{"as_of":"2026-08-16T00:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ee74221f28ac6b0de40d555cf3de28c940443b61897d54a4d389590a9455ae9b","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T23:59:17.993681Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T00:38:02.427407Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-03T01:37:30.404151Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"cited_work":{"arxiv_id":"2602.12155","doi":null,"metadata_source":"pith","pith_arxiv_id":"2602.12155","snapshot_observed_at":"2026-07-03T01:37:30.404151Z","title":"Fail: Flow matching adversarial imitation learning for image generation","venue":"cs.CV","work_id":"233c9e43-dac7-4711-8475-7ea9b9004be0","year":2026},"citing_paper":{"arxiv_id":"2604.13602","last_updated":"2026-04-15T08:11:34Z","snapshot_observed_at":"2026-08-15T05:29:27.850072Z","submitted_at":"2026-04-15T08:11:34Z","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","version":1},"reference_index":174,"source":"pdf_text","source_observed_at":"2026-05-10T13:58:53.430492Z"},"links":{"cited_paper":"/paper/2602.12155","citing_paper":"/paper/2604.13602"},"observation_digest":"sha256:141e5548014cf54dd8c52270b3ccbdf376523e204a45d2e56203f3d2623d1931","observation_id":"d28d6489-dbe1-4a67-a3b1-d5ceb1e74a9e","resolution":{"observed_at":"2026-06-30T03:17:27.371081Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"cited_work":{"arxiv_id":"2602.12155","doi":null,"metadata_source":"pith","pith_arxiv_id":"2602.12155","snapshot_observed_at":"2026-07-03T01:37:30.404151Z","title":"Fail: Flow matching adversarial imitation learning for image generation","venue":"cs.CV","work_id":"233c9e43-dac7-4711-8475-7ea9b9004be0","year":2026},"citing_paper":{"arxiv_id":"2606.09711","last_updated":"2026-06-08T16:32:54Z","snapshot_observed_at":"2026-07-06T23:49:03.237958Z","submitted_at":"2026-06-08T16:32:54Z","title":"Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization","version":1},"reference_index":286,"source":"arxiv_source","source_observed_at":"2026-06-27T16:26:34.918099Z"},"links":{"cited_paper":"/paper/2602.12155","citing_paper":"/paper/2606.09711"},"observation_digest":"sha256:e3df7d64315af42d56e6bbee629bcefe3721967781e2ec7b05f697e494347c07","observation_id":"df89d157-c801-4394-b017-29a36d388137","resolution":{"observed_at":"2026-07-03T01:37:30.405440Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.12155","snapshot_observed_at":"2026-08-05T00:38:02.427407Z","title":"arXiv preprint arXiv:2602.12155 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.00572","last_updated":"2026-08-01T10:14:43Z","snapshot_observed_at":"2026-08-15T10:54:13.936301Z","submitted_at":"2026-08-01T10:14:43Z","title":"AnyBand: Unified Multi-Bandwidth Speech Extension via Frequency-Aware In-Context Spectral Infilling","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-05T00:38:02.427407Z"},"links":{"cited_paper":"/paper/2602.12155","citing_paper":"/paper/2608.00572"},"observation_digest":"sha256:43e8729ffae362884c66bb6238b9d278056ed4a36ae6438b92ac5326bb3e0ef0","observation_id":"dc0c84c3-4acb-4a32-8d6f-2d329ef53ada","resolution":{"observed_at":"2026-08-05T00:38:02.427407Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2602.12155/citation-record","integrity":"/paper/2602.12155/integrity","json":"/paper/2602.12155/citation-record.json","paper":"/paper/2602.12155"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.17811","last_updated":"2025-01-29T18:00:19Z","snapshot_observed_at":"2026-08-12T12:44:22.350068Z","submitted_at":"2025-01-29T18:00:19Z","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.17811","snapshot_observed_at":"2026-08-02T23:59:13.320139Z","title":"Janus-pro: Unified multimodal understand- ing and generation with data and model scaling.arXiv preprint arXiv:2501.17811,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:13.320139Z"},"links":{"cited_paper":"/paper/2501.17811","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:148ed646b36e33f2e22f15274ef75732b2892801ce56e7a31891259fb747f736","observation_id":"a0b4121d-4ba3-494b-93fd-44031dafec3f","resolution":{"observed_at":"2026-08-02T23:59:13.320139Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15807","last_updated":"2023-09-27T17:30:19Z","snapshot_observed_at":"2026-08-15T07:12:45.000333Z","submitted_at":"2023-09-27T17:30:19Z","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15807","snapshot_observed_at":"2026-08-02T23:59:13.788036Z","title":"Emu: