{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BO35SUXELIPHXDB674ADIGPKEB","short_pith_number":"pith:BO35SUXE","schema_version":"1.0","canonical_sha256":"0bb7d952e45a1e7b8c3eff003419ea20494076dba00e1116e1f1c1f1952ef043","source":{"kind":"arxiv","id":"2506.01558","version":1},"attestation_state":"computed","paper":{"title":"SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Xu, Jiaze Li, Yansong Tang, Yong Liu, Yuji Wang","submitted_at":"2025-06-02T11:36:25Z","abstract_excerpt":"Reference Audio-Visual Segmentation (Ref-AVS) aims to provide a pixel-wise scene understanding in Language-aided Audio-Visual Scenes (LAVS). This task requires the model to continuously segment objects referred to by text and audio from a video. Previous dual-modality methods always fail due to the lack of a third modality and the existing triple-modality method struggles with spatio-temporal consistency, leading to the target shift of different frames. In this work, we introduce a novel framework, termed SAM2-LOVE, which integrates textual, audio, and visual representations into a learnable t"},"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":"2506.01558","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T11:36:25Z","cross_cats_sorted":[],"title_canon_sha256":"7fc4a0731d178a0e5e0bc3752bc82b233287b544f63605c834b4086e9a6c2de3","abstract_canon_sha256":"94fb5047e744eba6e615b444ace9e405778bb2e346b14b999c15ea8a40ec8ced"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:15.820825Z","signature_b64":"3RaukJb3w7xcuZSO3VPjXJF5dqxDWURlas2MBHM3TmVxDvEjBvVDrdIHqajLtah11vOrmxvphhEazX3i5o1lCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bb7d952e45a1e7b8c3eff003419ea20494076dba00e1116e1f1c1f1952ef043","last_reissued_at":"2026-07-05T11:14:15.820397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:15.820397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Xu, Jiaze Li, Yansong Tang, Yong Liu, Yuji Wang","submitted_at":"2025-06-02T11:36:25Z","abstract_excerpt":"Reference Audio-Visual Segmentation (Ref-AVS) aims to provide a pixel-wise scene understanding in Language-aided Audio-Visual Scenes (LAVS). This task requires the model to continuously segment objects referred to by text and audio from a video. Previous dual-modality methods always fail due to the lack of a third modality and the existing triple-modality method struggles with spatio-temporal consistency, leading to the target shift of different frames. In this work, we introduce a novel framework, termed SAM2-LOVE, which integrates textual, audio, and visual representations into a learnable t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01558","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/2506.01558/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":"2506.01558","created_at":"2026-07-05T11:14:15.820447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01558v1","created_at":"2026-07-05T11:14:15.820447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01558","created_at":"2026-07-05T11:14:15.820447+00:00"},{"alias_kind":"pith_short_12","alias_value":"BO35SUXELIPH","created_at":"2026-07-05T11:14:15.820447+00:00"},{"alias_kind":"pith_short_16","alias_value":"BO35SUXELIPHXDB6","created_at":"2026-07-05T11:14:15.820447+00:00"},{"alias_kind":"pith_short_8","alias_value":"BO35SUXE","created_at":"2026-07-05T11:14:15.820447+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/BO35SUXELIPHXDB674ADIGPKEB","json":"https://pith.science/pith/BO35SUXELIPHXDB674ADIGPKEB.json","graph_json":"https://pith.science/api/pith-number/BO35SUXELIPHXDB674ADIGPKEB/graph.json","events_json":"https://pith.science/api/pith-number/BO35SUXELIPHXDB674ADIGPKEB/events.json","paper":"https://pith.science/paper/BO35SUXE"},"agent_actions":{"view_html":"https://pith.science/pith/BO35SUXELIPHXDB674ADIGPKEB","download_json":"https://pith.science/pith/BO35SUXELIPHXDB674ADIGPKEB.json","view_paper":"https://pith.science/paper/BO35SUXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01558&json=true","fetch_graph":"https://pith.science/api/pith-number/BO35SUXELIPHXDB674ADIGPKEB/graph.json","fetch_events":"https://pith.science/api/pith-number/BO35SUXELIPHXDB674ADIGPKEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BO35SUXELIPHXDB674ADIGPKEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BO35SUXELIPHXDB674ADIGPKEB/action/storage_attestation","attest_author":"https://pith.science/pith/BO35SUXELIPHXDB674ADIGPKEB/action/author_attestation","sign_citation":"https://pith.science/pith/BO35SUXELIPHXDB674ADIGPKEB/action/citation_signature","submit_replication":"https://pith.science/pith/BO35SUXELIPHXDB674ADIGPKEB/action/replication_record"}},"created_at":"2026-07-05T11:14:15.820447+00:00","updated_at":"2026-07-05T11:14:15.820447+00:00"}