{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WSXQB3YFEBQXZPRB2N3Y4B4RNN","short_pith_number":"pith:WSXQB3YF","canonical_record":{"source":{"id":"2502.00358","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-01T07:40:29Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"ef447f2aa700526619e8f8f2b2cc7579d426ac016c857eab8e3d700e44648a5d","abstract_canon_sha256":"c746fd448b8185ae6bac3f69d02389e0cc95c818131d61459cf0c3d9a660cc38"},"schema_version":"1.0"},"canonical_sha256":"b4af00ef0520617cbe21d3778e07916b7906283b935efd6a4e067cb509faad3e","source":{"kind":"arxiv","id":"2502.00358","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00358","created_at":"2026-07-05T10:17:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00358v2","created_at":"2026-07-05T10:17:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00358","created_at":"2026-07-05T10:17:53Z"},{"alias_kind":"pith_short_12","alias_value":"WSXQB3YFEBQX","created_at":"2026-07-05T10:17:53Z"},{"alias_kind":"pith_short_16","alias_value":"WSXQB3YFEBQXZPRB","created_at":"2026-07-05T10:17:53Z"},{"alias_kind":"pith_short_8","alias_value":"WSXQB3YF","created_at":"2026-07-05T10:17:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WSXQB3YFEBQXZPRB2N3Y4B4RNN","target":"record","payload":{"canonical_record":{"source":{"id":"2502.00358","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-01T07:40:29Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"ef447f2aa700526619e8f8f2b2cc7579d426ac016c857eab8e3d700e44648a5d","abstract_canon_sha256":"c746fd448b8185ae6bac3f69d02389e0cc95c818131d61459cf0c3d9a660cc38"},"schema_version":"1.0"},"canonical_sha256":"b4af00ef0520617cbe21d3778e07916b7906283b935efd6a4e067cb509faad3e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:53.567419Z","signature_b64":"VZikjofEknq/brlVAy7DeOsqg7W9MQcxWW0N2RFa4YCPHskRXkE09nY484/vkgv0DyYFZvYNcDTqqW1b/+yQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4af00ef0520617cbe21d3778e07916b7906283b935efd6a4e067cb509faad3e","last_reissued_at":"2026-07-05T10:17:53.566917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:53.566917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.00358","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WjiWPTyARmrATRAb2hUEQgC8q5mHFpH5C10V8lFKP6mv/xSlfDtOlEPivR3LL6y9VucZOWEZzarwaMNHB/1sBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:47:10.446032Z"},"content_sha256":"3902fb95fdfd1f3edba4dd14e36789ade0d0952799f37af9c4240dcf48a67131","schema_version":"1.0","event_id":"sha256:3902fb95fdfd1f3edba4dd14e36789ade0d0952799f37af9c4240dcf48a67131"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WSXQB3YFEBQXZPRB2N3Y4B4RNN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Audio-Visual Segmentation Models Truly Segment Sounding Objects?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jia Li, Wenjie Zhao, Yapeng Tian, Yunhui Guo, Ziru Huang","submitted_at":"2025-02-01T07:40:29Z","abstract_excerpt":"Unlike traditional visual segmentation, audio-visual segmentation (AVS) requires the model not only to identify and segment objects but also to determine whether they are sound sources. Recent AVS approaches, leveraging transformer architectures and powerful foundation models like SAM, have achieved impressive performance on standard benchmarks. Yet, an important question remains: Do these models genuinely integrate audio-visual cues to segment sounding objects? In this paper, we systematically investigate this issue in the context of robust AVS. Our study reveals a fundamental bias in current"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00358","kind":"arxiv","version":2},"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/2502.00358/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":"2026-07-05T10:17:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ozj5kj5xjTky34JJ575uO6B/8Jxw5a/fwH+CETn8fz00LwGcTsvziTR8x4G+mCRWCssuIQa9D9JsBu2RMueOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:47:10.446536Z"},"content_sha256":"3a3c5aebe4afba71ec9f9d57d4dca21d543eb700f07fbe47b655f61056e76d37","schema_version":"1.0","event_id":"sha256:3a3c5aebe4afba71ec9f9d57d4dca21d543eb700f07fbe47b655f61056e76d37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WSXQB3YFEBQXZPRB2N3Y4B4RNN/bundle.json","state_url":"https://pith.science/pith/WSXQB3YFEBQXZPRB2N3Y4B4RNN