Enhancing image generation models us- ing photogenic needles in a haystack.arXiv preprint arXiv:2309.15807,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:13.788036Z"},"links":{"cited_paper":"/paper/2309.15807","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:15113ee7d3ce1b736e6a17bc7292aaf3b3c4337edb243088ad0757d739f7322d","observation_id":"86223844-178b-4219-962d-5a12096217af","resolution":{"observed_at":"2026-08-02T23:59:13.788036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.11248","last_updated":"2018-08-13T18:33:24Z","snapshot_observed_at":"2026-08-14T20:18:41.596978Z","submitted_at":"2017-10-30T21:22:28Z","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.11248","snapshot_observed_at":"2026-08-02T23:59:13.978878Z","title":"Learning robust rewards with adversarial inverse reinforcement learning.arXiv preprint arXiv:1710.11248, 2017a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:13.978878Z"},"links":{"cited_paper":"/paper/1710.11248","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:92840f8016c298a9aabe69da99c54f7f378e8a5302448d2bf3b98e41aa045650","observation_id":"274bffed-081c-426a-b544-abf5f793c6a0","resolution":{"observed_at":"2026-08-02T23:59:13.978878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.22058","last_updated":"2025-07-29T17:59:04Z","snapshot_observed_at":"2026-08-15T19:53:33.201174Z","submitted_at":"2025-07-29T17:59:04Z","title":"X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.22058","snapshot_observed_at":"2026-08-02T23:59:14.132457Z","title":"X-omni: Reinforcement learning makes discrete autoregressive image generative models great again.arXiv preprint arXiv:2507.22058,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:14.132457Z"},"links":{"cited_paper":"/paper/2507.22058","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:62d785fe2e9b6f763a4ba1990c3f17310725e97b62125b03aa49f8b8447b0cc7","observation_id":"4a78692d-2783-4952-afa1-acbe16800b3f","resolution":{"observed_at":"2026-08-02T23:59:14.132457Z","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":"2026-08-02T23:59:17.862417Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:17.862417Z"},"links":{"citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:7aaff1d0bd32fd55b2458f20cfd2726b18484329a9c4b1a33fdd9940b2a9611e","observation_id":"bb9e4bf9-2c61-4835-8079-70bdef6dd9ca","resolution":{"observed_at":"2026-08-02T23:59:17.862417Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.02925","last_updated":"2018-10-15T17:27:25Z","snapshot_observed_at":"2026-08-14T18:31:08.421832Z","submitted_at":"2018-09-09T05:37:25Z","title":"Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.02925","snapshot_observed_at":"2026-08-02T23:59:14.512941Z","title":"K., Dwibedi, D., Levine, S., and Tompson, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:14.512941Z"},"links":{"cited_paper":"/paper/1809.02925","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:89fca94107a83a5c6757b6b684ecaa06645e05d3ce65b132a4c8844249abee86","observation_id":"4eb4d2eb-7ccc-42e0-8226-b093c5bc099c","resolution":{"observed_at":"2026-08-02T23:59:14.512941Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.15742","last_updated":"2025-06-24T05:31:03Z","snapshot_observed_at":"2026-08-14T01:48:52.921086Z","submitted_at":"2025-06-17T20:18:23Z","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.15742","snapshot_observed_at":"2026-08-02T23:59:14.925936Z","title":"F., Batifol, S., Blattmann, A., Boesel, F., Con- sul, S., Diagne, C., Dockhorn, T., English, J., English, Z., Esser, P., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:14.925936Z"},"links":{"cited_paper":"/paper/2506.15742","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:c6cb8901a0d2b6f3f815b573dd754b412f4e0620de973ea03d00b96df6aa3b49","observation_id":"94d76a06-1e3d-4784-acdf-3d4c5bdff26f","resolution":{"observed_at":"2026-08-02T23:59:14.925936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17245","last_updated":"2024-02-27T06:31:52Z","snapshot_observed_at":"2026-07-06T17:36:01.939242Z","submitted_at":"2024-02-27T06:31:52Z","title":"Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17245","snapshot_observed_at":"2026-08-02T23:59:15.072317Z","title":"Playground