{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4BO2FGV2MGK7PUO3Y24VZLV2LH","short_pith_number":"pith:4BO2FGV2","canonical_record":{"source":{"id":"2008.03894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-10T04:16:20Z","cross_cats_sorted":[],"title_canon_sha256":"06ae3f8f96fc45c650ebc812ee7f008467c14b78b44993ea7be565aaad0acb71","abstract_canon_sha256":"cb3f8d2c4c8961e2363f2ed077c39efad5a116fc9d269dbd00aa1fc15577eac9"},"schema_version":"1.0"},"canonical_sha256":"e05da29aba6195f7d1dbc6b95caeba59edbf8748514947c360b2985c9de9b016","source":{"kind":"arxiv","id":"2008.03894","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.03894","created_at":"2026-07-05T01:25:57Z"},{"alias_kind":"arxiv_version","alias_value":"2008.03894v1","created_at":"2026-07-05T01:25:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03894","created_at":"2026-07-05T01:25:57Z"},{"alias_kind":"pith_short_12","alias_value":"4BO2FGV2MGK7","created_at":"2026-07-05T01:25:57Z"},{"alias_kind":"pith_short_16","alias_value":"4BO2FGV2MGK7PUO3","created_at":"2026-07-05T01:25:57Z"},{"alias_kind":"pith_short_8","alias_value":"4BO2FGV2","created_at":"2026-07-05T01:25:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4BO2FGV2MGK7PUO3Y24VZLV2LH","target":"record","payload":{"canonical_record":{"source":{"id":"2008.03894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-10T04:16:20Z","cross_cats_sorted":[],"title_canon_sha256":"06ae3f8f96fc45c650ebc812ee7f008467c14b78b44993ea7be565aaad0acb71","abstract_canon_sha256":"cb3f8d2c4c8961e2363f2ed077c39efad5a116fc9d269dbd00aa1fc15577eac9"},"schema_version":"1.0"},"canonical_sha256":"e05da29aba6195f7d1dbc6b95caeba59edbf8748514947c360b2985c9de9b016","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:57.605137Z","signature_b64":"Tsg5zDYD/30XjgtRbDuF7PZJ/RlgwQW6l8m1h6ZDddbFEwrien3BIBy75fEGe1Er03nJLNRxVvAGxFGie5sWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e05da29aba6195f7d1dbc6b95caeba59edbf8748514947c360b2985c9de9b016","last_reissued_at":"2026-07-05T01:25:57.604732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:57.604732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.03894","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":"2026-07-05T01:25:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XMn/OcodY4oxXTYVyZlpyhXQWD8QAcryQ/I8o+GniOWe+rNfxyubkencvL/YaOXJkh0lK8Q1/YDRUD2HiC8FCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:16:08.775205Z"},"content_sha256":"bd8d4cf40cde388f378569bbeef2942b06ce5e60254485d3b0ea6d6bb3060714","schema_version":"1.0","event_id":"sha256:bd8d4cf40cde388f378569bbeef2942b06ce5e60254485d3b0ea6d6bb3060714"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4BO2FGV2MGK7PUO3Y24VZLV2LH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio-visual Speaker Recognition with a Cross-modal Discriminative Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Rohan Kumar Das, Ruijie Tao","submitted_at":"2020-08-10T04:16:20Z","abstract_excerpt":"Audio-visual speaker recognition is one of the tasks in the recent 2019 NIST speaker recognition evaluation (SRE). Studies in neuroscience and computer science all point to the fact that vision and auditory neural signals interact in the cognitive process. This motivated us to study a cross-modal network, namely voice-face discriminative network (VFNet) that establishes the general relation between human voice and face. Experiments show that VFNet provides additional speaker discriminative information. With VFNet, we achieve 16.54% equal error rate relative reduction over the score level fusio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03894","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/2008.03894/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":"2026-07-05T01:25:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Sr4WEHNzNJ0Cma/ZUgTD5WgeRZJy4ADWpl/2AuvY3dNlUdjLB6dFMcD1YcDQbLy7+Y2bkYTRZp/yvKCYXfxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:16:08.775708Z"},"content_sha256":"03391b7b3393d2664dcc6d1845a509fabc28706b9c3617921e14ac89cd0c1b32","schema_version":"1.0","event_id":"sha256:03391b7b3393d2664dcc6d1845a509fabc28706b9c3617921e14ac89cd0c1b32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4BO2FGV2MGK7PUO3Y24VZLV2LH/bundle.json","state_url":"https://pith.science