{"as_of":"2026-08-10T03:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:95f61ae313afb1413ad6129c2845a9fa0235a9a5a3657cb3c2a41755b3d2e235","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T10:55:38.472962Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2502.02867/citation-record","integrity":"/paper/2502.02867/integrity","json":"/paper/2502.02867/citation-record.json","paper":"/paper/2502.02867"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.132808Z","title":null,"venue":null,"work_id":"70a96d4d-30e8-41f5-8c8c-26a6f3a7341c","year":2025},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.248676Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:7a7279f832e5c6ae957259f2402d2ca21a818d6bc5d86a62e8754469bd3de4db","observation_id":"3a24a114-a932-443d-8b88-8db50f47517f","resolution":{"observed_at":"2026-08-09T10:55:39.137422Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:38.966119Z","title":"𝒕: 1.56Frame Label: 0.64Sequence Label: 0.88Estimatedreward 𝑹","venue":null,"work_id":"88e9ab2c-3281-4a9c-9e2e-dae8ccf4b098","year":2025},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.467796Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:72b28a81177fd227dd4b218f19df45e7baf5cff3f518ef46ef84f99ffe527860","observation_id":"f4c4f418-f29f-4574-94f2-e6725eeb55ba","resolution":{"observed_at":"2026-08-09T10:55:38.971488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:38.984448Z","title":"𝒕: 1.45FrameLabel: 0.76Sequence Label: 1.00Estimatedreward 𝑹","venue":null,"work_id":"a10a3513-efb3-424b-9973-84fe8829b989","year":2025},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.458542Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:b78fec0b2f7ec6639b104b1e4f0c4f6ebcc6c54d4f18c89cc8b55d175b9f4968","observation_id":"e59fe372-292d-4566-bd12-35a7dd819590","resolution":{"observed_at":"2026-08-09T10:55:38.990125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:38.949726Z","title":null,"venue":null,"work_id":"470059ba-541b-4625-a0b0-3b8725097fd0","year":2025},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.472962Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:f5b7b5c21eabc8c1846ce83dd259131fec6f4fd8d2446a7b263872412271f3f1","observation_id":"d322f51c-278a-4a27-93b3-26bc0a3adcc3","resolution":{"observed_at":"2026-08-09T10:55:38.954970Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.315985Z","title":"Generative adversarial nets","venue":null,"work_id":"e7bfdd9b-fc19-4c67-a05e-7fc7ef192598","year":2025},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.835138Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:702fd1604fa027c259bf9c0d911d8a447bcee0aaba8a8afc8db1adc90e93a668","observation_id":"c9778d1a-d640-47fd-a99f-7063848bc95c","resolution":{"observed_at":"2026-08-09T10:55:39.320644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.300097Z","title":"Robust imitation learning for mobile manipulator focusing on task-related viewpoints and regions","venue":null,"work_id":"7e1bc5c6-2728-464e-9368-efd7d5dd9400","year":2024},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.845395Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:27f547ee5610dcc739c372e5e13d8642e1c0dd570a81913858efdde608e42051","observation_id":"202370b2-8314-4a4e-ab8c-2b964cbdb42a","resolution":{"observed_at":"2026-08-09T10:55:39.305243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.284685Z","title":"Adversar- ial imitation learning from video using a state observer","venue":null,"work_id":"4d1e0d22-f149-43cf-9608-5bdb8ad209d0","year":2022},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.851588Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:605368c6b0b41a398d2aad7c359277adebd9d5f0ce28d4b6973ab1fe09be87a9","observation_id":"5ab52842-d584-4a78-9060-80e788f0ebbf","resolution":{"observed_at":"2026-08-09T10:55:39.289768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.05274","last_updated":"2020-02-28T16:02:59Z","snapshot_observed_at":"2026-08-09T14:57:36.265847Z","submitted_at":"2019-06-12T17:57:02Z","title":"Efficient Exploration via State Marginal Matching","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.05274","snapshot_observed_at":"2026-08-09T10:55:37.856871Z","title":"Efficient