{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:N5YNYBXMVTV7DVG7P5Q4BDANN5","short_pith_number":"pith:N5YNYBXM","canonical_record":{"source":{"id":"2309.16569","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-28T16:25:29Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"89fc4cbd0bcce3b5c9f95ea8b7feee3570e87991fae625af072d5529e10a6f6a","abstract_canon_sha256":"8fb8fed3fa70b4094d3830ef07769f356f2cbd65ef305838740bc17ac5ad0233"},"schema_version":"1.0"},"canonical_sha256":"6f70dc06ecacebf1d4df7f61c08c0d6f5399ae2b726f595e7af31084fe40b85c","source":{"kind":"arxiv","id":"2309.16569","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16569","created_at":"2026-07-05T06:55:18Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16569v1","created_at":"2026-07-05T06:55:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16569","created_at":"2026-07-05T06:55:18Z"},{"alias_kind":"pith_short_12","alias_value":"N5YNYBXMVTV7","created_at":"2026-07-05T06:55:18Z"},{"alias_kind":"pith_short_16","alias_value":"N5YNYBXMVTV7DVG7","created_at":"2026-07-05T06:55:18Z"},{"alias_kind":"pith_short_8","alias_value":"N5YNYBXM","created_at":"2026-07-05T06:55:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:N5YNYBXMVTV7DVG7P5Q4BDANN5","target":"record","payload":{"canonical_record":{"source":{"id":"2309.16569","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-28T16:25:29Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"89fc4cbd0bcce3b5c9f95ea8b7feee3570e87991fae625af072d5529e10a6f6a","abstract_canon_sha256":"8fb8fed3fa70b4094d3830ef07769f356f2cbd65ef305838740bc17ac5ad0233"},"schema_version":"1.0"},"canonical_sha256":"6f70dc06ecacebf1d4df7f61c08c0d6f5399ae2b726f595e7af31084fe40b85c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:18.417880Z","signature_b64":"YDMM07wCmhDHxBYYAAB91QcG5HQ9t2oArIu2CVGKpSfznIVA6+MUuFRmuX20FnGpwQlxacRknwipgzXA+qQADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f70dc06ecacebf1d4df7f61c08c0d6f5399ae2b726f595e7af31084fe40b85c","last_reissued_at":"2026-07-05T06:55:18.417391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:18.417391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.16569","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":"2026-07-05T06:55:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xnVs74WuwHbrl/WLVw1SmH4B+effQP8GIWhwFGK1m+1soiXVpNiiOXw9TribCGj7tpDuVJCoWvbcGZd73vYEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:14:17.606518Z"},"content_sha256":"5e22aec734114e1cce91f2481741fdfa597eacb0f1e72b015f6feec85f468597","schema_version":"1.0","event_id":"sha256:5e22aec734114e1cce91f2481741fdfa597eacb0f1e72b015f6feec85f468597"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:N5YNYBXMVTV7DVG7P5Q4BDANN5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio-Visual Speaker Verification via Joint Cross-Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jahangir Alam, R. Gnana Praveen","submitted_at":"2023-09-28T16:25:29Z","abstract_excerpt":"Speaker verification has been widely explored using speech signals, which has shown significant improvement using deep models. Recently, there has been a surge in exploring faces and voices as they can offer more complementary and comprehensive information than relying only on a single modality of speech signals. Though current methods in the literature on the fusion of faces and voices have shown improvement over that of individual face or voice modalities, the potential of audio-visual fusion is not fully explored for speaker verification. Most of the existing methods based on audio-visual f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16569","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/2309.16569/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":"2026-07-05T06:55:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QGGCSDK7h7KvNkhhxCKBB6AI+w2gXU+yK1h33DY1HQU3jIbeMDqxOoHYibRhclvf2/ryDgfVAjq0OKoM4urBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:14:17.607245Z"},"content_sha256":"3b0acd7fc70c5000bbced79fbd238a48295ca4a0921b3d37a1578c42f5b47261","schema_version":"1.0","event_id":"sha256:3b0acd7fc70c5000bbced79fbd238a48295ca4a0921b3d37a1578c42f5b47261"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N5YNYBXMVTV7DVG7P5Q4BDANN5/bundle.json","state_url":"https://pith