution":{"observed_at":"2026-08-16T11:49:08.638338Z","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":"2026-08-16T11:49:09.001713Z","title":"Dense optical tracking: Connecting the dots","venue":null,"work_id":"0926b406-3e70-4c3e-a390-965fc8be21e1","year":2024},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.642910Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:3aa63dd1dce9be6ebc4af622ffa4e99e6432d26c0e7c5f818a534eabb022289a","observation_id":"56796982-f0f3-4eef-a1ff-aaffde9d3802","resolution":{"observed_at":"2026-08-16T11:49:09.006946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15127","last_updated":"2023-11-25T22:28:38Z","snapshot_observed_at":"2026-08-20T09:39:07.545813Z","submitted_at":"2023-11-25T22:28:38Z","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.15127","snapshot_observed_at":"2026-08-16T11:49:08.647325Z","title":"Stable video diffusion: Scaling latent video diffu- sion models to large datasets","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.647325Z"},"links":{"cited_paper":"/paper/2311.15127","citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:9448b119155fd595049dd779a3090f71a5a894a163921e90d86a63dd0f0dd8aa","observation_id":"d6a6c667-ffa3-4e36-a1f9-7e50bb54f8fb","resolution":{"observed_at":"2026-08-16T11:49:08.647325Z","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":"2026-08-16T11:49:08.651940Z","title":"Bridgedata v2: A dataset for robot learning at scale","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.651940Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:1c860e75e972af930e4bcb13fa74b7192a21097053617f9ab3bcd8a7b9975790","observation_id":"58f04020-3bd9-4cb8-898b-7d87c87b7d24","resolution":{"observed_at":"2026-08-16T11:49:08.651940Z","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":"2026-08-16T11:49:08.975222Z","title":"Film: Visual reason- ing with a general conditioning layer","venue":null,"work_id":"79e0f311-e868-4e1f-9e06-12f791d63ace","year":2018},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.656386Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:300345ba816fba66476b6055fd485f6f4fe0eeba7834c8b414b6f35609d86463","observation_id":"69bb75bd-81bd-4a9d-aaf4-2321ecaed664","resolution":{"observed_at":"2026-08-16T11:49:08.979886Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:49:08.960146Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","venue":null,"work_id":"c03a033b-ccfc-4cba-a9d2-93d201652d98","year":2017},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.660673Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:cf0706acda6c985bfe6eb2e50cb632b0476a8b3cf0d7951902dd651ad2abadbf","observation_id":"1e6d4f00-93d6-48a1-8288-a15b6e668c0d","resolution":{"observed_at":"2026-08-16T11:49:08.965017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:49:08.945344Z","title":"Bovik, H.R","venue":null,"work_id":"7dad9945-3702-47de-b6bb-232f09a0bc41","year":2004},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.664953Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:20d57ef80a3609540cd6aca403cafc61f0911a5af5fdd37dd93c6557c39dd5da","observation_id":"965a5b2b-96a0-4a04-ad74-dea1071309c1","resolution":{"observed_at":"2026-08-16T11:49:08.949881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:49:08.930867Z","title":"Image quality metrics: Psnr vs","venue":null,"work_id":"5f3e83bb-fbb1-4dd2-b34b-c8b1caca25e2","year":2010},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.669701Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:9547d4272eacc44c56b6dbcaf65076d380c3d2c662f267c8c7ac0b57de495a27","observation_id":"c3c661d7-57bb-4493-b50c-670ce34d6d69","resolution":{"observed_at":"2026-08-16T11:49:08.935241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:49:08.916651Z","title":"The unreasonable effectiveness of deep features as a perceptual metric","venue":null,"work_id":"11928616-55a0-4fff-81c9-73bd8b7ae325","year":2018},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.675377Z"},"links":{"citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:660eb2355ff855fbe86bafafa4c16dfbb4485fd04665494f58ad4ff6ccbe218b","observation_id":"131fe764-c74b-444b-be34-0d959ee61567","resolution":{"observed_at":"2026-08-16T11:49:08.920835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.01717","last_updated":"2019-03-27T16:43:17Z","snapshot_observed_at":"2026-08-18T04:00:09.136122Z","submitted_at":"2018-12-03T03:57:42Z","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.01717","snapshot_observed_at":"2026-08-16T11:49:08.680321Z","title":"Towards accurate generative models of video: A new metric & challenges","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T11:49:08.680321Z"},"links":{"cited_paper":"/paper/1812.01717","citing_paper":"/paper/2504.14535"},"observation_digest":"sha256:6a928364935a5caa65f8a422a611c67c87dab1e39c97b493f52680cba161599b","observation_id":"43cbee19-e1e2-4b92-a8b7-6b0131d29c70","resolution":{"observed_at":"2026-08-16T11:49:08.680321Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2504.14535","last_updated":"2025-04-20T08:22:29Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-19T01:49:12.723591Z","submitted_at":"2025-04-20T08:22:29Z","title":"FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":1,"verified_fuzzy":23},"total_outbound_references":39},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2504.14535."}