exploration via state marginal matching","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.856871Z"},"links":{"cited_paper":"/paper/1906.05274","citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:1a7bd6dbf33d75990a264cb169cd5f1ffadb15eae87adc32d8eef021e21e3e2c","observation_id":"ec6414f9-18e5-4a30-ab6c-1c4715e65e0c","resolution":{"observed_at":"2026-08-09T10:55:37.856871Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.01129","last_updated":"2019-05-23T11:24:12Z","snapshot_observed_at":"2026-07-06T06:26:25.585190Z","submitted_at":"2018-03-03T09:17:42Z","title":"OIL: Observational Imitation Learning","version":3},"cited_work":{"arxiv_id":"1803.01129","doi":null,"metadata_source":"pith","pith_arxiv_id":"1803.01129","snapshot_observed_at":"2026-08-09T10:55:38.785726Z","title":"OIL: Observational Imitation Learning","venue":"cs.CV","work_id":"a0e8714b-4305-4d56-bb26-e6c0724dabd3","year":2018},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.862501Z"},"links":{"cited_paper":"/paper/1803.01129","citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:8bba7ac3ddd2f8cd7a2749576c3ec472613e2f50537c069796dbd43eea0ad2ad","observation_id":"7e1b6740-1473-4a41-b064-10f8f9ce865e","resolution":{"observed_at":"2026-08-09T10:55:38.791011Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.268761Z","title":"Imitation from observation: Learning to imitate behaviors from raw video via context translation","venue":null,"work_id":"40c17095-b0ae-4e76-b2b8-e43a0755c0df","year":2018},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.893774Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:069a55dcffa126a1ea6ec895900b7633d6824653689c34e1b63710821bcc524a","observation_id":"4475f500-9ef6-4b71-9e48-ee6ca17c8bae","resolution":{"observed_at":"2026-08-09T10:55:39.274183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.251812Z","title":"Versatile offline imitation from observations and examples via reg- ularized state-occupancy matching","venue":null,"work_id":"3b607023-25d1-4bc3-bb35-72853564f297","year":2025},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.921684Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:21495f87186b1955a371be33630201307e0d8cb32f86027aded0c65ecfc639ba","observation_id":"01a14776-0bff-4e56-aba0-c08e6f5247e0","resolution":{"observed_at":"2026-08-09T10:55:39.257936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.233405Z","title":"Time-contrastive networks: Self-supervised learning from video","venue":null,"work_id":"055cf1df-6f9c-491a-a241-0c56b28e9ffd","year":2018},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.999170Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:617944b874e15093f061f5768c1c9b29a91985ffa53482fa0be6c38924d5b246","observation_id":"e50dc8c1-9932-483c-9f3d-cfa7102dc244","resolution":{"observed_at":"2026-08-09T10:55:39.239554Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1801.00690","last_updated":"2018-01-02T15:48:14Z","snapshot_observed_at":"2026-08-01T20:24:08.300098Z","submitted_at":"2018-01-02T15:48:14Z","title":"DeepMind Control Suite","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.00690","snapshot_observed_at":"2026-08-09T10:55:38.102479Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.102479Z"},"links":{"cited_paper":"/paper/1801.00690","citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:1129c0bcfc5e18b1cafaa6ec30773f1681701fe5b19163be722254c0f3313fa1","observation_id":"ff320b2a-65dc-42d1-90f9-2fc5efa76819","resolution":{"observed_at":"2026-08-09T10:55:38.102479Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.200273Z","title":"Mujoco: A physics engine for model-based control","venue":null,"work_id":"f78d95d6-2d47-4304-a72b-d00a7aa754ad","year":2012},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.108619Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:a856de4c3206644f1d66c331c658cd34d016d1114d394d54d789b17817686929","observation_id":"03101c55-f781-429a-b10e-0f3937d0e1dd","resolution":{"observed_at":"2026-08-09T10:55:39.205489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.183768Z","title":"Decomposing the