v2","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:15.072317Z"},"links":{"cited_paper":"/paper/2402.17245","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:3ccf1c646226105a909aed59e12cbc71ac32f6d7ca35a49e4369d3c1d1042b7e","observation_id":"f78ed658-46cc-4566-baf4-fed0239a4fe0","resolution":{"observed_at":"2026-08-02T23:59:15.072317Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.05470","last_updated":"2025-10-27T09:57:02Z","snapshot_observed_at":"2026-08-13T10:15:00.293616Z","submitted_at":"2025-05-08T17:58:45Z","title":"Flow-GRPO: Training Flow Matching Models via Online RL","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.05470","snapshot_observed_at":"2026-08-02T23:59:15.386262Z","title":"Flow-grpo: Training flow matching models via online rl.arXiv preprint arXiv:2505.05470,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:15.386262Z"},"links":{"cited_paper":"/paper/2505.05470","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:33bc275220834c2501b4fffd36acff726a26b75770cbc2ad6c94ab8fb16646fc","observation_id":"8a656026-517d-4ef3-bef0-4c6615b48164","resolution":{"observed_at":"2026-08-02T23:59:15.386262Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.03003","last_updated":"2022-09-07T08:59:55Z","snapshot_observed_at":"2026-07-06T13:49:40.974495Z","submitted_at":"2022-09-07T08:59:55Z","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.03003","snapshot_observed_at":"2026-08-02T23:59:15.544483Z","title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:15.544483Z"},"links":{"cited_paper":"/paper/2209.03003","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:a019227895e221cd4e20dd8a14de93a2f0516c238146c91e100f10d2bcd6cd67","observation_id":"8f369ea5-f9c5-42c8-81cc-693911905620","resolution":{"observed_at":"2026-08-02T23:59:15.544483Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-02T23:59:15.697284Z","title":"and Hutter, F","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:15.697284Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:58cdaa5bd483b2bf12ed662d68962a72b0e1762af63b4cb73604e6c51a3484b3","observation_id":"d98f1354-21d8-462d-9250-32d032ece66a","resolution":{"observed_at":"2026-08-02T23:59:15.697284Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.03789","last_updated":"2025-08-22T08:53:37Z","snapshot_observed_at":"2026-08-07T20:35:27.515637Z","submitted_at":"2025-08-05T17:17:13Z","title":"HPSv3: Towards Wide-Spectrum Human Preference Score","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.03789","snapshot_observed_at":"2026-08-02T23:59:15.904880Z","title":"10 FAIL: Flow Matching Adversarial Imitation Learning for Image Generation Mao, W., Chen, H., Yang, Z., and Shou, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:15.904880Z"},"links":{"cited_paper":"/paper/2508.03789","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:607a6cabd44b4b3857525d778d64136309ec23afe2974bf12ae3d8e019dbd112","observation_id":"71aaac17-d079-4327-a4b9-f971fe9f3c99","resolution":{"observed_at":"2026-08-02T23:59:15.904880Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.21053","last_updated":"2025-08-01T13:04:28Z","snapshot_observed_at":"2026-08-14T04:52:19.396797Z","submitted_at":"2025-07-28T17:59:57Z","title":"Flow Matching Policy Gradients","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.21053","snapshot_observed_at":"2026-08-02T23:59:16.138832Z","title":"M., Weber, E., Choi, H., Feng, H., and