{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MX7TIZY3LGR7FEYMVENPHXOWH7","short_pith_number":"pith:MX7TIZY3","schema_version":"1.0","canonical_sha256":"65ff34671b59a3f2930ca91af3ddd63ff3bdbf952ce04b2c11bd9655a81d85a0","source":{"kind":"arxiv","id":"2411.17646","version":2},"attestation_state":"computed","paper":{"title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carlo Masone, Claudia Cuttano, Gabriele Rosi, Gabriele Trivigno, Giuseppe Averta","submitted_at":"2024-11-26T18:10:54Z","abstract_excerpt":"Referring Video Object Segmentation (RVOS) relies on natural language expressions to segment an object in a video clip. Existing methods restrict reasoning either to independent short clips, losing global context, or process the entire video offline, impairing their application in a streaming fashion. In this work, we aim to surpass these limitations and design an RVOS method capable of effectively operating in streaming-like scenarios while retaining contextual information from past frames. We build upon the Segment-Anything 2 (SAM2) model, that provides robust segmentation and tracking capab"},"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":"2411.17646","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T18:10:54Z","cross_cats_sorted":[],"title_canon_sha256":"e6f5f133331c85a81be084a283c6236c52a2d1f63da150117a44ccfbf8547e24","abstract_canon_sha256":"71436caa14ea428442a6935e5cd16722d742b5e3770ea2c1dcca3ee608dd8a26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:38.482381Z","signature_b64":"FesG6hUInIRILKJAZRYlRFA7SehuxcNZz0zvDkLIvfykrfpPL1iWhXP/aRWiN39tKT+44RmNuLa0tjsZR2L7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65ff34671b59a3f2930ca91af3ddd63ff3bdbf952ce04b2c11bd9655a81d85a0","last_reissued_at":"2026-07-05T10:38:38.481949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:38.481949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Carlo Masone, Claudia Cuttano, Gabriele Rosi, Gabriele Trivigno, Giuseppe Averta","submitted_at":"2024-11-26T18:10:54Z","abstract_excerpt":"Referring Video Object Segmentation (RVOS) relies on natural language expressions to segment an object in a video clip. Existing methods restrict reasoning either to independent short clips, losing global context, or process the entire video offline, impairing their application in a streaming fashion. In this work, we aim to surpass these limitations and design an RVOS method capable of effectively operating in streaming-like scenarios while retaining contextual information from past frames. We build upon the Segment-Anything 2 (SAM2) model, that provides robust segmentation and tracking capab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17646","kind":"arxiv","version":2},"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/2411.17646/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":"2411.17646","created_at":"2026-07-05T10:38:38.482003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17646v2","created_at":"2026-07-05T10:38:38.482003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17646","created_at":"2026-07-05T10:38:38.482003+00:00"},{"alias_kind":"pith_short_12","alias_value":"MX7TIZY3LGR7","created_at":"2026-07-05T10:38:38.482003+00:00"},{"alias_kind":"pith_short_16","alias_value":"MX7TIZY3LGR7FEYM","created_at":"2026-07-05T10:38:38.482003+00:00"},{"alias_kind":"pith_short_8","alias_value":"MX7TIZY3","created_at":"2026-07-05T10:38:38.482003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20103","citing_title":"BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MX7TIZY3LGR7FEYMVENPHXOWH7","json":"https://pith.science/pith/MX7TIZY3LGR7FEYMVENPHXOWH7.json","graph_json":"https://pith.science/api/pith-number/MX7TIZY3LGR7FEYMVENPHXOWH7/graph.json","events_json":"https://pith.science/api/pith-number/MX7TIZY3LGR7FEYMVENPHXOWH7/events.json","paper":"https://pith.science/paper/MX7TIZY3"},"agent_actions":{"view_html":"https://pith.science/pith/MX7TIZY3LGR7FEYMVENPHXOWH7","download_json":"https://pith.science/pith/MX7TIZY3LGR7FEYMVENPHXOWH7.json","view_paper":"https://pith.science/paper/MX7TIZY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17646&json=true","fetch_graph":"https://pith.science/api/pith-number/MX7TIZY3LGR7FEYMVENPHXOWH7/graph.json","fetch_events":"https://pith.science/api/pith-number/MX7TIZY3LGR7FEYMVENPHXOWH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MX7TIZY3LGR7FEYMVENPHXOWH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MX7TIZY3LGR7FEYMVENPHXOWH7/action/storage_attestation","attest_author":"https://pith.science/pith/MX7TIZY3LGR7FEYMVENPHXOWH7/action/author_attestation","sign_citation":"https://pith.science/pith/MX7TIZY3LGR7FEYMVENPHXOWH7/action/citation_signature","submit_replication":"https://pith.science/pith/MX7TIZY3LGR7FEYMVENPHXOWH7/action/replication_record"}},"created_at":"2026-07-05T10:38:38.482003+00:00","updated_at":"2026-07-05T10:38:38.482003+00:00"}