{"as_of":"2026-08-05T11:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cf24de585aa07f8876a05ba0742511b131b867e608b4f96d80b1c395c0ea3fa9","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T13:45:43.662583Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+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/2605.28203/citation-record","integrity":"/paper/2605.28203/integrity","json":"/paper/2605.28203/citation-record.json","paper":"/paper/2605.28203"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.20314","last_updated":"2025-04-19T02:22:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-26T08:25:43Z","title":"Wan: Open and Advanced Large-Scale Video Generative Models","version":2},"cited_work":{"arxiv_id":"2503.20314","doi":"10.1109/19.492748","metadata_source":"pith","pith_arxiv_id":"2503.20314","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Wan: Open and Advanced Large-Scale Video Generative Models","venue":"cs.CV","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","year":2025},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"cited_paper":"/paper/2503.20314","citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:01a63cce2319cfabe763f463dfc7dfb2b1f07f0473ce1d7363b34f7e60c5c4bc","observation_id":"4c2c8276-929f-4132-910e-93a09e36b4f1","resolution":{"observed_at":"2026-06-29T13:53:28.899896Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2512.16776","last_updated":"2025-12-18T17:08:12Z","snapshot_observed_at":"2026-07-06T22:39:28.855621Z","submitted_at":"2025-12-18T17:08:12Z","title":"Kling-Omni Technical Report","version":1},"cited_work":{"arxiv_id":"2512.16776","doi":"10.48550/arxiv.2512.16776","metadata_source":"pith","pith_arxiv_id":"2512.16776","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Kling-Omni Technical Report","venue":"cs.CV","work_id":"52d502bd-9d8e-4944-9bf2-cfd097cfdb4e","year":2025},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"cited_paper":"/paper/2512.16776","citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:132b94c85e9f1eccd2158c1dda46ceb181ad677d9b47f19c2e49611ac0514958","observation_id":"c0485399-117f-40bb-ad74-2277ecb07f06","resolution":{"observed_at":"2026-06-29T13:53:28.907216Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-10T21:18:49.73319+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-10T21:18:49.73319+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.03603","last_updated":"2025-03-11T08:14:25Z","snapshot_observed_at":"2026-08-03T00:44:01.942521Z","submitted_at":"2024-12-03T23:52:37Z","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","version":6},"cited_work":{"arxiv_id":"2412.03603","doi":"10.48550/arxiv.2412.03603","metadata_source":"pith","pith_arxiv_id":"2412.03603","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","venue":"cs.CV","work_id":"881efa7e-7e73-4c66-9cc3-2803e551061c","year":2024},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"cited_paper":"/paper/2412.03603","citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:431789a58b6872c80c0cfc41cefd05483bc94d02d46a61e9bac568418aa605c4","observation_id":"8ab92f39-c31d-483b-9ec0-35b012df52d5","resolution":{"observed_at":"2026-06-29T13:53:28.892190Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-10T21:18:49.433177+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-10T21:18:49.433177+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15127","last_updated":"2023-11-25T22:28:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","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":"2311.15127","doi":"10.48550/arxiv.2311.15127","metadata_source":"pith","pith_arxiv_id":"2311.15127","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","venue":"cs.CV","work_id":"4f68eada-27e3-437a-a2fe-6e4ca524d0d3","year":2023},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"cited_paper":"/paper/2311.15127","citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:9f8e23cfe34f2233b210aac5fbbe11e611a0b2d2ee1a1e58f0964997f93b1ddf","observation_id":"bf11c1c6-6a14-4e5c-ab7d-39411e582ab8","resolution":{"observed_at":"2026-06-29T13:53:28.909933Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-11T15:53:24.472993+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T15:53:24.472993+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.15868","last_updated":"2022-05-29T19:02:15Z","snapshot_observed_at":"2026-07-06T13:15:58.303738Z","submitted_at":"2022-05-29T19:02:15Z","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","version":1},"cited_work":{"arxiv_id":"2205.15868","doi":"10.48550/arxiv.2205.15868","metadata_source":"pith","pith_arxiv_id":"2205.15868","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","venue":"cs.CV","work_id":"2dbd6bcd-fc98-4fbf-b586-f6d94fe1abd2","year":2022},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"cited_paper":"/paper/2205.15868","citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:b353a0d9db0d0059de74b8d17d428b9b81d7ffb0f14e28e6113ed6a01d189ffb","observation_id":"4664f098-c94d-4e92-85b1-24f4dafe3c0e","resolution":{"observed_at":"2026-06-29T13:53:28.902384Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.06571","last_updated":"2023-08-12T13:53:10Z","snapshot_observed_at":"2026-07-06T16:05:35.645037Z","submitted_at":"2023-08-12T13:53:10Z","title":"ModelScope