Kanazawa, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:16.138832Z"},"links":{"cited_paper":"/paper/2507.21053","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:24954b1c2c9a5473e46294f3143bbee469723f8d56519d75b0878a0205307971","observation_id":"6110491d-3f52-421b-9f2f-7a52c6b18727","resolution":{"observed_at":"2026-08-02T23:59:16.138832Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-11T10:12:11.384939Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-02T23:59:16.234675Z","title":"Oquab, M., Darcet, T., Moutakanni, T., V o, H., Szafraniec, M., Khalidov, V ., Fernandez, P., Haziza, D., Massa, F., El- Nouby, A., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:16.234675Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:22a5efea9be02fae09562007e9ccd7273df4664c718589b1875697ca092e6414","observation_id":"182e82a6-cc07-40ed-b41c-2131866326e9","resolution":{"observed_at":"2026-08-02T23:59:16.234675Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.08848","last_updated":"2024-06-05T00:17:20Z","snapshot_observed_at":"2026-08-13T04:19:27.434130Z","submitted_at":"2024-02-13T23:29:09Z","title":"Hybrid Inverse Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.08848","snapshot_observed_at":"2026-08-02T23:59:16.415376Z","title":"S., Bagnell, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:16.415376Z"},"links":{"cited_paper":"/paper/2402.08848","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:3efeee789d5091d1e0079da54f75d3f22181a2aa284b8b9c8c8cd5f4b26fdd00","observation_id":"01f2ff38-0fa1-4bb2-b121-ba6cb451f60d","resolution":{"observed_at":"2026-08-02T23:59:16.415376Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-08-15T20:26:32.102285Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-02T23:59:16.749269Z","title":"Proximal policy optimization algorithms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:16.749269Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:6789ffec2b0a202607f5b2053f6e444f41e0df337b260e75ad80d160bd639093","observation_id":"06747a69-9d39-4bbc-ba0d-282da1218ef5","resolution":{"observed_at":"2026-08-02T23:59:16.749269Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.06942","last_updated":"2025-09-11T17:14:11Z","snapshot_observed_at":"2026-08-14T05:10:53.900739Z","submitted_at":"2025-09-08T17:54:08Z","title":"Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.06942","snapshot_observed_at":"2026-08-02T23:59:17.056636Z","title":"Directly aligning the full diffusion trajectory with fine-grained human preference","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:17.056636Z"},"links":{"cited_paper":"/paper/2509.06942","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:47ae1221b9ecdc15a06c8c3947296ff5c74ae07a51feef87866784f3fe44969c","observation_id":"3226be7c-d242-46f4-a027-d3641c51b797","resolution":{"observed_at":"2026-08-02T23:59:17.056636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.10104","last_updated":"2025-08-13T18:00:55Z","snapshot_observed_at":"2026-08-13T10:44:26.934833Z","submitted_at":"2025-08-13T18:00:55Z","title":"DINOv3","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.10104","snapshot_observed_at":"2026-08-02T23:59:17.124942Z","title":"Song, J., Meng, C., and Ermon, S","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:17.124942Z"},"links":{"cited_paper":"/paper/2508.10104","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:6ab8b0fbfd25c20ec89f6ee4067966b9e16dd7610a7660cbfdc6ab35f5304b12","observation_id":"e2167caf-095e-4f7b-bd71-915bfd384348","resolution":{"observed_at":"2026-08-02T23:59:17.124942Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20314","last_updated":"2025-04-19T02:22:42Z","snapshot_observed_at":"2026-08-12T22:34:51.361078Z","submitted_at":"2025-03-26T08:25:43Z","title":"Wan: Open and Advanced Large-Scale Video Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20314","snapshot_observed_at":"2026-08-02T23:59:17.243926Z","title":"Wan: Open and advanced large-scale video generative models.arXiv preprint arXiv:2503.20314,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:17.243926Z"},"links":{"cited_paper":"/paper/2503.20314","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:74211151bd2de334933dff560ad9a7fe4f8199f704821b5f170d7fd3b811c03e","observation_id":"0e4d725a-ed8e-4c67-bb7f-4566a1961c45","resolution":{"observed_at":"2026-08-02T23:59:17.243926Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.18869","last_updated":"2024-09-27T16:06:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-09-27T16:06:11Z","title":"Emu3: Next-Token Prediction is All You Need","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.18869","snapshot_observed_at":"2026-08-02T23:59:17.317623Z","title":"Emu3: Next-token prediction is all you need.arXiv preprint arXiv:2409.18869,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:17.317623Z"},"links":{"cited_paper":"/paper/2409.18869","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:5d8ef2e5bfdb2cd6189d0b3c0a96fd4e898bd8b193d4326d13f5b1b5f497f3ad","observation_id":"c032f16a-a040-4fb4-9c40-c4286e83d5b1","resolution":{"observed_at":"2026-08-02T23:59:17.317623Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.20751","last_updated":"2026-04-20T06:12:09Z","snapshot_observed_at":"2026-08-15T08:35:23.989525Z","submitted_at":"2025-08-28T13:11:24Z","title":"Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.20751","snapshot_observed_at":"2026-08-02T23:59:17.428586Z","title":"Pref-grpo: Pairwise preference reward-based grpo for stable text-to-image reinforcement learning.arXiv preprint arXiv:2508.20751, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:17.428586Z"},"links":{"cited_paper":"/paper/2508.20751","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:72b3e58099f46967cb91edbab7ada0c8bfb13121af8d7962b59902f0b9abbe50","observation_id":"5081e440-d5f6-4bc2-a884-09bb00c77df0","resolution":{"observed_at":"2026-08-02T23:59:17.428586Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.02324","last_updated":"2025-08-04T11:49:20Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-08-04T11:49:20Z","title":"Qwen-Image Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.02324","snapshot_observed_at":"2026-08-02T23:59:17.509783Z","title":"Janus: Decoupling visual encoding for unified multimodal understanding and generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:17.509783Z"},"links":{"cited_paper":"/paper/2508.02324","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:6a0ca6ad03c01aaa5f5678cdcf4487e6ce983e8815b93d9894402e88e5f2b317","observation_id":"b258675a-e4d7-4741-b290-ba436f8b0f16","resolution":{"observed_at":"2026-08-02T23:59:17.509783Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07804","last_updated":"2022-04-04T18:55:28Z","snapshot_observed_at":"2026-08-14T14:51:23.655760Z","submitted_at":"2021-12-15T00:09:38Z","title":"Tackling the Generative Learning Trilemma with Denoising Diffusion GANs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.07804","snapshot_observed_at":"2026-08-02T23:59:17.581662Z","title":"Tackling the generative learning trilemma with denoising diffusion gans.arXiv preprint arXiv:2112.07804,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:17.581662Z"},"links":{"cited_paper":"/paper/2112.07804","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:89835e292595baa7182033ea6af6054aa92ed6cc62f9dfaf2d6b69977f943383","observation_id":"2ecd5d4b-1a6c-4aef-bc49-b849fb441aa4","resolution":{"observed_at":"2026-08-02T23:59:17.581662Z","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":"2026-08-02T23:59:17.668474Z","title":"Ad- vantage weighted matching: Aligning rl with pretraining in diffusion models.arXiv preprint arXiv:2509.25050, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:17.668474Z"},"links":{"citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:88d9dbf64d7cace7748ea6b8ca2f9215fbd9e1377164663ff48ab53206a4e66f","observation_id":"17ec8c89-3e9b-4634-bb62-eab347019ae5","resolution":{"observed_at":"2026-08-02T23:59:17.668474Z","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":"2026-08-02T23:59:17.762900Z","title":"Therefore, we approximate the log-probability of a samplexunder policyπ θ as: logπθ(x)≈ −LCF M(θ, x) +C.