{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PM3PES4P5TMHE7ZOKTSD3Z4HQB","short_pith_number":"pith:PM3PES4P","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"},"canonical_sha256":"7b36f24b8fecd8727f2e54e43de7878074cae65d174f22e22e4308c0a670a6c5","source":{"kind":"arxiv","id":"2608.03264","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PM3PES4P5TMHE7ZOKTSD3Z4HQB","target":"record","payload":{"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"},"canonical_sha256":"7b36f24b8fecd8727f2e54e43de7878074cae65d174f22e22e4308c0a670a6c5","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"},"source_kind":"arxiv","source_id":"2608.03264","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-05T00:46:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kRW/2osFQBqOUW2O5XuMwKA0LAPgVpCYDcUFJPPDvQjs0z0CeGaRtPEik7vvnCXPAFQ++30CfcgV85KUfvr7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:02:33.071641Z"},"content_sha256":"209b41407a5a7c0f9ce6b62d47b40fbc132c7a37c36a7451001f2b99dded1137","schema_version":"1.0","event_id":"sha256:209b41407a5a7c0f9ce6b62d47b40fbc132c7a37c36a7451001f2b99dded1137"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PM3PES4P5TMHE7ZOKTSD3Z4HQB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-05T00:46:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hmPFpC0C/g20JSiZsjDfG2aOP7A9ZikPFWRVxJq1RZ7y1c45me/eujGb3enO8n54+fmaL32bqkUZyCcZ84C+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:02:33.072014Z"},"content_sha256":"a8d6953a97328be0ea4d6065dfc26f471d73bc42235bb2ab4364472c2f65738b","schema_version":"1.0","event_id":"sha256:a8d6953a97328be0ea4d6065dfc26f471d73bc42235bb2ab4364472c2f65738b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB/bundle.json","state_url":"https://pith.science/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T21:02:33Z","links":{"resolver":"https://pith.science/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB","bundle":"https://pith.science/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB/bundle.json","state":"https://pith.science/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PM3PES4P5TMHE7ZOKTSD3Z4HQB/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s8dgIx/D30KzwHDus9yUyX+rNeQjMca2wal/Exb2n4czPF3abAjweNT3dmd98ye8LjNzvIPpInn9sylo9tvtDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:02:33.074870Z","bundle_sha256":"fbcb51019460354c233d86000fcfeaf9c60c7903db51cfc5d8eec9fcdf5c2f59"}}