Text-to-Video Technical Report","version":1},"cited_work":{"arxiv_id":"2308.06571","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.06571","snapshot_observed_at":"2026-07-11T01:57:50.025885Z","title":"ModelScope Text-to-Video Technical Report","venue":"cs.CV","work_id":"1b1baf78-58ec-44d0-b700-84dff57b2f1f","year":2023},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"cited_paper":"/paper/2308.06571","citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:e02c64284227d88e36a60cbdeb3fed56f244b7897d7bde0875437140af82a4f8","observation_id":"a076c62b-6e82-4c83-9a32-6b0e72b6b0ee","resolution":{"observed_at":"2026-06-29T13:53:28.875499Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-29T13:45:43.662583Z","title":"Learning to summarize with human feedback","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:4a508ee20fb3de8b2d2a82897a788456ed669d1087d25905c916c277dfb3a3a7","observation_id":"a40fbba8-4cab-4222-a0bb-282c461071c5","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.08593","last_updated":"2020-01-08T23:02:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2019-09-18T17:33:39Z","title":"Fine-Tuning Language Models from Human Preferences","version":2},"cited_work":{"arxiv_id":"1909.08593","doi":"10.48550/arxiv.1909.08593","metadata_source":"pith","pith_arxiv_id":"1909.08593","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Fine-Tuning Language Models from Human Preferences","venue":"cs.CL","work_id":"4f54aad1-f3b6-404f-b9c7-e21ba0a33b99","year":2019},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"cited_paper":"/paper/1909.08593","citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:4f8367fe5446f4ee4f3aeb91bb75b811ebc5ab16318bdf02fc1991068aa8e526","observation_id":"37839c27-50ea-4692-81c1-c7366237d90b","resolution":{"observed_at":"2026-06-29T13:53:28.904611Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-18T08:21:06.631932+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-18T08:21:06.631932+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-29T13:45:43.662583Z","title":"Deep reinforcement learning from human preferences.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:105ac81c08fba1b1397d78181a3f79bac067a3bda1abe903558e09fb2943cb4e","observation_id":"f863fe9b-6d4e-40d9-b2e2-4e51f42ad9ad","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Evalcrafter: Benchmarking and evaluating large video generation models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:5bd953a67122ba906f23be5c51296566d8e46fb0df6237f12c86d135337fc664","observation_id":"ba7a37b0-d7c5-481c-8ff6-a6c6cd6e018a","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Vbench: Comprehensive benchmark suite for video generative models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:d22dcac8c9ecb95f19959e7ad33ae208184e898b5533bce37331db68a3f5c39e","observation_id":"7940855a-6a7f-45c0-8017-46ed7d2a4a2a","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Fetv: A benchmark for fine-grained evaluation of open-domain text-to-video generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:3a6c7096612e3f0dcb5601a5fa16e0a795bfe3096acf3294c73699f584eef9e5","observation_id":"a3965412-3538-4c15-a62e-22829ad11376","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Mj-video: Benchmarking and rewarding video generation with fine-grained video preference","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:02808a6c44088856f64d4259844a5aaff64a0361cf32712912592686812204f0","observation_id":"8bebce10-846c-425b-8845-a11f0662afa8","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Videoscore: Building automatic metrics to simulate fine-grained human feedback for video generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:2c299b9b5a4ae28e4eb0dda18db8d528e99dc0ef8ed2334fdf42570caaf2c005","observation_id":"dcfdb1db-f566-4193-837a-949c57f3cbe5","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.21059","last_updated":"2026-01-05T02:39:01Z","snapshot_observed_at":"2026-08-03T02:30:08.318253Z","submitted_at":"2024-12-30T16:24:09Z","title":"VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation","version":4},"cited_work":{"arxiv_id":"2412.21059","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.21059","snapshot_observed_at":"2026-07-03T00:07:27.977777Z","title":"VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation","venue":"cs.CV","work_id":"63f252a7-e52d-4e87-b849-d1375bee5b37","year":2024},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"cited_paper":"/paper/2412.21059","citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:8bb89584ddc30cc6bb7d3827fab4348ff28a8a001bbbf716c71804993fbde230","observation_id":"b80344cc-a755-4576-b0c0-b251f7386931","resolution":{"observed_at":"2026-06-29T13:53:28.892673Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.13918","last_updated":"2025-10-27T08:22:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-23T18:55:41Z","title":"Improving