{"as_of":"2026-08-07T12:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:361682be33566abceca079ad262b2494b02d67dc26df967e0541f6d3c4f61d2a","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-21T07:18:57.039115Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2605.20385/citation-record","integrity":"/paper/2605.20385/integrity","json":"/paper/2605.20385/citation-record.json","paper":"/paper/2605.20385"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fully convolutional networks for semantic segmentation","venue":null,"work_id":"89f416fd-f7e3-4f12-9f7f-71a1154710fd","year":2015},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:0d320c7bed2c1e8f677c338b619f6a95578088988483afb40238be689356aeb8","observation_id":"016beb94-be7c-4fcf-96f1-3e825cddca78","resolution":{"observed_at":"2026-05-21T07:19:47.209508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Encoder- decoder with atrous separable convolution for semantic image segmentation","venue":null,"work_id":"8ecbf0bc-d299-49c6-8de5-8f14967c95da","year":2018},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:0381f2a8970da17453531f3be741ef2e9aa3858bbca0a092dccde63e54289256","observation_id":"dc237dfc-b4f6-44e2-8d09-f76b8b3d03bf","resolution":{"observed_at":"2026-05-21T07:19:47.198968Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Segformer: Simple and efficient design for semantic segmentation with transformers","venue":null,"work_id":"86d099d5-f7ba-4088-8530-558fa9e7e89a","year":2021},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:c82cfbdbea4582202b2ad4f0373e99f89e563c71ea22d27b0007a0ecc8835dc9","observation_id":"b6f0ebf8-b783-47ef-a59e-15251082cb43","resolution":{"observed_at":"2026-05-21T07:19:47.206702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Schwing, Alexander Kirillov, and Rohit Girdhar","venue":null,"work_id":"c63b50cd-2ef4-4e1b-b0a3-c3e004e40b19","year":2022},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:7e69f0b28d9506c1e8cf1bd88c1f29dcccb295847bb32bd130151779cdfad86f","observation_id":"a813c43d-5b8c-46a9-b893-ca218e5e71de","resolution":{"observed_at":"2026-05-21T07:19:47.203843Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-07-10T03:06:43.908517Z","title":"Segment anything","venue":null,"work_id":"ffd866b4-b8b4-4924-887d-af662dde5bdc","year":2023},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:64171c3ac6a42c083007c9e897b3a0b9a5203f8276dae62e59451930f37a7713","observation_id":"5d5faa3c-5408-495d-b745-e0ccdf566f7f","resolution":{"observed_at":"2026-05-21T07:19:47.201402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Sam 3: Segment anything with concepts","venue":null,"work_id":"7aa9edef-dcca-4a82-92df-18b1880bf527","year":2026},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:b4649d1b3fbe22b77d42ce690d1638a331507f8205996b5300d0e0c3d84082e3","observation_id":"681d364a-037e-48f3-8ad0-7dc5c6c0f97b","resolution":{"observed_at":"2026-05-21T07:19:47.196580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Context-independent and context-dependent information in concepts","venue":null,"work_id":"6f4100a5-b7de-432e-949e-012320629f7b","year":1982},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:bd0ab5fb1591396fa6ffeff69acf3e708967dc98d93ada8467586762f5aa841f","observation_id":"a42c3810-6598-4281-921b-75be663bff65","resolution":{"observed_at":"2026-05-21T07:19:47.264282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Neural correlates of context- independent and context-dependent self-knowledge.Brainand Cognition, 125:23–31","venue":null,"work_id":"729a7418-c90c-451f-977f-747126ce9640","year":2018},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:dbc2934c9f2212c298159059c65e9a222d6936a6a8c9304f1c6d5efabb8c3f40","observation_id":"fd648b85-63c4-4967-84ce-35355501672c","resolution":{"observed_at":"2026-05-21T07:19:47.258896Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Individual pattern representations are context indepen- dent,buttheircollectiverepresentationiscontextdependent","venue":null,"work_id":"d89c8bc6-c404-499e-ba8d-c349c4b26a9d","year":2005},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:916897b9da6c923bb0c842186644fb3b064a09cfd18d127b4bce12a8212983ff","observation_id":"4a557098-9187-4128-bef4-15ecda629317","resolution":{"observed_at":"2026-05-21T07:19:47.261388Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Spider: a unified framework for context-dependent concept segmentation","venue":null,"work_id":"cf24bb8c-ff94-4683-a742-a1a69068292b","year":2024},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:049a861cc35cfdce5ea26c139def94cde52195698326cf3cedd50391445f452e","observation_id":"6ce66e71-9f69-4ac8-a53b-b5b3945c78ed","resolution":{"observed_at":"2026-05-21T07:19:47.254043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.01240","last_updated":"2025-08-26T08:58:35Z","snapshot_observed_at":"2026-07-06T20:00:00.800207Z","submitted_at":"2024-12-02T08:03:56Z","title":"Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes","version":3},"cited_work":{"arxiv_id":"2412.01240","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.01240","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"a7f26afe-80c5-4db8-a26a-958d4712a300","year":2024},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"cited_paper":"/paper/2412.01240","citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:42882646e308c4a2c865ec5e587fe11eebf7f6f1e49b773e7a814152a6e8526d","observation_id":"32e69853-526c-4581-812f-12ab69c9fc59","resolution":{"observed_at":"2026-05-21T07:19:46.756427Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Seggpt: Towards segmenting everything in context","venue":null,"work_id":"47e40cc1-8c38-4cde-8377-23a76a17b14c","year":2023},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:91d0ba6ca61d2286a1b8d6d502930c07385b3184ff7840930d9b8e49aff70011","observation_id":"3f21e113-da23-4823-a857-9e69c9901771","resolution":{"observed_at":"2026-05-21T07:19:47.249273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Sam3-i: Segment anything with instructions","venue":null,"work_id":"0c8167ab-59fb-4d82-9701-5ed94b0bc9e9","year":2026},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:1c4f810ad98462ee2011469d264e6d7b8b5e72590c5da6dcc68e94c343d86da8","observation_id":"4cb3d230-b28c-4dea-a997-c00181bce85e","resolution":{"observed_at":"2026-05-21T07:19:47.246903Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.07916","last_updated":"2026-08-04T13:16:24Z","snapshot_observed_at":"2026-08-07T11:21:20.034879Z","submitted_at":"2026-04-09T07:37:09Z","title":"Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation","version":2},"cited_work":{"arxiv_id":"2604.07916","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.07916","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation","venue":"cs.CV","work_id":"9c946de7-e37e-44a8-9a27-b7c161c81e4a","year":2026},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"cited_paper":"/paper/2604.07916","citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:c5e6a37984ee81f2f250d696461436445178df1eaa1accae23f0c71defda4e35","observation_id":"0a441029-53a9-470a-a482-5172f9d449cd","resolution":{"observed_at":"2026-05-21T07:19:46.767662Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.06520","last_updated":"2026-05-31T09:29:40Z","snapshot_observed_at":"2026-08-05T01:42:30.194131Z","submitted_at":"2025-03-09T08:48:51Z","title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","version":3},"cited_work":{"arxiv_id":"2503.06520","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.06520","snapshot_observed_at":"2026-07-04T19:30:08.050016Z","title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","venue":"cs.CV","work_id":"7a33b2a4-8409-4a00-ad7b-84e810df1ba7","year":2025},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"cited_paper":"/paper/2503.06520","citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:32776ad4ce8d2a3abfe4b059ccca9e0e91e7f74cf60de7e0fe956fbdb87b1a45","observation_id":"f48b71ec-24d0-40ff-a141-c3dbc2822433","resolution":{"observed_at":"2026-05-21T07:19:46.749161Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Lens: Learning to segment anything with unified reinforced reasoning","venue":null,"work_id":"4a5fc2d4-3e65-4279-8104-c899985559ba","year":2026},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:554593ac569448c357001da32addeb92c2c351887d007f22ac70e9e4490592f6","observation_id":"fcd04b4a-bd1c-46b1-917f-df15ada8f55a","resolution":{"observed_at":"2026-05-21T07:19:47.244495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-07-10T03:06:43.966629Z","title":"Lisa: Reasoning segmentation via large language model","venue":null,"work_id":"65ea6a8f-17d6-47e9-b126-0d1ea82dd36d","year":2024},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:2b7b5e28f3f99351cffa68af66a7b45024cbed44362ad32ce88764574b06062a","observation_id":"248c9c68-f915-4973-a3f7-6ec4d10010ee","resolution":{"observed_at":"2026-05-21T07:19:47.232047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Instructseg: Unifying instructed visual segmentation with multi-modal large language models","venue":null,"work_id":"f0c7b5db-e592-42cb-b527-994952441660","year":2025},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:7efd9408b5310bf28a1d392025ff5359dcc05e59be31cf367d0ac8eae4660b94","observation_id":"25f8be5c-a041-43f6-b5e8-edd848ae06be","resolution":{"observed_at":"2026-05-21T07:19:47.219862Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Segagent: Exploring pixel understanding capabilities in mllms by imitating human annotator trajectories","venue":null,"work_id":"1578f35e-3748-4738-8b21-742fe07803ea","year":2025},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:8c2135d0630ca69103601f22678fa0752b9282ccfafb98167ea189f98ef76b2b","observation_id":"ff9e118b-7d95-4e5d-859a-eba17704bbba","resolution":{"observed_at":"2026-05-21T07:19:47.279866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2602.03320","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Medsam-agent: Empowering interactive medical image segmenta- tion with multi-turn agentic reinforcement learning.arXivpreprint","venue":null,"work_id":"660f5ee6-1c05-4918-8712-f5a97e182381","year":2026},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:aff5842a15bba07e8b4386ef0b2556cbc9ade57d89dcffc89230e76022d5004b","observation_id":"f49e25ea-93b2-4eb9-8d83-957be0c3fce5","resolution":{"observed_at":"2026-05-21T07:19:46.760217Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.22624","last_updated":"2025-06-27T20:40:45Z","snapshot_observed_at":"2026-08-07T10:58:15.548547Z","submitted_at":"2025-06-27T20:40:45Z","title":"Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2506.22624","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.22624","snapshot_observed_at":"2026-07-04T15:09:55.141278Z","title":"Seg-r1: Segmentation can be surprisingly simple with reinforcement 33 ConceptSeg-R1 learning","venue":null,"work_id":"19db66be-f721-4ce8-8a0e-51fd1e4046ba","year":2025},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"cited_paper":"/paper/2506.22624","citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:7f37317b65549a7436fa6507fbbee12789a61444edf4549476aa8662d9501f64","observation_id":"0beefd03-c983-4d47-8f8b-3d16e5353938","resolution":{"observed_at":"2026-05-21T07:19:46.744672Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"The cityscapes dataset for semantic urban scene understanding","venue":null,"work_id":"602629c1-297c-4bdb-bb40-d3651fe70e19","year":2016},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:45b7f7e1c7e52b0800e3abea37927802dea3ec5f72b4c7e8a4458aef2a67ca8d","observation_id":"e78bb7de-31f8-4067-8789-b6d9ac4a7165","resolution":{"observed_at":"2026-05-21T07:19:47.251781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2603.23489","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T22:13:59.625281Z","title":"Agentrvos: Reasoning over object tracks for zero-shot referring video object segmentation","venue":null,"work_id":"ce43c3a8-6a82-4965-bfba-c61237290d5e","year":2026},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:c73772eb3a1df96933ceca89e23bae1ed4673c86f370c0a638743a2446292d24","observation_id":"6ec20c48-6019-4727-b8fa-76128796ef9e","resolution":{"observed_at":"2026-05-21T07:19:46.732612Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2601.17420","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cot-seg: Rethinking segmentation with chain-of-thought reasoning and self-correction","venue":null,"work_id":"86f0b891-7e89-4b4f-a8ba-87b23db0e0f1","year":2026},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:b7a1d524fe9a2fd4856cf4fa0ad27904367acf4cc1922f5acd6426960b36db1a","observation_id":"25d4e8fe-8968-4926-92e0-225a51663694","resolution":{"observed_at":"2026-05-21T07:19:46.771292Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Glamm: Pixel grounding large multimodal model","venue":null,"work_id":"ace05678-5e4f-424f-8409-96e12f20f62a","year":2024},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:a2c782d3d798b80e2eab1c7707e841ebec38b1b4e0fbc502840df5a21053207b","observation_id":"6a7dae18-e32c-4e7b-97f4-879bcb767ff2","resolution":{"observed_at":"2026-05-21T07:19:47.277418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Model-agnostic meta-learning for fast adaptation of deep networks","venue":null,"work_id":"0cec67e9-d867-4937-a975-98547e760454","year":2017},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:d51760f3b86b28aae008fb592a4575612f14b327681c24fa0a623cd50428c679","observation_id":"9f11d055-e56a-4c67-8951-6f53ec5e7c68","resolution":{"observed_at":"2026-05-21T07:19:47.269881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.02999","last_updated":"2018-10-22T16:11:14Z","snapshot_observed_at":"2026-08-05T12:53:31.632675Z","submitted_at":"2018-03-08T08:29:38Z","title":"On First-Order Meta-Learning Algorithms","version":3},"cited_work":{"arxiv_id":"1803.02999","doi":null,"metadata_source":"pith","pith_arxiv_id":"1803.02999","snapshot_observed_at":"2026-07-08T22:55:40.216179Z","title":"On First-Order Meta-Learning Algorithms","venue":"cs.LG","work_id":"cfd46fb8-7c98-41ac-8499-e11236b08f18","year":2018},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"cited_paper":"/paper/1803.02999","citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:fd556a688d36f27e1a7ec44e57bd12c301590b67796adf44ba4af4adb0f51388","observation_id":"5e9e917c-3da8-40e0-b709-866e11e5e194","resolution":{"observed_at":"2026-05-21T07:19:46.763490Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Metaicl: Learning to learn in context","venue":null,"work_id":"cb182779-3dcd-4883-8329-189a2c9dedd5","year":2022},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:c55a6aa8a71be345454f10d176721a7c37a24439c0e9df4149e18ddae38b5dc2","observation_id":"e7cbf96f-3381-453d-afbe-98a390494f4e","resolution":{"observed_at":"2026-05-21T07:19:47.256633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Maml- en-llm: Model agnostic meta-training of llms for improved in-context learning","venue":null,"work_id":"13fe2840-5e6d-4121-88e2-a9df8925653c","year":2024},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:e4761e37db7cebe356d3261c281d74e85e122d5429cd65debf2fe53e8c64142f","observation_id":"387b6cd1-8592-47fd-a4c6-f653a496d570","resolution":{"observed_at":"2026-05-21T07:19:47.214595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2402.03300","doi":"10.1016/0004-3702(73)90011-8","metadata_source":"pith","pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","venue":"cs.CL","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","year":2024},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:1dc1417bfc8c38e0c11f1e0511cdc241190ed5314c0294dcc383a4e4410a3197","observation_id":"db16f40e-0f4a-482c-9b39-2fd30c6d0499","resolution":{"observed_at":"2026-05-21T07:19:46.728406Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.06565","last_updated":"2016-07-25T17:23:29Z","snapshot_observed_at":"2026-07-06T05:00:46.434335Z","submitted_at":"2016-06-21T13:37:05Z","title":"Concrete Problems in AI Safety","version":2},"cited_work":{"arxiv_id":"1606.06565","doi":"10.48550/arxiv.1606.06565","metadata_source":"pith","pith_arxiv_id":"1606.06565","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Concrete Problems in AI Safety","venue":"cs.AI","work_id":"c8d14fbe-6eab-464a-95b3-778aabd82fa3","year":2016},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"cited_paper":"/paper/1606.06565","citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:de88bcfcbd9b40b44fd4cc88c597cbbf94a230fa5c8e7d98dc099b364be902fc","observation_id":"26248b46-9481-4eb1-a223-c105558aed0c","resolution":{"observed_at":"2026-05-21T07:19:46.752589Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-07-13T23:49:52.215761+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-13T23:49:52.215761+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13923","last_updated":"2025-02-19T18:00:14Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-19T18:00:14Z","title":"Qwen2.5-VL Technical