{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S5A5V6E7GHCWC3ZUGGIYK25CYU","short_pith_number":"pith:S5A5V6E7","schema_version":"1.0","canonical_sha256":"9741daf89f31c5616f343191856ba2c53e4cb06d5d905e91a0617e18041df9b6","source":{"kind":"arxiv","id":"2503.12781","version":1},"attestation_state":"computed","paper":{"title":"SAM2 for Image and Video Segmentation: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Tang Hao, Zhang Jiaxing","submitted_at":"2025-03-17T03:33:36Z","abstract_excerpt":"Despite significant advances in deep learning for image and video segmentation, existing models continue to face challenges in cross-domain adaptability and generalization. Image and video segmentation are fundamental tasks in computer vision with wide-ranging applications in healthcare, agriculture, industrial inspection, and autonomous driving. With the advent of large-scale foundation models, SAM2 - an improved version of SAM (Segment Anything Model)has been optimized for segmentation tasks, demonstrating enhanced performance in complex scenarios. However, SAM2's adaptability and limitation"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.12781","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T03:33:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1fcd83f1cb0c56cf284454a6d2bbd099b67ff286ff8f2e960af2cbb9980b2103","abstract_canon_sha256":"849aac3e8efd2672d2611435395a43cc2f165e747ce6bdb3d80cd41d797998a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:46.031729Z","signature_b64":"vcbTRw/pVYLOrobq9OJtcSMqYxoGgMKPMVs+QUTY/FglnkfR+JQEwTf3XCMYEsQ06MAkbfCiRe8vnyBWI4NtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9741daf89f31c5616f343191856ba2c53e4cb06d5d905e91a0617e18041df9b6","last_reissued_at":"2026-07-05T10:32:46.031126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:46.031126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAM2 for Image and Video Segmentation: A Comprehensive Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Tang Hao, Zhang Jiaxing","submitted_at":"2025-03-17T03:33:36Z","abstract_excerpt":"Despite significant advances in deep learning for image and video segmentation, existing models continue to face challenges in cross-domain adaptability and generalization. Image and video segmentation are fundamental tasks in computer vision with wide-ranging applications in healthcare, agriculture, industrial inspection, and autonomous driving. With the advent of large-scale foundation models, SAM2 - an improved version of SAM (Segment Anything Model)has been optimized for segmentation tasks, demonstrating enhanced performance in complex scenarios. However, SAM2's adaptability and limitation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12781","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.12781/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.12781","created_at":"2026-07-05T10:32:46.031190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12781v1","created_at":"2026-07-05T10:32:46.031190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12781","created_at":"2026-07-05T10:32:46.031190+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5A5V6E7GHCW","created_at":"2026-07-05T10:32:46.031190+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5A5V6E7GHCWC3ZU","created_at":"2026-07-05T10:32:46.031190+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5A5V6E7","created_at":"2026-07-05T10:32:46.031190+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07230","citing_title":"`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2512.22046","citing_title":"Backdoor Attacks on Prompt-Driven Video Segmentation Foundation Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09648","citing_title":"TRACE: Thermal Recognition Attentive-Framework for CO2 Emissions from Livestock","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S5A5V6E7GHCWC3ZUGGIYK25CYU","json":"https://pith.science/pith/S5A5V6E7GHCWC3ZUGGIYK25CYU.json","graph_json":"https://pith.science/api/pith-number/S5A5V6E7GHCWC3ZUGGIYK25CYU/graph.json","events_json":"https://pith.science/api/pith-number/S5A5V6E7GHCWC3ZUGGIYK25CYU/events.json","paper":"https://pith.science/paper/S5A5V6E7"},"agent_actions":{"view_html":"https://pith.science/pith/S5A5V6E7GHCWC3ZUGGIYK25CYU","download_json":"https://pith.science/pith/S5A5V6E7GHCWC3ZUGGIYK25CYU.json","view_paper":"https://pith.science/paper/S5A5V6E7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12781&json=true","fetch_graph":"https://pith.science/api/pith-number/S5A5V6E7GHCWC3ZUGGIYK25CYU/graph.json","fetch_events":"https://pith.science/api/pith-number/S5A5V6E7GHCWC3ZUGGIYK25CYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5A5V6E7GHCWC3ZUGGIYK25CYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5A5V6E7GHCWC3ZUGGIYK25CYU/action/storage_attestation","attest_author":"https://pith.science/pith/S5A5V6E7GHCWC3ZUGGIYK25CYU/action/author_attestation","sign_citation":"https://pith.science/pith/S5A5V6E7GHCWC3ZUGGIYK25CYU/action/citation_signature","submit_replication":"https://pith.science/pith/S5A5V6E7GHCWC3ZUGGIYK25CYU/action/replication_record"}},"created_at":"2026-07-05T10:32:46.031190+00:00","updated_at":"2026-07-05T10:32:46.031190+00:00"}