{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZEQPEIC42PLJ54EQLK5KIDAF3M","short_pith_number":"pith:ZEQPEIC4","schema_version":"1.0","canonical_sha256":"c920f2205cd3d69ef0905abaa40c05db2cb8aef8f1b4363eea4cc66505a668f7","source":{"kind":"arxiv","id":"2506.01304","version":1},"attestation_state":"computed","paper":{"title":"SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiyang Mei, Mike Zheng Shou, Pengyu Zhang","submitted_at":"2025-06-02T04:30:14Z","abstract_excerpt":"Foundation models like the Segment Anything Model (SAM) have significantly advanced promptable image segmentation in computer vision. However, extending these capabilities to videos presents substantial challenges, particularly in ensuring precise and temporally consistent mask propagation in dynamic scenes. SAM 2 attempts to address this by training a model on massive image and video data from scratch to learn complex spatiotemporal associations, resulting in huge training costs that hinder research and practical deployment. In this paper, we introduce SAM-I2V, an effective image-to-video upg"},"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":"2506.01304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T04:30:14Z","cross_cats_sorted":[],"title_canon_sha256":"7478e536d81e37388a7094c86265b5b10101c383cb574472a69be978501421ac","abstract_canon_sha256":"67fd08476795d36f57338be90bb8010c989a3dbadb54859f9916b7bebf898e4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:11.436784Z","signature_b64":"j0dqIaljU1fGfEWRHru6xmz56gz1SXthF3mG+8CDINuQs8vLAEg8pL33nEcGOl/PNItGsMZZl4DoM9/tV76bCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c920f2205cd3d69ef0905abaa40c05db2cb8aef8f1b4363eea4cc66505a668f7","last_reissued_at":"2026-07-05T11:14:11.436339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:11.436339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiyang Mei, Mike Zheng Shou, Pengyu Zhang","submitted_at":"2025-06-02T04:30:14Z","abstract_excerpt":"Foundation models like the Segment Anything Model (SAM) have significantly advanced promptable image segmentation in computer vision. However, extending these capabilities to videos presents substantial challenges, particularly in ensuring precise and temporally consistent mask propagation in dynamic scenes. SAM 2 attempts to address this by training a model on massive image and video data from scratch to learn complex spatiotemporal associations, resulting in huge training costs that hinder research and practical deployment. In this paper, we introduce SAM-I2V, an effective image-to-video upg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01304","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/2506.01304/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":"2506.01304","created_at":"2026-07-05T11:14:11.436396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01304v1","created_at":"2026-07-05T11:14:11.436396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01304","created_at":"2026-07-05T11:14:11.436396+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZEQPEIC42PLJ","created_at":"2026-07-05T11:14:11.436396+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZEQPEIC42PLJ54EQ","created_at":"2026-07-05T11:14:11.436396+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZEQPEIC4","created_at":"2026-07-05T11:14:11.436396+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZEQPEIC42PLJ54EQLK5KIDAF3M","json":"https://pith.science/pith/ZEQPEIC42PLJ54EQLK5KIDAF3M.json","graph_json":"https://pith.science/api/pith-number/ZEQPEIC42PLJ54EQLK5KIDAF3M/graph.json","events_json":"https://pith.science/api/pith-number/ZEQPEIC42PLJ54EQLK5KIDAF3M/events.json","paper":"https://pith.science/paper/ZEQPEIC4"},"agent_actions":{"view_html":"https://pith.science/pith/ZEQPEIC42PLJ54EQLK5KIDAF3M","download_json":"https://pith.science/pith/ZEQPEIC42PLJ54EQLK5KIDAF3M.json","view_paper":"https://pith.science/paper/ZEQPEIC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01304&json=true","fetch_graph":"https://pith.science/api/pith-number/ZEQPEIC42PLJ54EQLK5KIDAF3M/graph.json","fetch_events":"https://pith.science/api/pith-number/ZEQPEIC42PLJ54EQLK5KIDAF3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZEQPEIC42PLJ54EQLK5KIDAF3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZEQPEIC42PLJ54EQLK5KIDAF3M/action/storage_attestation","attest_author":"https://pith.science/pith/ZEQPEIC42PLJ54EQLK5KIDAF3M/action/author_attestation","sign_citation":"https://pith.science/pith/ZEQPEIC42PLJ54EQLK5KIDAF3M/action/citation_signature","submit_replication":"https://pith.science/pith/ZEQPEIC42PLJ54EQLK5KIDAF3M/action/replication_record"}},"created_at":"2026-07-05T11:14:11.436396+00:00","updated_at":"2026-07-05T11:14:11.436396+00:00"}