{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GL247SBXETWHPMBV3LDGHYHUCJ","short_pith_number":"pith:GL247SBX","schema_version":"1.0","canonical_sha256":"32f5cfc83724ec77b035dac663e0f41254a53150b8d17e89b0778c677174d6d3","source":{"kind":"arxiv","id":"2304.02970","version":7},"attestation_state":"computed","paper":{"title":"Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chong Wang, Fengbei Liu, Gustavo Carneiro, Helen Frazer, Hu Wang, Yuanhong Chen, Yuyuan Liu","submitted_at":"2023-04-06T09:54:06Z","abstract_excerpt":"Audio-visual segmentation (AVS) is a challenging task that involves accurately segmenting sounding objects based on audio-visual cues. The effectiveness of audio-visual learning critically depends on achieving accurate cross-modal alignment between sound and visual objects. Successful audio-visual learning requires two essential components: 1) a challenging dataset with high-quality pixel-level multi-class annotated images associated with audio files, and 2) a model that can establish strong links between audio information and its corresponding visual object. However, these requirements are on"},"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":"2304.02970","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T09:54:06Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"7ecc66ae26a533b2635349ab8538b3af7149827793a96b2dcfde900c25ccd3df","abstract_canon_sha256":"b1ce1df7a26e2d829bb9b16d209f4de56a8afd033daee6d85c3d0642985f9ab6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:20.056081Z","signature_b64":"TcSswM28FKpy//HqjwKZ2v2M88Rw3Y5xWVelLCbEUBpaJbsxp76NU0PN1cUfC5hibTdN+kp+z+17LHYk1uFSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32f5cfc83724ec77b035dac663e0f41254a53150b8d17e89b0778c677174d6d3","last_reissued_at":"2026-07-05T08:55:20.055599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:20.055599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chong Wang, Fengbei Liu, Gustavo Carneiro, Helen Frazer, Hu Wang, Yuanhong Chen, Yuyuan Liu","submitted_at":"2023-04-06T09:54:06Z","abstract_excerpt":"Audio-visual segmentation (AVS) is a challenging task that involves accurately segmenting sounding objects based on audio-visual cues. The effectiveness of audio-visual learning critically depends on achieving accurate cross-modal alignment between sound and visual objects. Successful audio-visual learning requires two essential components: 1) a challenging dataset with high-quality pixel-level multi-class annotated images associated with audio files, and 2) a model that can establish strong links between audio information and its corresponding visual object. However, these requirements are on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02970","kind":"arxiv","version":7},"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/2304.02970/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":"2304.02970","created_at":"2026-07-05T08:55:20.055657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.02970v7","created_at":"2026-07-05T08:55:20.055657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02970","created_at":"2026-07-05T08:55:20.055657+00:00"},{"alias_kind":"pith_short_12","alias_value":"GL247SBXETWH","created_at":"2026-07-05T08:55:20.055657+00:00"},{"alias_kind":"pith_short_16","alias_value":"GL247SBXETWHPMBV","created_at":"2026-07-05T08:55:20.055657+00:00"},{"alias_kind":"pith_short_8","alias_value":"GL247SBX","created_at":"2026-07-05T08:55:20.055657+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/GL247SBXETWHPMBV3LDGHYHUCJ","json":"https://pith.science/pith/GL247SBXETWHPMBV3LDGHYHUCJ.json","graph_json":"https://pith.science/api/pith-number/GL247SBXETWHPMBV3LDGHYHUCJ/graph.json","events_json":"https://pith.science/api/pith-number/GL247SBXETWHPMBV3LDGHYHUCJ/events.json","paper":"https://pith.science/paper/GL247SBX"},"agent_actions":{"view_html":"https://pith.science/pith/GL247SBXETWHPMBV3LDGHYHUCJ","download_json":"https://pith.science/pith/GL247SBXETWHPMBV3LDGHYHUCJ.json","view_paper":"https://pith.science/paper/GL247SBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.02970&json=true","fetch_graph":"https://pith.science/api/pith-number/GL247SBXETWHPMBV3LDGHYHUCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GL247SBXETWHPMBV3LDGHYHUCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GL247SBXETWHPMBV3LDGHYHUCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GL247SBXETWHPMBV3LDGHYHUCJ/action/storage_attestation","attest_author":"https://pith.science/pith/GL247SBXETWHPMBV3LDGHYHUCJ/action/author_attestation","sign_citation":"https://pith.science/pith/GL247SBXETWHPMBV3LDGHYHUCJ/action/citation_signature","submit_replication":"https://pith.science/pith/GL247SBXETWHPMBV3LDGHYHUCJ/action/replication_record"}},"created_at":"2026-07-05T08:55:20.055657+00:00","updated_at":"2026-07-05T08:55:20.055657+00:00"}