{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PM3PES4P5TMHE7ZOKTSD3Z4HQB","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":"be55766085200acd4adb9bde5278b1a1536bc8eeb1ed7a5bcbac80ceec3b6154","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-08-04T07:35:57Z","title_canon_sha256":"69cb9346dcefd9b95ef08b2fd6617d7b95f736df3a894ba5a733d46c134ee246"},"schema_version":"1.0","source":{"id":"2608.03264","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03264","created_at":"2026-08-05T00:46:33Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03264v1","created_at":"2026-08-05T00:46:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03264","created_at":"2026-08-05T00:46:33Z"},{"alias_kind":"pith_short_12","alias_value":"PM3PES4P5TMH","created_at":"2026-08-05T00:46:33Z"},{"alias_kind":"pith_short_16","alias_value":"PM3PES4P5TMHE7ZO","created_at":"2026-08-05T00:46:33Z"},{"alias_kind":"pith_short_8","alias_value":"PM3PES4P","created_at":"2026-08-05T00:46:33Z"}],"graph_snapshots":[{"event_id":"sha256:a8d6953a97328be0ea4d6065dfc26f471d73bc42235bb2ab4364472c2f65738b","target":"graph","created_at":"2026-08-05T00:46:33Z","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/2608.03264/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Huchuan Lu, Jiahong Jiang, Jialong Zhong, Jingjing Li, Kai Peng, Leiye Liu, Miao Zhang, TingWei Liu, Wei Ji, Yongri Piao","cross_cats":["cs.CV","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-08-04T07:35:57Z","title":"Hear to See: Discerning Stateful Listening for Audio-Visual Instance Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03264","kind":"arxiv","version":1},"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":"sha256:209b41407a5a7c0f9ce6b62d47b40fbc132c7a37c36a7451001f2b99dded1137","target":"record","created_at":"2026-08-05T00:46:33Z","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":"be55766085200acd4adb9bde5278b1a1536bc8eeb1ed7a5bcbac80ceec3b6154","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-08-04T07:35:57Z","title_canon_sha256":"69cb9346dcefd9b95ef08b2fd6617d7b95f736df3a894ba5a733d46c134ee246"},"schema_version":"1.0","source":{"id":"2608.03264","kind":"arxiv","version":1}},"canonical_sha256":"7b36f24b8fecd8727f2e54e43de7878074cae65d174f22e22e4308c0a670a6c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b36f24b8fecd8727f2e54e43de7878074cae65d174f22e22e4308c0a670a6c5","first_computed_at":"2026-08-05T00:46:33.153331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:46:33.153331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K0NmXFrDdVNl7i744d+FtXcWJP+30j+dSQ+aDONZuVxuSLcCllv9eLTxQ12dE4VzWFSFYZ8+XaB6qSFsYDdUAA==","signature_status":"signed_v1","signed_at":"2026-08-05T00:46:33.155794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03264","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:209b41407a5a7c0f9ce6b62d47b40fbc132c7a37c36a7451001f2b99dded1137","sha256:a8d6953a97328be0ea4d6065dfc26f471d73bc42235bb2ab4364472c2f65738b"],"state_sha256":"9d8cc63ef5d4efae906ed3c9fbc217d8c58eead6dbeb83954d709c349beab7cc"}