(7) A.2","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:17.762900Z"},"links":{"citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:d68bc53a56c422e9a929c30b23c739d51bc20b85c7a14bfa63523e2cf3efb010","observation_id":"b17a2fa9-7b02-4132-993c-2e367cc34ae2","resolution":{"observed_at":"2026-08-02T23:59:17.762900Z","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":"2026-08-02T23:59:17.930672Z","title":"For inference, we generate 4 images per prompt for UniGen and DPG, and 1 image per prompt for Alchemist","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:17.930672Z"},"links":{"citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:3997dff076c702e600d8f8e259b5927da24832ba85ef8876b6000b2a9660f66b","observation_id":"95b73786-1c01-4bf2-8203-4840b05c20f1","resolution":{"observed_at":"2026-08-02T23:59:17.930672Z","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":"2026-08-02T23:59:17.993681Z","title":"Subsequently, from step 100 to 400, the optimization shifts focus to refining low-level details, resulting in significant improvements in text rendering and fine-grained textures","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:17.993681Z"},"links":{"citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:1b090a17631810ad895d5483412030c3589f39f9ae978a04ada373a08092d48e","observation_id":"38ded7db-07c0-4538-a564-121e087e3c5e","resolution":{"observed_at":"2026-08-02T23:59:17.993681Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.21631","last_updated":"2025-11-27T12:16:54Z","snapshot_observed_at":"2026-08-11T14:42:37.584016Z","submitted_at":"2025-11-26T17:59:08Z","title":"Qwen3-VL Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.21631","snapshot_observed_at":"2026-08-02T23:59:12.875366Z","title":"Qwen3-vl technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":2004,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:12.875366Z"},"links":{"cited_paper":"/paper/2511.21631","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:04d17d3221f9c89a278c30ea134bad9f0e0ea2f2618779f56814ed67ac40e44b","observation_id":"3ed0c257-6fec-4467-b33e-a268a69c9105","resolution":{"observed_at":"2026-08-02T23:59:12.875366Z","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":"2026-08-02T23:59:16.572031Z","title":"Fast high-resolution image synthe- sis with latent adversarial diffusion distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":2011,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:16.572031Z"},"links":{"citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:55c573f5c5887e5209d9d6086ec80e7697218cfe15a7a67540088ac800f793e1","observation_id":"5593e5a7-9ffa-46d9-bb08-b66bd3f16928","resolution":{"observed_at":"2026-08-02T23:59:16.572031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02747","last_updated":"2023-02-08T15:46:05Z","snapshot_observed_at":"2026-08-15T23:01:10.150957Z","submitted_at":"2022-10-06T08:32:20Z","title":"Flow Matching for Generative Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.02747","snapshot_observed_at":"2026-08-02T23:59:15.214194Z","title":"T., Ben-Hamu, H., Nickel, M., and Le, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:15.214194Z"},"links":{"cited_paper":"/paper/2210.02747","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:8aa17f21c28d8bbab5bafd77202c81fadd79dc7573fae5f3cff0f5b279c8b700","observation_id":"856a6ee4-ac84-43be-9b18-dd5e22efcbe7","resolution":{"observed_at":"2026-08-02T23:59:15.214194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-08-14T06:37:15.299690Z","submitted_at":"2022-07-26T01:42:07Z","title":"Classifier-Free Diffusion Guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.12598","snapshot_observed_at":"2026-08-02T23:59:14.302528Z","title":"and Salimans, T","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:14.302528Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:819b2f9cbb7e6c47bc4e2ca5f058dec18af574d454dda208e02d5c0fdd30015e","observation_id":"d96873e6-8d3a-4d72-965d-fbccdbc9e5f0","resolution":{"observed_at":"2026-08-02T23:59:14.302528Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-02T23:59:16.887647Z","title":"Deepseekmath: Push- ing the limits of mathematical reasoning in open language models.arXiv preprint