Report","version":1},"cited_work":{"arxiv_id":"2502.13923","doi":"10.48550/arxiv.2502.13923","metadata_source":"pith","pith_arxiv_id":"2502.13923","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Qwen2.5-VL Technical Report","venue":"cs.CV","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","year":2025},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"cited_paper":"/paper/2502.13923","citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:877ab3d28213263fb40a2ff5aabef5201f87c06e3df2880fa33e84c2bd08e5e3","observation_id":"37024d76-ea68-4791-986c-4bc2e5775a57","resolution":{"observed_at":"2026-05-21T07:19:46.740489Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-07-12T05:19:13.082554+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T05:19:13.082554+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Sam4mllm: Enhance multi-modal large language model for referring expression segmentation","venue":null,"work_id":"ec7fdd7e-df3e-4c9c-8342-654ceffeaf43","year":2024},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:f99f47614ce3639c29be6dc8e8753cc02e942c848a2c26f856043e908fd92d83","observation_id":"c5ebc8f6-425f-4380-a984-197d93856230","resolution":{"observed_at":"2026-05-21T07:19:47.234403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Sam-r1: Leveraging sam for reward feedback in multimodal segmentation via reinforcement learning","venue":null,"work_id":"7ded1dee-7a87-4571-b631-798af2f7884f","year":2025},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:61e8f89466fcd18e84d845cc6bd3d785668187d049ff9c18f644adfb85acca99","observation_id":"b21e4500-1b2f-4874-b377-76c3b240c71a","resolution":{"observed_at":"2026-05-21T07:19:47.236976Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Discriminativeperceptionviaanchoreddescription for reasoning segmentation","venue":null,"work_id":"a1d804d9-51ed-4ba8-baca-a170dccddc6e","year":2026},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:80451931e8d897a80dcdf53e73d48c9ea4559ff82742f11efe15dc38be453fd9","observation_id":"0e0eada4-52d0-4aa1-aa36-550360f01bc3","resolution":{"observed_at":"2026-05-21T07:19:47.241837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Learning to detect salient objects with image-level supervision","venue":null,"work_id":"671a9e1d-22aa-487d-bda3-7213b0417a62","year":2017},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:402866e347dd51648737f2c6b5fa9efe18f1e0693d65ede0fda7bdd2752aace6","observation_id":"96ce9730-751b-429d-88e1-a56c05918629","resolution":{"observed_at":"2026-05-21T07:19:47.239484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Camou- flaged object detection","venue":null,"work_id":"bc126af0-7e96-4e52-881c-bd66c65e4529","year":2020},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:288ce9f861093c509f2d0ad52b8f4d18875d3e152aaeffb72bafae1ad3fa0158","observation_id":"f37278ed-5a75-4669-ab06-bd3b466e7451","resolution":{"observed_at":"2026-05-21T07:19:47.282354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Fss-1000: A 1000-class dataset for few-shot segmentation","venue":null,"work_id":"cf9451ff-c9d4-41bd-9595-0d42407716a1","year":2020},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:63badc65bcabe6e7011d52141009139ce7b34cf86cc17cac0db24e9891760bb4","observation_id":"235f61ee-e315-4c82-b1cc-362d32923204","resolution":{"observed_at":"2026-05-21T07:19:47.227260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Migician: Revealing the magic of free-form multi-image grounding in multimodal large language models","venue":null,"work_id":"a4dd4161-1b19-41fa-962e-ed1b603cc9c6","year":2025},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:892e4656ebd4933bede3497640761d48e5f69700bddc56d2d0266195e34f9997","observation_id":"5c6682fa-5f57-4f34-9dec-c3dbf40de67a","resolution":{"observed_at":"2026-05-21T07:19:47.222359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Re-thinking co-salient object detection.IEEE TPAMI, 44(8):4339–4354","venue":null,"work_id":"cdf18f9e-623e-475b-a3c6-355092240b8d","year":2021},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:ad400ca765d0d43cf808c8aa77eac0caaad32cfb57d2722fe9db2b88e2a1f985","observation_id":"f855c1a2-833e-4efa-83ce-482cf24ab360","resolution":{"observed_at":"2026-05-21T07:19:47.274855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"One-shot learning for semantic