generalization gap in imitation learning for visual robotic manipulation","venue":null,"work_id":"84658c37-81bb-4883-8acc-d99e3a84b4c4","year":2024},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.118726Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:27b95f6a9fad53734896863ce891bd30e3cf2263c2f4ebb92b0e87532f940509","observation_id":"81670c9f-8dbb-455d-b277-009fe037e494","resolution":{"observed_at":"2026-08-09T10:55:39.189152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1505.00853","last_updated":"2015-11-27T06:58:14Z","snapshot_observed_at":"2026-07-06T04:16:54.272660Z","submitted_at":"2015-05-05T01:16:39Z","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1505.00853","snapshot_observed_at":"2026-08-09T10:55:38.123852Z","title":"Empirical evaluation of rectified activations in con- volutional network","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.123852Z"},"links":{"cited_paper":"/paper/1505.00853","citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:5c0e69f82c553c516079c5bc06921f65fc285ec4c0dd706910eb683a0bf06c0e","observation_id":"67b7cf3b-133e-449a-84af-d7653cf8dbec","resolution":{"observed_at":"2026-08-09T10:55:38.123852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.166985Z","title":"Cross domain robot imitation with invariant representa- tion","venue":null,"work_id":"11d86e59-ee6b-4e42-b61c-71e379d132ec","year":2022},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.184844Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:db83f92b86d326c9b515fdd456257e2b7a59ad2e9c28f191119518331e11b437","observation_id":"db99e2f7-4fd5-41ec-b703-e3b107343f22","resolution":{"observed_at":"2026-08-09T10:55:39.172328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.117478Z","title":"The GP term enforces Lipschitz continuity on the discriminator, stabilizing adversarial training by mitigating extreme gradients and promoting smooth convergence","venue":null,"work_id":"a5aa1fcc-0209-4998-b83f-569d1d3fab8c","year":2018},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.254119Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:ce113bc316db68e5552e7bb729af63fdd7de9d4435dbf992ebe4e10099ef512a","observation_id":"34b83334-f33d-4eed-8a8d-27afa5192dc0","resolution":{"observed_at":"2026-08-09T10:55:39.122646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.101726Z","title":"The final output is flattened and passed through a dense layer with 32 units","venue":null,"work_id":"1fd9257f-489e-4861-b8c9-050e33bb3e9b","year":2025},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.259428Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:35460c7f93c831a25424ba827fb6a7c7410469e27b490b364fbab15e845ed412","observation_id":"ee39446a-2ee7-4e16-add7-5a2fee00d4a6","resolution":{"observed_at":"2026-08-09T10:55:39.106785Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.086303Z","title":"Architectural specifications of the proposed networks","venue":null,"work_id":"1c3894f3-da29-4e09-a9ec-6a0648029f92","year":2025},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.265089Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:e1d6dbf9dc73542aae2b8e5eb19e0680d62ca2a8b5d150345fbd58eff42c6c99","observation_id":"7cc48a56-23c3-4fe3-8657-6e9300653500","resolution":{"observed_at":"2026-08-09T10:55:39.091379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.070883Z","title":"For BSR and BT R, random policies are used for data collection","venue":null,"work_id":"1f63f847-c06d-4bc9-ba35-027b2cfa4ece","year":2021},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.270779Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:43d67b641c68ce887f83cea942037b83cac39f9c430cae980b8b30a8ba600824","observation_id":"41a30f3c-d8bd-4310-a2b6-da2c6bdeb80d","resolution":{"observed_at":"2026-08-09T10:55:39.076058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.018671Z","title":"It uses an encoder to extract domain-independent features, a domain discriminator to differentiate domains, and a label discriminator to classify expert and non-expert