arXiv:2402.03300,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:16.887647Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:60b15483cf120e276f1366946d7730cf986e18e5c23131193febca496ac6576d","observation_id":"521b2c4b-8a75-44fc-9bbf-d7e9050b8194","resolution":{"observed_at":"2026-08-02T23:59:16.887647Z","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":"2026-08-02T23:59:17.174609Z","title":"Alchemist: Turning public text-to-image data into generative gold.arXiv preprint arXiv:2505.19297,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:17.174609Z"},"links":{"citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:878856fe003209e21e0cd006e616af6db801d3e1eafb21d19a09f2b959c1e1d3","observation_id":"2dbf4cb5-45fe-4559-b77f-46e77d2443e0","resolution":{"observed_at":"2026-08-02T23:59:17.174609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.04720","last_updated":"2019-05-14T13:41:42Z","snapshot_observed_at":"2026-08-14T18:52:39.404750Z","submitted_at":"2018-07-12T16:56:50Z","title":"A Large-Scale Study on Regularization and Normalization in GANs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.04720","snapshot_observed_at":"2026-08-02T23:59:14.697410Z","title":"The gan landscape: Losses, architectures, regularization, and normalization.arXiv preprint arXiv:1807.04720,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:14.697410Z"},"links":{"cited_paper":"/paper/1807.04720","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:f8af96da87e64e1a026ccbf00fc9f995bb8420577601cf48facbad57205e7256","observation_id":"58864310-b306-4983-b100-3a323443aa4b","resolution":{"observed_at":"2026-08-02T23:59:14.697410Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.22699","last_updated":"2026-07-06T06:19:03Z","snapshot_observed_at":"2026-08-13T02:23:40.621810Z","submitted_at":"2025-11-27T18:52:07Z","title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.22699","snapshot_observed_at":"2026-08-02T23:59:13.166878Z","title":"Z-image: An efficient image generation foundation model with single-stream diffusion transformer.arXiv preprint arXiv:2511.22699,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:13.166878Z"},"links":{"cited_paper":"/paper/2511.22699","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:e54e67daba83e28645644fdd720faf07b5a9adc8009c4d9a2452f4a6cf7cfdac","observation_id":"fd15ab86-c4cc-4ca0-a4f3-28920028d1b0","resolution":{"observed_at":"2026-08-02T23:59:13.166878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13301","last_updated":"2024-01-04T19:11:25Z","snapshot_observed_at":"2026-08-09T16:20:23.732146Z","submitted_at":"2023-05-22T17:57:41Z","title":"Training Diffusion Models with Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13301","snapshot_observed_at":"2026-08-02T23:59:13.011493Z","title":"Training diffusion models with reinforcement learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:13.011493Z"},"links":{"cited_paper":"/paper/2305.13301","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:4a7a9c5cea27ddf61690a5e0673c66ad9fe6f1594010f383e0ecfed50c8dfa66","observation_id":"fe582972-1d29-471a-a6a1-684d1920a535","resolution":{"observed_at":"2026-08-02T23:59:13.011493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.17400","last_updated":"2024-06-21T16:45:11Z","snapshot_observed_at":"2026-08-06T10:08:54.816113Z","submitted_at":"2023-09-29T17:01:02Z","title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.17400","snapshot_observed_at":"2026-08-02T23:59:13.557517Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-02T23:59:13.557517Z"},"links":{"cited_paper":"/paper/2309.17400","citing_paper":"/paper/2602.12155"},"observation_digest":"sha256:017689f578640b27af02a71974a180e7c7ed4dd81041302127741187251d186b","observation_id":"ce9abb3d-6204-471d-97b7-4969ea6631f0","resolution":{"observed_at":"2026-08-02T23:59:13.557517Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2602.12155","last_updated":"2026-06-29T06:08:55Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T16:33:50.814086Z","submitted_at":"2026-02-12T16:36:33Z","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":36,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":37},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 3 inbound Pith citation observations for arXiv:2602.12155."}