{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VUT4VG2LCDVQMKDPMZXPWOSI54","short_pith_number":"pith:VUT4VG2L","canonical_record":{"source":{"id":"2506.18055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-06-22T14:43:37Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b5af44490d342a5c92a21174a35adc9ce8effd86f0a2659b407d15e20664656c","abstract_canon_sha256":"3c2bb1a814e9b6fe03ac16685c38d3c39140fba4a2434a6b8c5497d59c604747"},"schema_version":"1.0"},"canonical_sha256":"ad27ca9b4b10eb06286f666efb3a48ef09a3d54e404bc3411153cfc64506cb9d","source":{"kind":"arxiv","id":"2506.18055","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18055","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18055v1","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18055","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"pith_short_12","alias_value":"VUT4VG2LCDVQ","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"pith_short_16","alias_value":"VUT4VG2LCDVQMKDP","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"pith_short_8","alias_value":"VUT4VG2L","created_at":"2026-07-05T11:25:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VUT4VG2LCDVQMKDPMZXPWOSI54","target":"record","payload":{"canonical_record":{"source":{"id":"2506.18055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-06-22T14:43:37Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b5af44490d342a5c92a21174a35adc9ce8effd86f0a2659b407d15e20664656c","abstract_canon_sha256":"3c2bb1a814e9b6fe03ac16685c38d3c39140fba4a2434a6b8c5497d59c604747"},"schema_version":"1.0"},"canonical_sha256":"ad27ca9b4b10eb06286f666efb3a48ef09a3d54e404bc3411153cfc64506cb9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:27.903490Z","signature_b64":"QnvHdZFy75QY81sZ1UpQfa+M4Westy8Q8g61GwbvCmdtoJ3PH150xyv8x5CmXdq6nbVOANd1Nql/NuQ3JaFcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad27ca9b4b10eb06286f666efb3a48ef09a3d54e404bc3411153cfc64506cb9d","last_reissued_at":"2026-07-05T11:25:27.902891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:27.902891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.18055","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":"2026-07-05T11:25:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CB7owMsQ3SEwH3RbUn8PuRyzDbHYwhCqRa7bAaDPW4hRfOG32SKuf4ZUU5Vrs0N/P3tUsxudoDFighW1j99fDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:44:03.672670Z"},"content_sha256":"4cfdbb5456da378e6f50f815e635d4f85875617c5225111b621de8dd8b1666c9","schema_version":"1.0","event_id":"sha256:4cfdbb5456da378e6f50f815e635d4f85875617c5225111b621de8dd8b1666c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VUT4VG2LCDVQMKDPMZXPWOSI54","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Face-Voice Association for Audiovisual Active Speaker Detection in Egocentric Recordings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Jason Clarke, Stefan Goetze, Yoshihiko Gotoh","submitted_at":"2025-06-22T14:43:37Z","abstract_excerpt":"Audiovisual active speaker detection (ASD) is conventionally performed by modelling the temporal synchronisation of acoustic and visual speech cues. In egocentric recordings, however, the efficacy of synchronisation-based methods is compromised by occlusions, motion blur, and adverse acoustic conditions. In this work, a novel framework is proposed that exclusively leverages cross-modal face-voice associations to determine speaker activity. An existing face-voice association model is integrated with a transformer-based encoder that aggregates facial identity information by dynamically weighting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18055","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/2506.18055/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":"2026-07-05T11:25:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5YKu/lgTadI9pAuwWCH0N+UFPBTh69a2S8RB9CCr1KyealClU6QYwVJVhYZAWGwB716TzOwc+4oHEzhibgdWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:44:03.673205Z"},"content_sha256":"e96085ec9e7b90aab41c6caea20b62c1e7e1c3a714fe458c8da5b61ed15848b1","schema_version":"1.0","event_id":"sha256:e96085ec9e7b90aab41c6caea20b62c1e7e1c3a714fe458c8da5b61ed15848b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VUT4VG2LCDVQMKDPMZXPWOSI54/bundle.json","state_url":"https://pith.science