{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MX7TIZY3LGR7FEYMVENPHXOWH7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"71436caa14ea428442a6935e5cd16722d742b5e3770ea2c1dcca3ee608dd8a26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T18:10:54Z","title_canon_sha256":"e6f5f133331c85a81be084a283c6236c52a2d1f63da150117a44ccfbf8547e24"},"schema_version":"1.0","source":{"id":"2411.17646","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17646","created_at":"2026-07-05T10:38:38Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17646v2","created_at":"2026-07-05T10:38:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17646","created_at":"2026-07-05T10:38:38Z"},{"alias_kind":"pith_short_12","alias_value":"MX7TIZY3LGR7","created_at":"2026-07-05T10:38:38Z"},{"alias_kind":"pith_short_16","alias_value":"MX7TIZY3LGR7FEYM","created_at":"2026-07-05T10:38:38Z"},{"alias_kind":"pith_short_8","alias_value":"MX7TIZY3","created_at":"2026-07-05T10:38:38Z"}],"graph_snapshots":[{"event_id":"sha256:77e47bffc752cd5aec077de2260ab1e1cfd1a3940027295afaee5e8812f7971b","target":"graph","created_at":"2026-07-05T10:38:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.17646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Carlo Masone, Claudia Cuttano, Gabriele Rosi, Gabriele Trivigno, Giuseppe Averta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T18:10:54Z","title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17646","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3b88de9ad6ce3dedad04eb5026def518531a9f10bb1ce71f1b4ab91361ee900a","target":"record","created_at":"2026-07-05T10:38:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"71436caa14ea428442a6935e5cd16722d742b5e3770ea2c1dcca3ee608dd8a26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T18:10:54Z","title_canon_sha256":"e6f5f133331c85a81be084a283c6236c52a2d1f63da150117a44ccfbf8547e24"},"schema_version":"1.0","source":{"id":"2411.17646","kind":"arxiv","version":2}},"canonical_sha256":"65ff34671b59a3f2930ca91af3ddd63ff3bdbf952ce04b2c11bd9655a81d85a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65ff34671b59a3f2930ca91af3ddd63ff3bdbf952ce04b2c11bd9655a81d85a0","first_computed_at":"2026-07-05T10:38:38.481949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:38.481949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FesG6hUInIRILKJAZRYlRFA7SehuxcNZz0zvDkLIvfykrfpPL1iWhXP/aRWiN39tKT+44RmNuLa0tjsZR2L7Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:38.482381Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17646","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b88de9ad6ce3dedad04eb5026def518531a9f10bb1ce71f1b4ab91361ee900a","sha256:77e47bffc752cd5aec077de2260ab1e1cfd1a3940027295afaee5e8812f7971b"],"state_sha256":"0013d40fdf49b22a37fd884898f16970af948a32201b9ec920fbd2decfe14821"}