behaviors","venue":null,"work_id":"d25c65e4-cfdc-4462-bf3a-7b1ef63d6284","year":2016},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.435973Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:61cfa7daee95cfebf2443c348316f7915c08526beed0682269656435f6a81dc1","observation_id":"9d7c6b69-3794-4740-9d07-e011ec20bd2a","resolution":{"observed_at":"2026-08-09T10:55:39.024984Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.001734Z","title":"A discriminator generates rewards by distinguishing between expert and learner behaviors","venue":null,"work_id":"cf04a6b8-1970-41dd-a03f-8293fe9546db","year":2018},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.442343Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:fc94359fe0871a11130b385735eb90f66e2e31925380e7b8a9578b9f6464a30d","observation_id":"7a9ee9c8-582c-4d88-837e-cc5cea4b59ab","resolution":{"observed_at":"2026-08-09T10:55:39.007362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.038587Z","title":"Image resolution for each task was configured to the minimum level required for clear agent distinction, optimizing memory usage while maintaining sufficient visual detail","venue":null,"work_id":"4d725962-99a3-47ef-b28c-6271fe893310","year":2025},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":200,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.396025Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:8df034d1892b89e4d867276e3ff811e5a3baf9e2105be21f0f464aa08abc9ba9","observation_id":"477c83dc-4873-4558-8693-a778bd50f82c","resolution":{"observed_at":"2026-08-09T10:55:39.044194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.055958Z","title":"The target position is defined in polar coordinates, with r ∈ 0.15, 0.2 and 16 Submission and Formatting Instructions for ICML 2025 φ ∈ 0, π/4, π/2,","venue":null,"work_id":"9da9642d-bc36-459b-9534-6b614a2dc72d","year":2025},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":1000,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.338722Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:6f88a4f800840f76bbe9e777ebcb03a6c8ae81a67717b6a4f779e4bce2e93c60","observation_id":"e461422e-31c4-489f-8a0f-90f3e70c0734","resolution":{"observed_at":"2026-08-09T10:55:39.060840Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.00821","last_updated":"2020-08-25T02:41:11Z","snapshot_observed_at":"2026-08-04T12:42:55.627023Z","submitted_at":"2018-10-01T17:02:24Z","title":"Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.00821","snapshot_observed_at":"2026-08-09T10:55:37.957364Z","title":"ISBN 1558607072","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2000,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.957364Z"},"links":{"cited_paper":"/paper/1810.00821","citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:c6a57764ed2262f18baefb5345b8becc3d75372df342cfc5f04057589676e8f6","observation_id":"9ce42051-1963-468f-9596-f5c711a3fdb5","resolution":{"observed_at":"2026-08-09T10:55:37.957364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.366210Z","title":"Environmental and behavioral imitation for autonomous navigation","venue":null,"work_id":"3fc0e381-b422-4d4d-9557-ef210bd7d13e","year":2024},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2004,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.792651Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:a51c3e1941cc1de9f0123e17892495cc82cd9915284c323dabaeb406f0b40a24","observation_id":"b2d321c7-10ef-4f14-b2fc-7431a7c04537","resolution":{"observed_at":"2026-08-09T10:55:39.371959Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.05079","last_updated":"2021-03-08T21:18:58Z","snapshot_observed_at":"2026-07-06T10:48:00.988941Z","submitted_at":"2021-03-08T21:18:58Z","title":"Domain-Robust Visual Imitation Learning with Mutual Information Constraints","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.05079","snapshot_observed_at":"2026-08-09T10:55:37.798040Z","title":"and Celiktutan, O","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2006,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.798040Z"},"links":{"cited_paper":"/paper/2103.05079","citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:ef9397f9025da206862d70b764d8aa24314500ca477695db901a03dc1e742d1f","observation_id":"5dea54dc-c55b-4dad-89d3-cb2fa736ae0c","resolution":{"observed_at":"2026-08-09T10:55:37.798040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.148595Z","title":"12 