.science/pith/N5YNYBXMVTV7DVG7P5Q4BDANN5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N5YNYBXMVTV7DVG7P5Q4BDANN5/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":"2026-08-07T17:14:17Z","links":{"resolver":"https://pith.science/pith/N5YNYBXMVTV7DVG7P5Q4BDANN5","bundle":"https://pith.science/pith/N5YNYBXMVTV7DVG7P5Q4BDANN5/bundle.json","state":"https://pith.science/pith/N5YNYBXMVTV7DVG7P5Q4BDANN5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N5YNYBXMVTV7DVG7P5Q4BDANN5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:N5YNYBXMVTV7DVG7P5Q4BDANN5","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":"8fb8fed3fa70b4094d3830ef07769f356f2cbd65ef305838740bc17ac5ad0233","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-28T16:25:29Z","title_canon_sha256":"89fc4cbd0bcce3b5c9f95ea8b7feee3570e87991fae625af072d5529e10a6f6a"},"schema_version":"1.0","source":{"id":"2309.16569","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16569","created_at":"2026-07-05T06:55:18Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16569v1","created_at":"2026-07-05T06:55:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16569","created_at":"2026-07-05T06:55:18Z"},{"alias_kind":"pith_short_12","alias_value":"N5YNYBXMVTV7","created_at":"2026-07-05T06:55:18Z"},{"alias_kind":"pith_short_16","alias_value":"N5YNYBXMVTV7DVG7","created_at":"2026-07-05T06:55:18Z"},{"alias_kind":"pith_short_8","alias_value":"N5YNYBXM","created_at":"2026-07-05T06:55:18Z"}],"graph_snapshots":[{"event_id":"sha256:3b0acd7fc70c5000bbced79fbd238a48295ca4a0921b3d37a1578c42f5b47261","target":"graph","created_at":"2026-07-05T06:55:18Z","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/2309.16569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speaker verification has been widely explored using speech signals, which has shown significant improvement using deep models. Recently, there has been a surge in exploring faces and voices as they can offer more complementary and comprehensive information than relying only on a single modality of speech signals. Though current methods in the literature on the fusion of faces and voices have shown improvement over that of individual face or voice modalities, the potential of audio-visual fusion is not fully explored for speaker verification. Most of the existing methods based on audio-visual f","authors_text":"Jahangir Alam, R. Gnana Praveen","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-28T16:25:29Z","title":"Audio-Visual Speaker Verification via Joint Cross-Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16569","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":"sha256:5e22aec734114e1cce91f2481741fdfa597eacb0f1e72b015f6feec85f468597","target":"record","created_at":"2026-07-05T06:55:18Z","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":"8fb8fed3fa70b4094d3830ef07769f356f2cbd65ef305838740bc17ac5ad0233","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-28T16:25:29Z","title_canon_sha256":"89fc4cbd0bcce3b5c9f95ea8b7feee3570e87991fae625af072d5529e10a6f6a"},"schema_version":"1.0","source":{"id":"2309.16569","kind":"arxiv","version":1}},"canonical_sha256":"6f70dc06ecacebf1d4df7f61c08c0d6f5399ae2b726f595e7af31084fe40b85c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f70dc06ecacebf1d4df7f61c08c0d6f5399ae2b726f595e7af31084fe40b85c","first_computed_at":"2026-07-05T06:55:18.417391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:18.417391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YDMM07wCmhDHxBYYAAB91QcG5HQ9t2oArIu2CVGKpSfznIVA6+MUuFRmuX20FnGpwQlxacRknwipgzXA+qQADA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:18.417880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.16569","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e22aec734114e1cce91f2481741fdfa597eacb0f1e72b015f6feec85f468597","sha256:3b0acd7fc70c5000bbced79fbd238a48295ca4a0921b3d37a1578c42f5b47261"],"state_sha256":"16f2ee37d599ab47981a61632083bd6d536f7a07e9c721aff7a7d8d1fc1d8d1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8t4m7zhHh3YQixHInhYprvQnub7QoWyT4oADWdZM85iTWwVrJwLWv9wCs1FtHcyjUnA+7oibJWxumU7CkPIVDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:14:17.613540Z","bundle_sha256":"6315300889f85797543ab7c3f4a6eeac8d493fbe253faf77af882dbbdafafb96"}}