segmentation","venue":null,"work_id":"ba647057-eb6e-4cfe-8b8e-1c6df3d7b7df","year":2017},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:57b5aa9b977bd393308ce75abbd8638e615a185e35edd725e5899a1b5aeb7a42","observation_id":"d9c3f9ec-0a34-4b02-9c8c-eb8e91904910","resolution":{"observed_at":"2026-05-21T07:19:47.266997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Segmenting transparent objects in the wild","venue":null,"work_id":"61f527b5-9e4a-4beb-b5cc-1bbf857e2596","year":2020},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:394f78b8d0fee886fb94e41af0296ceff69ed6c0af2d1630ccad091d71e28255","observation_id":"21cf35de-e8ed-44b6-9874-bcf27bffdd79","resolution":{"observed_at":"2026-05-21T07:19:47.217153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Large-scale training of shadow detectors with noisily-annotated shadow examples","venue":null,"work_id":"c9d4a008-c76e-4c75-8738-77ec5f67ba34","year":2016},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:3d1b6bfce94a7f238fc0b7efab3e8927e8c96546a0c6aa6b9eab820e0444009e","observation_id":"865fdad6-40a6-4686-814b-7d29fcb7a62d","resolution":{"observed_at":"2026-05-21T07:19:47.272453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Autocorrelation-aware aggregation network for salient object detection of strip steel surface defects.IEEE TIM, 72:1–12","venue":null,"work_id":"8fb818a0-3d68-4d2f-8d9a-42d0cc5fe940","year":2023},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:abaa19368847171285f9472bf439427612c9e7ef75dadc2231b737af0b558f4c","observation_id":"096909bb-8c39-433e-80f1-b6dbd51b527d","resolution":{"observed_at":"2026-05-21T07:19:47.224909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Pranet: Parallel reverse attention network for polyp segmentation","venue":null,"work_id":"81e9e89f-569e-429c-bfed-e6bf739f1050","year":2020},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:2ff557ce70d67f22050b74c5e3a2687829b6d38e55b178d4e8c8225f2278da49","observation_id":"c79cf963-72b1-4ed8-945e-37c1d58e8f2a","resolution":{"observed_at":"2026-05-21T07:19:47.229603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Dataset of breast ultrasound images.Datain brief, 28:104863","venue":null,"work_id":"c6a52af6-f15a-40e9-9ab2-30ac9cfd4852","year":2020},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:9fcf24b8c59ff759170bd616b1e5399f48e046598d28a3b9e42978107026412a","observation_id":"cc982ec8-7af8-4a77-b3f4-0348a1eb15c9","resolution":{"observed_at":"2026-05-21T07:19:47.284761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.03368","last_updated":"2019-03-29T17:36:27Z","snapshot_observed_at":"2026-08-07T00:39:52.073704Z","submitted_at":"2019-02-09T04:18:10Z","title":"Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)","version":2},"cited_work":{"arxiv_id":"1902.03368","doi":"10.48550/arxiv.1902.03368","metadata_source":"pith","pith_arxiv_id":"1902.03368","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)","venue":"cs.CV","work_id":"a1680554-54cc-449f-aa92-0acb940cad0a","year":2019},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"cited_paper":"/paper/1902.03368","citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:bba5f804614b07387537e67a40e43a7255b4475dad13f09baf1041e8ca8008c0","observation_id":"6bb23771-38b1-45d0-aadb-3bd4de5f2b66","resolution":{"observed_at":"2026-05-21T07:19:46.736797Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-05T21:23:00.469572Z","title":"Decoupledweightdecayregularization","venue":null,"work_id":"31c11b11-f178-4987-88de-ca7f6a1d5515","year":2019},"citing_paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-21T07:18:57.039115Z"},"links":{"citing_paper":"/paper/2605.20385"},"observation_digest":"sha256:416ead06514cf893a48a78ddcf3d5898a48ab099e261fb494269cfbe0c70af77","observation_id":"6e02d98b-2022-4cc2-bdd6-31ae858e4c02","resolution":{"observed_at":"2026-05-21T07:19:47.211782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.20385","last_updated":"2026-05-19T18:35:38Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-01T15:35:47.309290Z","submitted_at":"2026-05-19T18:35:38Z","title":"ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":12,"verified_fuzzy":36},"total_outbound_references":48},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2605.20385."}