Submission and Formatting Instructions for ICML 2025 A","venue":null,"work_id":"429b6da2-8bf7-4719-8da2-1a899c093288","year":2025},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2008,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.242226Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:c493b747f2d61ca19314aa5a6c9742ae97e8b7e467fec99f6e0dc5f73231703b","observation_id":"2dad6298-11c5-4a24-8df2-34d6fd2c3572","resolution":{"observed_at":"2026-08-09T10:55:39.153783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1807.06158","last_updated":"2019-06-18T04:56:56Z","snapshot_observed_at":"2026-07-06T06:50:35.226504Z","submitted_at":"2018-07-17T00:25:15Z","title":"Generative Adversarial Imitation from Observation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.06158","snapshot_observed_at":"2026-08-09T10:55:38.113522Z","title":"Behavioral cloning from observation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.113522Z"},"links":{"cited_paper":"/paper/1807.06158","citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:81775bc87f0d8f957c16b6bd0d24e73d7345986a8fe045d3c19217e478ed84d3","observation_id":"857a91ba-fd97-44fe-9786-98e056fd9252","resolution":{"observed_at":"2026-08-09T10:55:38.113522Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.05905","last_updated":"2019-01-29T12:10:47Z","snapshot_observed_at":"2026-08-01T15:24:35.515954Z","submitted_at":"2018-12-13T04:44:29Z","title":"Soft Actor-Critic Algorithms and Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.05905","snapshot_observed_at":"2026-08-09T10:55:37.839943Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.839943Z"},"links":{"cited_paper":"/paper/1812.05905","citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:3879bef1a6f7f87448301f604159ccf5facbdec173543bb85526aa2ee85666b2","observation_id":"fc12cce3-df75-4948-a326-fdc09623b56c","resolution":{"observed_at":"2026-08-09T10:55:37.839943Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.01331","last_updated":"2024-06-09T18:43:27Z","snapshot_observed_at":"2026-07-06T16:42:16.200015Z","submitted_at":"2023-11-02T15:41:57Z","title":"Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching","version":3},"cited_work":{"arxiv_id":"2311.01331","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.01331","snapshot_observed_at":"2026-08-09T10:55:38.512611Z","title":"Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching","venue":"cs.LG","work_id":"0a769cc7-21cb-463b-9e1d-6deb2c7e29c5","year":2023},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.129671Z"},"links":{"cited_paper":"/paper/2311.01331","citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:649b08b12cfa6da2328b190cbeaff65272fd6856fd7f793576f5cf0f5c16c5b1","observation_id":"b261aca9-70db-445b-85dc-74fe6a2d4383","resolution":{"observed_at":"2026-08-09T10:55:38.583360Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.330874Z","title":"Learning robust rewards with adverserial inverse reinforcement learning","venue":null,"work_id":"8a1bd18c-bf1f-44f7-98b2-7d6c79e8f128","year":2018},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.824433Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:48f4e35a061659b98e3ea09712c5d9d5373be4766c4439e5d3cd2f5446f54141","observation_id":"89bd068f-0d54-4838-8cc2-3d16ee3965e0","resolution":{"observed_at":"2026-08-09T10:55:39.336641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.11446","last_updated":"2022-04-25T05:36:54Z","snapshot_observed_at":"2026-07-06T13:03:22.436518Z","submitted_at":"2022-04-25T05:36:54Z","title":"Imitation Learning from Observations under Transition Model Disparity","version":1},"cited_work":{"arxiv_id":"2204.11446","doi":null,"metadata_source":"pith","pith_arxiv_id":"2204.11446","snapshot_observed_at":"2026-08-09T10:55:38.847812Z","title":"Imitation Learning from Observations under Transition Model