/pith/4BO2FGV2MGK7PUO3Y24VZLV2LH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4BO2FGV2MGK7PUO3Y24VZLV2LH/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":"2026-08-07T05:16:08Z","links":{"resolver":"https://pith.science/pith/4BO2FGV2MGK7PUO3Y24VZLV2LH","bundle":"https://pith.science/pith/4BO2FGV2MGK7PUO3Y24VZLV2LH/bundle.json","state":"https://pith.science/pith/4BO2FGV2MGK7PUO3Y24VZLV2LH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4BO2FGV2MGK7PUO3Y24VZLV2LH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4BO2FGV2MGK7PUO3Y24VZLV2LH","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":"cb3f8d2c4c8961e2363f2ed077c39efad5a116fc9d269dbd00aa1fc15577eac9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-10T04:16:20Z","title_canon_sha256":"06ae3f8f96fc45c650ebc812ee7f008467c14b78b44993ea7be565aaad0acb71"},"schema_version":"1.0","source":{"id":"2008.03894","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.03894","created_at":"2026-07-05T01:25:57Z"},{"alias_kind":"arxiv_version","alias_value":"2008.03894v1","created_at":"2026-07-05T01:25:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03894","created_at":"2026-07-05T01:25:57Z"},{"alias_kind":"pith_short_12","alias_value":"4BO2FGV2MGK7","created_at":"2026-07-05T01:25:57Z"},{"alias_kind":"pith_short_16","alias_value":"4BO2FGV2MGK7PUO3","created_at":"2026-07-05T01:25:57Z"},{"alias_kind":"pith_short_8","alias_value":"4BO2FGV2","created_at":"2026-07-05T01:25:57Z"}],"graph_snapshots":[{"event_id":"sha256:03391b7b3393d2664dcc6d1845a509fabc28706b9c3617921e14ac89cd0c1b32","target":"graph","created_at":"2026-07-05T01:25:57Z","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/2008.03894/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual speaker recognition is one of the tasks in the recent 2019 NIST speaker recognition evaluation (SRE). Studies in neuroscience and computer science all point to the fact that vision and auditory neural signals interact in the cognitive process. This motivated us to study a cross-modal network, namely voice-face discriminative network (VFNet) that establishes the general relation between human voice and face. Experiments show that VFNet provides additional speaker discriminative information. With VFNet, we achieve 16.54% equal error rate relative reduction over the score level fusio","authors_text":"Haizhou Li, Rohan Kumar Das, Ruijie Tao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-10T04:16:20Z","title":"Audio-visual Speaker Recognition with a Cross-modal Discriminative Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03894","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:bd8d4cf40cde388f378569bbeef2942b06ce5e60254485d3b0ea6d6bb3060714","target":"record","created_at":"2026-07-05T01:25:57Z","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":"cb3f8d2c4c8961e2363f2ed077c39efad5a116fc9d269dbd00aa1fc15577eac9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-10T04:16:20Z","title_canon_sha256":"06ae3f8f96fc45c650ebc812ee7f008467c14b78b44993ea7be565aaad0acb71"},"schema_version":"1.0","source":{"id":"2008.03894","kind":"arxiv","version":1}},"canonical_sha256":"e05da29aba6195f7d1dbc6b95caeba59edbf8748514947c360b2985c9de9b016","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e05da29aba6195f7d1dbc6b95caeba59edbf8748514947c360b2985c9de9b016","first_computed_at":"2026-07-05T01:25:57.604732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:25:57.604732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tsg5zDYD/30XjgtRbDuF7PZJ/RlgwQW6l8m1h6ZDddbFEwrien3BIBy75fEGe1Er03nJLNRxVvAGxFGie5sWAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:25:57.605137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.03894","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd8d4cf40cde388f378569bbeef2942b06ce5e60254485d3b0ea6d6bb3060714","sha256:03391b7b3393d2664dcc6d1845a509fabc28706b9c3617921e14ac89cd0c1b32"],"state_sha256":"294f40d1fcec470ace4af6cf307ad8cdc85a608a63abf0f60220c25afa25bc38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zxaAU4XnZSxSollbNNoziMHTKjL/IvRsh5XqfUAfJFmRVGoNKW7Rzr2gSyoVRSB2834cyyKov332gczlHfEBBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:16:08.781247Z","bundle_sha256":"7155fae3ea6dd364f73bd7c37bb4831f80aa3ebab606a70040b517c513116f2d"}}