{"as_of":"2026-08-09T07:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e4015fdeb18ca5a08ddcc3485a326bff969bf6e2c355f814f82094fcb757de19","coverage":[{"denominator":12,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:22:03.700313Z","state":"measured"},{"denominator":12,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":12,"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/2507.08548/citation-record","integrity":"/paper/2507.08548/integrity","json":"/paper/2507.08548/citation-record.json","paper":"/paper/2507.08548"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.16268","last_updated":"2025-07-29T00:08:01Z","snapshot_observed_at":"2026-07-06T19:37:16.203681Z","submitted_at":"2024-10-21T17:59:19Z","title":"SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.16268","snapshot_observed_at":"2026-08-06T18:22:02.691583Z","title":"S am2 L ong: E nhancing S am 2 for L ong V ideo S egmentation with a T raining- F ree M emory T ree","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.08548","last_updated":"2025-07-11T12:53:19Z","snapshot_observed_at":"2026-08-09T06:05:00.155443Z","submitted_at":"2025-07-11T12:53:19Z","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-06T18:22:02.691583Z"},"links":{"cited_paper":"/paper/2410.16268","citing_paper":"/paper/2507.08548"},"observation_digest":"sha256:05c0ddd1d95e905c35d5f57ce2ff86afc9521acb2ff74a1502f6f7be2d4086fb","observation_id":"fd2630ab-d29e-4d2d-97df-4372f9e52958","resolution":{"observed_at":"2026-08-06T18:22:02.691583Z","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":"2026-08-06T18:22:04.422146Z","title":"A N ew A pproach to L inear F iltering and P rediction P roblems, 1960","venue":null,"work_id":"948ff3d6-906d-4cd0-a488-1f8e4d91be68","year":1960},"citing_paper":{"arxiv_id":"2507.08548","last_updated":"2025-07-11T12:53:19Z","snapshot_observed_at":"2026-08-09T06:05:00.155443Z","submitted_at":"2025-07-11T12:53:19Z","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-06T18:22:02.752233Z"},"links":{"citing_paper":"/paper/2507.08548"},"observation_digest":"sha256:9b01a775bb5675a80eb804273065826fc242a00e0419a5b55aa5f50b0237fc1c","observation_id":"2d2cea7a-a71c-4946-9482-a011f3dac24c","resolution":{"observed_at":"2026-08-06T18:22:04.489902Z","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":"2026-08-06T18:22:04.266585Z","title":"Segment A nything","venue":null,"work_id":"142103a8-faa2-4ee6-979e-c2ef52c35154","year":2023},"citing_paper":{"arxiv_id":"2507.08548","last_updated":"2025-07-11T12:53:19Z","snapshot_observed_at":"2026-08-09T06:05:00.155443Z","submitted_at":"2025-07-11T12:53:19Z","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-06T18:22:02.806288Z"},"links":{"citing_paper":"/paper/2507.08548"},"observation_digest":"sha256:efbed786e21be84f5ada222f2a0bfe280a0095019e432b8774be864ff78a7ca6","observation_id":"2650f388-cd36-44bd-837f-77246884e793","resolution":{"observed_at":"2026-08-06T18:22:04.343236Z","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":"2026-08-06T18:22:04.070395Z","title":"The F irst V isual O bject T racking S egmentation VOTS2023 C hallenge R esults","venue":null,"work_id":"0f40bfdb-1c58-42b7-ae80-765fe8c786c9","year":2023},"citing_paper":{"arxiv_id":"2507.08548","last_updated":"2025-07-11T12:53:19Z","snapshot_observed_at":"2026-08-09T06:05:00.155443Z","submitted_at":"2025-07-11T12:53:19Z","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-06T18:22:02.893633Z"},"links":{"citing_paper":"/paper/2507.08548"},"observation_digest":"sha256:3bf44d44db03e7ffffb370617cc1668866503c800fefac8381aece739ab00c20","observation_id":"95cac272-353f-45a9-9e95-5a781ca7dd87","resolution":{"observed_at":"2026-08-06T18:22:04.155636Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:22:02.998133Z","title":"Deep L earning for V isual T racking: A C omprehensive S urvey","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.08548","last_updated":"2025-07-11T12:53:19Z","snapshot_observed_at":"2026-08-09T06:05:00.155443Z","submitted_at":"2025-07-11T12:53:19Z","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T18:22:02.998133Z"},"links":{"citing_paper":"/paper/2507.08548"},"observation_digest":"sha256:c1e05227ab8dc1d679282b7daedf1f5842908d183f5c92bc38c3e0a562130bd2","observation_id":"05eb3d49-5822-4733-bc7b-14baaf1ba5c9","resolution":{"observed_at":"2026-08-06T18:22:02.998133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.00714","last_updated":"2024-10-28T16:37:57Z","snapshot_observed_at":"2026-07-06T18:55:41.459417Z","submitted_at":"2024-08-01T17:00:08Z","title":"SAM 2: Segment Anything in Images and Videos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.00714","snapshot_observed_at":"2026-08-06T18:22:03.104662Z","title":"S am 2: S egment A nything in I mages and V ideos","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08548","last_updated":"2025-07-11T12:53:19Z","snapshot_observed_at":"2026-08-09T06:05:00.155443Z","submitted_at":"2025-07-11T12:53:19Z","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-06T18:22:03.104662Z"},"links":{"cited_paper":"/paper/2408.00714","citing_paper":"/paper/2507.08548"},"observation_digest":"sha256:cd19d7c5f4b67c6be22d4cddc76b4bb3026d29a2a15607002a81c06066994eb0","observation_id":"0a4b67db-105b-4c62-88d4-854229079d7a","resolution":{"observed_at":"2026-08-06T18:22:03.104662Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.00989","last_updated":"2023-06-01T17:59:58Z","snapshot_observed_at":"2026-08-09T06:04:31.284029Z","submitted_at":"2023-06-01T17:59:58Z","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.00989","snapshot_observed_at":"2026-08-06T18:22:03.200784Z","title":"Hiera: A H ierarchical V ision T ransformer without the B ells-and- W histles","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08548","last_updated":"2025-07-11T12:53:19Z","snapshot_observed_at":"2026-08-09T06:05:00.155443Z","submitted_at":"2025-07-11T12:53:19Z","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T18:22:03.200784Z"},"links":{"cited_paper":"/paper/2306.00989","citing_paper":"/paper/2507.08548"},"observation_digest":"sha256:aa0fd962d160469c4b26b57792982a47952acab09a665088e371ccd5fb7fd601","observation_id":"b2e5c341-216a-4c28-9289-0d704b1da705","resolution":{"observed_at":"2026-08-06T18:22:03.200784Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-06T18:22:03.297394Z","title":"Proximal P olicy O ptimization A lgorithms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.08548","last_updated":"2025-07-11T12:53:19Z","snapshot_observed_at":"2026-08-09T06:05:00.155443Z","submitted_at":"2025-07-11T12:53:19Z","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-06T18:22:03.297394Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2507.08548"},"observation_digest":"sha256:4b2a5ab9331783b14ee9cfbb47ee4977a71fda4a5dd4204df30210648feb3d9f","observation_id":"db0b8b04-45d1-4171-86f7-31b308badbca","resolution":{"observed_at":"2026-08-06T18:22:03.297394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.17576","last_updated":"2024-12-04T08:58:53Z","snapshot_observed_at":"2026-07-06T19:57:24.407368Z","submitted_at":"2024-11-26T16:41:09Z","title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.17576","snapshot_observed_at":"2026-08-06T18:22:03.406039Z","title":"A D istractor- A ware M emory for V isual O bject T racking with SAM2","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08548","last_updated":"2025-07-11T12:53:19Z","snapshot_observed_at":"2026-08-09T06:05:00.155443Z","submitted_at":"2025-07-11T12:53:19Z","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T18:22:03.406039Z"},"links":{"cited_paper":"/paper/2411.17576","citing_paper":"/paper/2507.08548"},"observation_digest":"sha256:a2534de887dcd1cc331eca8c52054f2a4806ec952c8fb2360006a71025481296","observation_id":"78bca6da-90de-40f9-ae44-3e5b69b0e55b","resolution":{"observed_at":"2026-08-06T18:22:03.406039Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.11922","last_updated":"2024-11-30T22:32:34Z","snapshot_observed_at":"2026-08-08T21:51:38.855361Z","submitted_at":"2024-11-18T05:59:03Z","title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.11922","snapshot_observed_at":"2026-08-06T18:22:03.534727Z","title":"S amurai: A dapting S egment A nything M odel for Z ero- S hot V isual T racking with M otion- A ware M emory","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08548","last_updated":"2025-07-11T12:53:19Z","snapshot_observed_at":"2026-08-09T06:05:00.155443Z","submitted_at":"2025-07-11T12:53:19Z","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T18:22:03.534727Z"},"links":{"cited_paper":"/paper/2411.11922","citing_paper":"/paper/2507.08548"},"observation_digest":"sha256:dfd30953a6e78288eac0dfe454fdc0cec65e2e77ddfd551a518fb86c8301cadc","observation_id":"96fa4e76-1556-4046-93ce-99abd5080994","resolution":{"observed_at":"2026-08-06T18:22:03.534727Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.00739","last_updated":"2025-04-30T02:19:31Z","snapshot_observed_at":"2026-08-07T15:57:58.535280Z","submitted_at":"2025-04-30T02:19:31Z","title":"MoSAM: Motion-Guided Segment Anything Model with Spatial-Temporal Memory Selection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.00739","snapshot_observed_at":"2026-08-06T18:22:03.615112Z","title":"M o SAM : M otion- G uided S egment A nything M odel with S patial- T emporal M emory S election","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.08548","last_updated":"2025-07-11T12:53:19Z","snapshot_observed_at":"2026-08-09T06:05:00.155443Z","submitted_at":"2025-07-11T12:53:19Z","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T18:22:03.615112Z"},"links":{"cited_paper":"/paper/2505.00739","citing_paper":"/paper/2507.08548"},"observation_digest":"sha256:b80118a2b0e5106d430f10587a8d02154fe8e7a046c5feaf5a2060b74c2805bc","observation_id":"1a02e3be-8380-4c7b-88da-7b44d4598de1","resolution":{"observed_at":"2026-08-06T18:22:03.615112Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:22:03.700313Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.08548","last_updated":"2025-07-11T12:53:19Z","snapshot_observed_at":"2026-08-09T06:05:00.155443Z","submitted_at":"2025-07-11T12:53:19Z","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-06T18:22:03.700313Z"},"links":{"citing_paper":"/paper/2507.08548"},"observation_digest":"sha256:f84fab2c2ecd082a123744193b1cbc2ca4bb62e1eb778bf59cae8907620f0056","observation_id":"0e787c96-7d1d-4b26-846c-fca398d1c877","resolution":{"observed_at":"2026-08-06T18:22:03.700313Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.08548","last_updated":"2025-07-11T12:53:19Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T06:05:00.155443Z","submitted_at":"2025-07-11T12:53:19Z","title":"SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2"},"reference_resolution":{"displayed":12,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":0,"verified_fuzzy":3},"total_outbound_references":12},"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 9 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2507.08548."}