/pith/VUT4VG2LCDVQMKDPMZXPWOSI54/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VUT4VG2LCDVQMKDPMZXPWOSI54/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":"2026-08-08T16:44:03Z","links":{"resolver":"https://pith.science/pith/VUT4VG2LCDVQMKDPMZXPWOSI54","bundle":"https://pith.science/pith/VUT4VG2LCDVQMKDPMZXPWOSI54/bundle.json","state":"https://pith.science/pith/VUT4VG2LCDVQMKDPMZXPWOSI54/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VUT4VG2LCDVQMKDPMZXPWOSI54/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VUT4VG2LCDVQMKDPMZXPWOSI54","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":"3c2bb1a814e9b6fe03ac16685c38d3c39140fba4a2434a6b8c5497d59c604747","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-06-22T14:43:37Z","title_canon_sha256":"b5af44490d342a5c92a21174a35adc9ce8effd86f0a2659b407d15e20664656c"},"schema_version":"1.0","source":{"id":"2506.18055","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18055","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18055v1","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18055","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"pith_short_12","alias_value":"VUT4VG2LCDVQ","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"pith_short_16","alias_value":"VUT4VG2LCDVQMKDP","created_at":"2026-07-05T11:25:27Z"},{"alias_kind":"pith_short_8","alias_value":"VUT4VG2L","created_at":"2026-07-05T11:25:27Z"}],"graph_snapshots":[{"event_id":"sha256:e96085ec9e7b90aab41c6caea20b62c1e7e1c3a714fe458c8da5b61ed15848b1","target":"graph","created_at":"2026-07-05T11:25:27Z","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/2506.18055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audiovisual active speaker detection (ASD) is conventionally performed by modelling the temporal synchronisation of acoustic and visual speech cues. In egocentric recordings, however, the efficacy of synchronisation-based methods is compromised by occlusions, motion blur, and adverse acoustic conditions. In this work, a novel framework is proposed that exclusively leverages cross-modal face-voice associations to determine speaker activity. An existing face-voice association model is integrated with a transformer-based encoder that aggregates facial identity information by dynamically weighting","authors_text":"Jason Clarke, Stefan Goetze, Yoshihiko Gotoh","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-06-22T14:43:37Z","title":"Face-Voice Association for Audiovisual Active Speaker Detection in Egocentric Recordings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18055","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":"sha256:4cfdbb5456da378e6f50f815e635d4f85875617c5225111b621de8dd8b1666c9","target":"record","created_at":"2026-07-05T11:25:27Z","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":"3c2bb1a814e9b6fe03ac16685c38d3c39140fba4a2434a6b8c5497d59c604747","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-06-22T14:43:37Z","title_canon_sha256":"b5af44490d342a5c92a21174a35adc9ce8effd86f0a2659b407d15e20664656c"},"schema_version":"1.0","source":{"id":"2506.18055","kind":"arxiv","version":1}},"canonical_sha256":"ad27ca9b4b10eb06286f666efb3a48ef09a3d54e404bc3411153cfc64506cb9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad27ca9b4b10eb06286f666efb3a48ef09a3d54e404bc3411153cfc64506cb9d","first_computed_at":"2026-07-05T11:25:27.902891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:27.902891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QnvHdZFy75QY81sZ1UpQfa+M4Westy8Q8g61GwbvCmdtoJ3PH150xyv8x5CmXdq6nbVOANd1Nql/NuQ3JaFcAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:27.903490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18055","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cfdbb5456da378e6f50f815e635d4f85875617c5225111b621de8dd8b1666c9","sha256:e96085ec9e7b90aab41c6caea20b62c1e7e1c3a714fe458c8da5b61ed15848b1"],"state_sha256":"db71513c7fc31c38ea27ea58132a66f7a1ccd70407a586554c17851889a48b4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VyaGU5WlCdzsQmRjdfRkfDPtlcjjhR7RpYjFlp+bP097nXQbbUuqVgmZ1rODp9NftKlHfewbNdbuJQ5VRy/+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:44:03.678753Z","bundle_sha256":"a8267cec85d64cd6d00f5e1db94c6d60daf18a91251abfac8154be19b04b2485"}}