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WSXQB3YFEBQXZPRB2N3Y4B4RNN/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":"2026-08-06T22:47:10Z","links":{"resolver":"https://pith.science/pith/WSXQB3YFEBQXZPRB2N3Y4B4RNN","bundle":"https://pith.science/pith/WSXQB3YFEBQXZPRB2N3Y4B4RNN/bundle.json","state":"https://pith.science/pith/WSXQB3YFEBQXZPRB2N3Y4B4RNN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WSXQB3YFEBQXZPRB2N3Y4B4RNN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WSXQB3YFEBQXZPRB2N3Y4B4RNN","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":"c746fd448b8185ae6bac3f69d02389e0cc95c818131d61459cf0c3d9a660cc38","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-01T07:40:29Z","title_canon_sha256":"ef447f2aa700526619e8f8f2b2cc7579d426ac016c857eab8e3d700e44648a5d"},"schema_version":"1.0","source":{"id":"2502.00358","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00358","created_at":"2026-07-05T10:17:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00358v2","created_at":"2026-07-05T10:17:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00358","created_at":"2026-07-05T10:17:53Z"},{"alias_kind":"pith_short_12","alias_value":"WSXQB3YFEBQX","created_at":"2026-07-05T10:17:53Z"},{"alias_kind":"pith_short_16","alias_value":"WSXQB3YFEBQXZPRB","created_at":"2026-07-05T10:17:53Z"},{"alias_kind":"pith_short_8","alias_value":"WSXQB3YF","created_at":"2026-07-05T10:17:53Z"}],"graph_snapshots":[{"event_id":"sha256:3a3c5aebe4afba71ec9f9d57d4dca21d543eb700f07fbe47b655f61056e76d37","target":"graph","created_at":"2026-07-05T10:17:53Z","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/2502.00358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unlike traditional visual segmentation, audio-visual segmentation (AVS) requires the model not only to identify and segment objects but also to determine whether they are sound sources. Recent AVS approaches, leveraging transformer architectures and powerful foundation models like SAM, have achieved impressive performance on standard benchmarks. Yet, an important question remains: Do these models genuinely integrate audio-visual cues to segment sounding objects? In this paper, we systematically investigate this issue in the context of robust AVS. Our study reveals a fundamental bias in current","authors_text":"Jia Li, Wenjie Zhao, Yapeng Tian, Yunhui Guo, Ziru Huang","cross_cats":["cs.AI","cs.LG","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-01T07:40:29Z","title":"Do Audio-Visual Segmentation Models Truly Segment Sounding Objects?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00358","kind":"arxiv","version":2},"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":"sha256:3902fb95fdfd1f3edba4dd14e36789ade0d0952799f37af9c4240dcf48a67131","target":"record","created_at":"2026-07-05T10:17:53Z","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":"c746fd448b8185ae6bac3f69d02389e0cc95c818131d61459cf0c3d9a660cc38","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-01T07:40:29Z","title_canon_sha256":"ef447f2aa700526619e8f8f2b2cc7579d426ac016c857eab8e3d700e44648a5d"},"schema_version":"1.0","source":{"id":"2502.00358","kind":"arxiv","version":2}},"canonical_sha256":"b4af00ef0520617cbe21d3778e07916b7906283b935efd6a4e067cb509faad3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4af00ef0520617cbe21d3778e07916b7906283b935efd6a4e067cb509faad3e","first_computed_at":"2026-07-05T10:17:53.566917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:53.566917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VZikjofEknq/brlVAy7DeOsqg7W9MQcxWW0N2RFa4YCPHskRXkE09nY484/vkgv0DyYFZvYNcDTqqW1b/+yQAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:53.567419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00358","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3902fb95fdfd1f3edba4dd14e36789ade0d0952799f37af9c4240dcf48a67131","sha256:3a3c5aebe4afba71ec9f9d57d4dca21d543eb700f07fbe47b655f61056e76d37"],"state_sha256":"1e735b3766f0e8c8b62dabc5cea7cd1d4aa673ff3507a2a41752b6de59ada541"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QLNOrNvToTPHZolsb20a7eFZ9RvdVhKkps4yRD+6E3KAm1khPFSyXoCVhdKUR+FngLGM6aoJl8C+0Us3s79QDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T22:47:10.450571Z","bundle_sha256":"b3f7bee0f33f7582a9fc55d46fe5f93a40f7bb957163924b66d82d131a653cc6"}}