Disparity","venue":"cs.LG","work_id":"911e2591-6af8-4e20-9f1f-ec22c6bf30d2","year":2022},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.829463Z"},"links":{"cited_paper":"/paper/2204.11446","citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:985961c9b708eddf7c2606cbc12ba60eb6c67b6aa95d8476e6c872bb8891e0aa","observation_id":"23c6bf2d-f2ac-4ee4-9058-f775440287d5","resolution":{"observed_at":"2026-08-09T10:55:38.854222Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.216153Z","title":"An integrated frame- work for human–robot collaborative manipulation","venue":null,"work_id":"31528c0c-f563-4ff1-99db-ded19d700a63","year":null},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:38.038274Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:b3e6657a1aca040d3b9f341f0320c9edbb6f947bd00fec8c26513af2d6d0de10","observation_id":"fb33711e-681b-448f-85d1-4f7cd149ccda","resolution":{"observed_at":"2026-08-09T10:55:39.221649Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T10:55:39.348346Z","title":"Model-based inverse reinforcement learning from visual demonstrations","venue":null,"work_id":"3f00f712-5d6c-46f9-9338-8f7b1a2fb27c","year":1930},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.813978Z"},"links":{"citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:3b5db707bdde88f3cb29e772a8ff0b8ea89d249fb02c0719a19fc90f4c077bc3","observation_id":"04589481-37e4-4009-9bfa-d06f1d1ea5db","resolution":{"observed_at":"2026-08-09T10:55:39.353869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.09251","last_updated":"2022-05-19T00:05:03Z","snapshot_observed_at":"2026-08-09T13:57:06.631130Z","submitted_at":"2022-05-19T00:05:03Z","title":"IL-flOw: Imitation Learning from Observation using Normalizing Flows","version":1},"cited_work":{"arxiv_id":"2205.09251","doi":null,"metadata_source":"pith","pith_arxiv_id":"2205.09251","snapshot_observed_at":"2026-08-09T10:55:38.912111Z","title":"IL-flOw: Imitation Learning from Observation using Normalizing Flows","venue":"cs.LG","work_id":"54d4f6f3-2779-4e9c-bcb0-323e529ea5cc","year":2022},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.803472Z"},"links":{"cited_paper":"/paper/2205.09251","citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:6f953d16978d2dcdf95db347f4495f05915b687dfa2168794ac5a7c0388da323","observation_id":"4a6a595b-25fb-4284-8378-f638c9bb7170","resolution":{"observed_at":"2026-08-09T10:55:38.917953Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.11248","last_updated":"2018-08-13T18:33:24Z","snapshot_observed_at":"2026-07-06T06:06:54.331476Z","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":"2026-08-09T10:55:37.819018Z","title":"Learning robust rewards with adversarial inverse reinforcement learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.819018Z"},"links":{"cited_paper":"/paper/1710.11248","citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:94d0b8ca34b476a6f5c6ad88d7556903c5231b8b45f37ff2c0dde6ac723f5edc","observation_id":"ea50033a-16b0-48f0-835d-25bd18a7b0ef","resolution":{"observed_at":"2026-08-09T10:55:37.819018Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.04678","last_updated":"2021-03-17T11:43:36Z","snapshot_observed_at":"2026-07-06T09:27:00.982430Z","submitted_at":"2020-06-08T15:30:11Z","title":"Primal Wasserstein Imitation Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.04678","snapshot_observed_at":"2026-08-09T10:55:37.808745Z","title":"Primal wasserstein imitation learning","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-09T10:55:37.808745Z"},"links":{"cited_paper":"/paper/2006.04678","citing_paper":"/paper/2502.02867"},"observation_digest":"sha256:93c23f3c8f89b973a92ab45d0474f3c1f61d5e1e3ae7b232595c92c398f7f59c","observation_id":"1cce4019-838e-4a4a-9157-2a1dc681cd9f","resolution":{"observed_at":"2026-08-09T10:55:37.808745Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.02867","last_updated":"2025-02-14T11:57:25Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T14:58:06.206298Z","submitted_at":"2025-02-05T03:52:36Z","title":"Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observations"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":11,"verified_exact":3,"verified_fuzzy":24},"total_outbound_references":39},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2502.02867."}