{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:46FHERGSDTYPMEE3U27UQH6CLK","short_pith_number":"pith:46FHERGS","canonical_record":{"source":{"id":"1811.10813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T04:58:10Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f32365eb075b41178492aef19926779bee33764ccb236b24043f7b0a4dbf47fb","abstract_canon_sha256":"5cd27c3470a4c5bf3ef10382f8ee272044d66f96fbe3a62ece1e3b04af763bb5"},"schema_version":"1.0"},"canonical_sha256":"e78a7244d21cf0f6109ba6bf481fc25a8a1aab895e4ab542ae7ae757c2ab6528","source":{"kind":"arxiv","id":"1811.10813","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10813","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10813v1","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10813","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"pith_short_12","alias_value":"46FHERGSDTYP","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"46FHERGSDTYPMEE3","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"46FHERGS","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:46FHERGSDTYPMEE3U27UQH6CLK","target":"record","payload":{"canonical_record":{"source":{"id":"1811.10813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T04:58:10Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f32365eb075b41178492aef19926779bee33764ccb236b24043f7b0a4dbf47fb","abstract_canon_sha256":"5cd27c3470a4c5bf3ef10382f8ee272044d66f96fbe3a62ece1e3b04af763bb5"},"schema_version":"1.0"},"canonical_sha256":"e78a7244d21cf0f6109ba6bf481fc25a8a1aab895e4ab542ae7ae757c2ab6528","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:47.485508Z","signature_b64":"f9c3p3UqPxif9UugBKhGIFahQvlLdlzMBrcJhxyhOIClo3O9/hNW5mBFfciajbCHhxI0AuGtkOyi5NyK7FT/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e78a7244d21cf0f6109ba6bf481fc25a8a1aab895e4ab542ae7ae757c2ab6528","last_reissued_at":"2026-05-17T23:59:47.485025Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:47.485025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.10813","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":"2026-05-17T23:59:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LnaLsmz8VADGDB3f/mhX5ChhH8XwOkVmPw4hfMmLasCdFgKVeW5BsMc24oVcxvTpvvLO+g+EZRQ8OHwIUeHdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T12:13:54.591462Z"},"content_sha256":"ddbad5d1d19b6764e8b968c73d19b854a68a7cecc144dea59dae3260f5ae957f","schema_version":"1.0","event_id":"sha256:ddbad5d1d19b6764e8b968c73d19b854a68a7cecc144dea59dae3260f5ae957f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:46FHERGSDTYPMEE3U27UQH6CLK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Noise-tolerant Audio-visual Online Person Verification using an Attention-based Neural Network Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CV","authors_text":"James Glass, Suwon Shon, Tae-Hyun Oh","submitted_at":"2018-11-27T04:58:10Z","abstract_excerpt":"In this paper, we present a multi-modal online person verification system using both speech and visual signals. Inspired by neuroscientific findings on the association of voice and face, we propose an attention-based end-to-end neural network that learns multi-sensory associations for the task of person verification. The attention mechanism in our proposed network learns to conditionally select a salient modality between speech and facial representations that provides a balance between complementary inputs. By virtue of this capability, the network is robust to missing or corrupted data from e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10813","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":""},"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":"2026-05-17T23:59:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gdEwCFefQcoD5S0nIi+qcN2Uxen3FROnBWyHx7s3aepbl6jfgKFbg/ydXo2kO1vvbN05iTbLKdkv2AMf17kgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T12:13:54.591800Z"},"content_sha256":"35b00166d00d87662147a6d3fe1dc02639afc948f800fb1c9f3da412871751a0","schema_version":"1.0","event_id":"sha256:35b00166d00d87662147a6d3fe1dc02639afc948f800fb1c9f3da412871751a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/46FHERGSDTYPMEE3U27UQH6CLK/bundle.json","state_url":"https://pith.science/pith/46FHERGSDTYPMEE3U27UQH6CLK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/46FHERGSDTYPMEE3U27UQH6CLK/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":"2026-06-08T12:13:54Z","links":{"resolver":"https://pith.science/pith/46FHERGSDTYPMEE3U27UQH6CLK","bundle":"https://pith.science/pith/46FHERGSDTYPMEE3U27UQH6CLK/bundle.json","state":"https://pith.science/pith/46FHERGSDTYPMEE3U27UQH6CLK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/46FHERGSDTYPMEE3U27UQH6CLK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:46FHERGSDTYPMEE3U27UQH6CLK","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":"5cd27c3470a4c5bf3ef10382f8ee272044d66f96fbe3a62ece1e3b04af763bb5","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T04:58:10Z","title_canon_sha256":"f32365eb075b41178492aef19926779bee33764ccb236b24043f7b0a4dbf47fb"},"schema_version":"1.0","source":{"id":"1811.10813","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10813","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10813v1","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10813","created_at":"2026-05-17T23:59:47Z"},{"alias_kind":"pith_short_12","alias_value":"46FHERGSDTYP","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"46FHERGSDTYPMEE3","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"46FHERGS","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:35b00166d00d87662147a6d3fe1dc02639afc948f800fb1c9f3da412871751a0","target":"graph","created_at":"2026-05-17T23:59:47Z","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"},"paper":{"abstract_excerpt":"In this paper, we present a multi-modal online person verification system using both speech and visual signals. Inspired by neuroscientific findings on the association of voice and face, we propose an attention-based end-to-end neural network that learns multi-sensory associations for the task of person verification. The attention mechanism in our proposed network learns to conditionally select a salient modality between speech and facial representations that provides a balance between complementary inputs. By virtue of this capability, the network is robust to missing or corrupted data from e","authors_text":"James Glass, Suwon Shon, Tae-Hyun Oh","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T04:58:10Z","title":"Noise-tolerant Audio-visual Online Person Verification using an Attention-based Neural Network Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10813","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:ddbad5d1d19b6764e8b968c73d19b854a68a7cecc144dea59dae3260f5ae957f","target":"record","created_at":"2026-05-17T23:59:47Z","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":"5cd27c3470a4c5bf3ef10382f8ee272044d66f96fbe3a62ece1e3b04af763bb5","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-27T04:58:10Z","title_canon_sha256":"f32365eb075b41178492aef19926779bee33764ccb236b24043f7b0a4dbf47fb"},"schema_version":"1.0","source":{"id":"1811.10813","kind":"arxiv","version":1}},"canonical_sha256":"e78a7244d21cf0f6109ba6bf481fc25a8a1aab895e4ab542ae7ae757c2ab6528","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e78a7244d21cf0f6109ba6bf481fc25a8a1aab895e4ab542ae7ae757c2ab6528","first_computed_at":"2026-05-17T23:59:47.485025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:47.485025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f9c3p3UqPxif9UugBKhGIFahQvlLdlzMBrcJhxyhOIClo3O9/hNW5mBFfciajbCHhxI0AuGtkOyi5NyK7FT/Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:47.485508Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.10813","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddbad5d1d19b6764e8b968c73d19b854a68a7cecc144dea59dae3260f5ae957f","sha256:35b00166d00d87662147a6d3fe1dc02639afc948f800fb1c9f3da412871751a0"],"state_sha256":"4f7d29d1394445e14dbd753e2dd74e2adb4b31bd34fd0393d1597426d3e305e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uos7GI2ih1Ie8PPGUBvYQjt0ivcAw/fpoKKqRx5kxdT2PvvpD4+eS2M0yxvTCI1Cmb2rbixDXzUIzrwg5kWPAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T12:13:54.593580Z","bundle_sha256":"86002b9aa110dbc3f24c8e1ad2dbdaa2a5281904665872d5013a90d065fdfbb1"}}