Video Generation with Human Feedback","version":2},"cited_work":{"arxiv_id":"2501.13918","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.13918","snapshot_observed_at":"2026-07-04T13:19:51.115512Z","title":"Improving Video Generation with Human Feedback","venue":"cs.CV","work_id":"cfe4c01d-1cf7-4a00-ba86-06d583ca2cff","year":2025},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"cited_paper":"/paper/2501.13918","citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:98c522f3d6c715b3413977e51b31b2231de6e5be6563806b5025460539518d59","observation_id":"3d41a57a-bb1c-4ef2-9d28-fc1946c0eb42","resolution":{"observed_at":"2026-06-29T13:53:28.889766Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.05790","last_updated":"2025-09-01T04:51:13Z","snapshot_observed_at":"2026-07-06T20:19:07.706492Z","submitted_at":"2025-01-10T08:50:38Z","title":"Understanding Impact of Human Feedback via Influence Functions","version":3},"cited_work":{"arxiv_id":"2501.05790","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.05790","snapshot_observed_at":"2026-06-29T13:53:28.895820Z","title":"Motwani, S","venue":null,"work_id":"c37ef38b-f5db-4325-88be-0dcdbba483cd","year":2025},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"cited_paper":"/paper/2501.05790","citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:c1f3459796ae9ead9085bb159e9aeb1dd98b6bf000f4d61756b1900f0c83a499","observation_id":"6a9f8b96-9fd2-43a4-886b-b1379412f12b","resolution":{"observed_at":"2026-06-29T13:53:28.897339Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-29T13:45:43.662583Z","title":"Understanding black-box predictions via influence functions","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:1d2279ad65a4ee3564024653aae949e8c961a8b777c3d6ef54c720882247abd9","observation_id":"a3d09cd6-24e5-47fc-8904-432954eb2bf0","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Estimating training data influence by tracing gradient descent.Advances in Neural Information Processing Systems, 33:19920–19930, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:def40b11dcb1960180f319eebeb4102085f1a6ebccf059435fb6bf95b048447b","observation_id":"714183a3-e9ff-4cb4-af5e-ec38b31b5deb","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Boosting text-to-video generative model with mllms feedback.Advances in Neural Information Processing Systems, 37:139444–139469, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:eca7839d720f5c0f57b1ae8d1667244267cb5c24ccbedeaf6a434b333162db4d","observation_id":"96664d27-0c83-416c-bdd6-c85d53cd4e00","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.01717","last_updated":"2019-03-27T16:43:17Z","snapshot_observed_at":"2026-07-06T07:19:11.957225Z","submitted_at":"2018-12-03T03:57:42Z","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","version":2},"cited_work":{"arxiv_id":"1812.01717","doi":"10.48550/arxiv.1812.01717","metadata_source":"pith","pith_arxiv_id":"1812.01717","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","venue":"cs.CV","work_id":"72f42543-17d5-49aa-ba5a-25d67ffbb88a","year":2018},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"cited_paper":"/paper/1812.01717","citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:217334a4310a89ed293bea1d609ea8f98d15486cf0247fb87e0bda8478524788","observation_id":"11d8e0d6-b12e-458b-bd89-944291fe8891","resolution":{"observed_at":"2026-06-29T13:53:28.894710Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-29T13:45:43.662583Z","title":"Clipscore: A reference-free evaluation metric for image captioning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:a2a26f89cafed2fed34f88142f9def7a366a111e69697e433a60a921bfb56fbf","observation_id":"b6c95465-430f-4bf5-9683-596fe0f6e968","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Mantis: Interleaved multi-image instruction tuning.Transactions on Machine Learning Research","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:add6f2dbf8f01170502de7a768c1a97e6772bee7a6e15d31ee759402d1ca88ab","observation_id":"f86c4e7d-8f54-401d-81a0-c8491b3bb0dd","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Video-llava: Learning united visual representation by alignment before projection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:32067f9f8e62fbb5864d35106eca0c6210f743a9a03cbe004b283b8f88a474eb","observation_id":"1aa8b947-42b5-48c7-b7b6-13fd4bc18810","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:338400066700f1f1d32cf3288aaa9000ddf068afc79c6c334ad1915899c01a8f","observation_id":"0e0ffc87-f1c3-4624-a199-268e91361696","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Gradient surgery for multi-task learning.Advances in neural information processing systems, 33:5824–5836, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:6e7a48f0a1956327efa013de7903db62415f63e771739e4c4c84ac5259640137","observation_id":"4a58cd9d-9adc-4d8a-a649-7b7767a311a0","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Reasonable effectiveness of random weighting: A litmus test for multi-task learning.Transactions on Machine Learning Research","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:01854df2400a6aaa7a2bc439aea51e16862172d0e93a27470f3a3c2c1f2750c7","observation_id":"c17ec987-0d2e-418f-a3e4-4b5fb974f382","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Data pruning via moving-one-sample-out.Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:04e285c72be50b6dccf3eb1cd6828fcae49c85659130715ee8543eae73ed1070","observation_id":"6e71559e-bd07-466a-8447-49c8c528a8ea","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":"Relatif: Identifying explanatory training samples via relative influence","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:70b0c7a2b5fcb3a1e690be77429dc4c2e6750755b04fbf6017f0ea9f67c3db12","observation_id":"7171cf9b-fc48-4ded-b42f-8a5dcd90a4c6","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.14186","last_updated":"2023-04-03T17:37:50Z","snapshot_observed_at":"2026-07-06T15:07:45.408464Z","submitted_at":"2023-03-24T17:56:22Z","title":"TRAK: Attributing Model Behavior at Scale","version":2},"cited_work":{"arxiv_id":"2303.14186","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.14186","snapshot_observed_at":"2026-07-03T19:18:54.731155Z","title":"Trak: Attributing model behavior at scale.arXiv preprint arXiv:2303.14186","venue":null,"work_id":"67157c45-de2e-4822-9316-57b0a8c904a5","year":2023},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"cited_paper":"/paper/2303.14186","citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:2ef6de97bfd0fe9d9a2293b0c221daa2942863d1bc1ddc6a6790a8f8b78bba42","observation_id":"6f4b982d-32d4-4d04-933c-bba738f1c738","resolution":{"observed_at":"2026-06-29T13:53:28.884287Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-29T13:45:43.662583Z","title":"Fast approximate natural gradient descent in a kronecker factored eigenbasis.Advances in neural information processing systems, 31, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:2194f5ffe0aaf82a3b95f1236e922b57b2383b43515a61f99f1ca61b41d7ee17","observation_id":"4a96ac10-48b2-4b86-b11a-0a2810fb293a","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.11599","last_updated":"2024-04-17T17:50:24Z","snapshot_observed_at":"2026-07-06T18:01:45.549839Z","submitted_at":"2024-04-17T17:50:24Z","title":"Variational Bayesian Last Layers","version":1},"cited_work":{"arxiv_id":"2404.11599","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.11599","snapshot_observed_at":"2026-07-10T21:37:41.900723Z","title":"arXiv preprint arXiv:2404.11599 , year=","venue":"cs.LG","work_id":"4b46a107-0c5d-40b5-9f15-7de1d82255af","year":2024},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"cited_paper":"/paper/2404.11599","citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:c28a900e040b824031782ae8afc007430638e888e74ad803026be263c2deb399","observation_id":"cd6594cc-e897-44bf-a580-37e8033248b2","resolution":{"observed_at":"2026-06-29T13:53:28.884633Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-29T13:45:43.662583Z","title":"Genai arena: An open evaluation platform for generative models.Advances in Neural Information Processing Systems, 37:79889–79908, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:f4627628e459a6af25a17361913ae14560d8e6a92884997a2253f78ff69e734d","observation_id":"19cd5792-f147-4146-83e8-6e16e2e8bb79","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2026-06-29T13:45:43.662583Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:bc200902b1787ef7c2a11dc5edaceb4b6b483a3662b8cde050ca9d69ce6b393e","observation_id":"37ea4c01-51e4-438c-84b8-f1a755cfbf4d","resolution":{"observed_at":"2026-06-29T13:45:43.662583Z","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":"2758.9249","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T13:53:28.880335Z","title":null,"venue":null,"work_id":"fb1b1147-2805-4d5d-b6b4-6d21c57b18a4","year":null},"citing_paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-29T13:45:43.662583Z"},"links":{"citing_paper":"/paper/2605.28203"},"observation_digest":"sha256:0bb3bdab88434cf0fb3ddc7f5995e9d28b043dd9ce81fe0b2bd734b9a27c24ae","observation_id":"766f9afa-8562-49f3-98be-6e10a0398c11","resolution":{"observed_at":"2026-06-29T13:53:28.881925Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.28203","last_updated":"2026-05-27T09:26:46Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T23:37:50.157617Z","submitted_at":"2026-05-27T09:26:46Z","title":"Refining Multidimensional Video Reward Models via Disentangled Influence Functions"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":21,"verified_exact":13,"verified_fuzzy":0},"total_outbound_references":35},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2605.28203."}