{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PM3PES4P5TMHE7ZOKTSD3Z4HQB","short_pith_number":"pith:PM3PES4P","schema_version":"1.0","canonical_sha256":"7b36f24b8fecd8727f2e54e43de7878074cae65d174f22e22e4308c0a670a6c5","source":{"kind":"arxiv","id":"2608.03264","version":1},"attestation_state":"computed","paper":{"title":"Hear to See: Discerning Stateful Listening for Audio-Visual Instance Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"cs.MM","authors_text":"Huchuan Lu, Jiahong Jiang, Jialong Zhong, Jingjing Li, Kai Peng, Leiye Liu, Miao Zhang, TingWei Liu, Wei Ji, Yongri Piao","submitted_at":"2026-08-04T07:35:57Z","abstract_excerpt":"Audio-visual instance segmentation (AVIS) requires accurately identifying and tracking individual sounding objects with pixel-level masks. Existing methods struggle to match overlapping acoustic events with visual instances and handle asynchronous audio-visual dynamics. Therefore, two critical questions arise: how can a model establish precise correspondence between overlapping sound sources and visual instances, and how can a model maintain robust tracking when audio and visual signals are temporally misaligned?This paper proposes Hear to See (H2S), addressing these challenges through two mec"},"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":"2608.03264","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-08-04T07:35:57Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"69cb9346dcefd9b95ef08b2fd6617d7b95f736df3a894ba5a733d46c134ee246","abstract_canon_sha256":"be55766085200acd4adb9bde5278b1a1536bc8eeb1ed7a5bcbac80ceec3b6154"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:46:33.155794Z","signature_b64":"K0NmXFrDdVNl7i744d+FtXcWJP+30j+dSQ+aDONZuVxuSLcCllv9eLTxQ12dE4VzWFSFYZ8+XaB6qSFsYDdUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b36f24b8fecd8727f2e54e43de7878074cae65d174f22e22e4308c0a670a6c5","last_reissued_at":"2026-08-05T00:46:33.153331Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:46:33.153331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hear to See: Discerning Stateful Listening for Audio-Visual Instance Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"cs.MM","authors_text":"Huchuan Lu, Jiahong Jiang, Jialong Zhong, Jingjing Li, Kai Peng, Leiye Liu, Miao Zhang, TingWei Liu, Wei Ji, Yongri Piao","submitted_at":"2026-08-04T07:35:57Z","abstract_excerpt":"Audio-visual instance segmentation (AVIS) requires accurately identifying and tracking individual sounding objects with pixel-level masks. Existing methods struggle to match overlapping acoustic events with visual instances and handle asynchronous audio-visual dynamics. Therefore, two critical questions arise: how can a model establish precise correspondence between overlapping sound sources and visual instances, and how can a model maintain robust tracking when audio and visual signals are temporally misaligned?This paper proposes Hear to See (H2S), addressing these challenges through two mec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03264","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/2608.03264/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":"2608.03264","created_at":"2026-08-05T00:46:33.154293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03264v1","created_at":"2026-08-05T00:46:33.154293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03264","created_at":"2026-08-05T00:46:33.154293+00:00"},{"alias_kind":"pith_short_12","alias_value":"PM3PES4P5TMH","created_at":"2026-08-05T00:46:33.154293+00:00"},{"alias_kind":"pith_short_16","alias_value":"PM3PES4P5TMHE7ZO","created_at":"2026-08-05T00:46:33.154293+00:00"},{"alias_kind":"pith_short_8","alias_value":"PM3PES4P","created_at":"2026-08-05T00:46:33.154293+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/PM3PES4P5TMHE7ZOKTSD3Z4HQB","json":"https://pith.science/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB.json","graph_json":"https://pith.science/api/pith-number/PM3PES4P5TMHE7ZOKTSD3Z4HQB/graph.json","events_json":"https://pith.science/api/pith-number/PM3PES4P5TMHE7ZOKTSD3Z4HQB/events.json","paper":"https://pith.science/paper/PM3PES4P"},"agent_actions":{"view_html":"https://pith.science/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB","download_json":"https://pith.science/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB.json","view_paper":"https://pith.science/paper/PM3PES4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03264&json=true","fetch_graph":"https://pith.science/api/pith-number/PM3PES4P5TMHE7ZOKTSD3Z4HQB/graph.json","fetch_events":"https://pith.science/api/pith-number/PM3PES4P5TMHE7ZOKTSD3Z4HQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB/action/storage_attestation","attest_author":"https://pith.science/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB/action/author_attestation","sign_citation":"https://pith.science/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB/action/citation_signature","submit_replication":"https://pith.science/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB/action/replication_record"}},"created_at":"2026-08-05T00:46:33.154293+00:00","updated_at":"2026-08-05T00:46:33.154293+00:00"}