{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RHZTNIGXWQ34RM5AXHFL3JMJHE","short_pith_number":"pith:RHZTNIGX","canonical_record":{"source":{"id":"2005.07074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-14T15:42:31Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"cfb99ae99c309ee8b384000930874d721b331c135b1627ecd2a252b41dd0991a","abstract_canon_sha256":"c4efd2788e9e9750e48f3053289e0b786c34780ef33e043515ac67063faa2aa7"},"schema_version":"1.0"},"canonical_sha256":"89f336a0d7b437c8b3a0b9cabda589391b178fbcbfeb8067cc7580c73d945ae4","source":{"kind":"arxiv","id":"2005.07074","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.07074","created_at":"2026-07-05T01:49:03Z"},{"alias_kind":"arxiv_version","alias_value":"2005.07074v1","created_at":"2026-07-05T01:49:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07074","created_at":"2026-07-05T01:49:03Z"},{"alias_kind":"pith_short_12","alias_value":"RHZTNIGXWQ34","created_at":"2026-07-05T01:49:03Z"},{"alias_kind":"pith_short_16","alias_value":"RHZTNIGXWQ34RM5A","created_at":"2026-07-05T01:49:03Z"},{"alias_kind":"pith_short_8","alias_value":"RHZTNIGX","created_at":"2026-07-05T01:49:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RHZTNIGXWQ34RM5AXHFL3JMJHE","target":"record","payload":{"canonical_record":{"source":{"id":"2005.07074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-14T15:42:31Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"cfb99ae99c309ee8b384000930874d721b331c135b1627ecd2a252b41dd0991a","abstract_canon_sha256":"c4efd2788e9e9750e48f3053289e0b786c34780ef33e043515ac67063faa2aa7"},"schema_version":"1.0"},"canonical_sha256":"89f336a0d7b437c8b3a0b9cabda589391b178fbcbfeb8067cc7580c73d945ae4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:03.058037Z","signature_b64":"y2fEN+2/lE8k74jSv08Os/0OH9J88s3u0tuxgHFl5CX+9RiskMc08g0ux10/VEMqinxFZtCEXxZRc1R2osi4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89f336a0d7b437c8b3a0b9cabda589391b178fbcbfeb8067cc7580c73d945ae4","last_reissued_at":"2026-07-05T01:49:03.057621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:03.057621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.07074","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":"2026-07-05T01:49:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7WD6vu8vHEdG27G8a7mFNvwJSoJl4+JDrcsB5dP0JP5Fy5r+l+wpHhEX1iwzK9ntLt6SCY2KmXbBNrQexWhIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:13:37.893872Z"},"content_sha256":"ba12763f2f4a7892cf0787166af6feb6a1b5ad2addd86a4679ebc55eefd38c3e","schema_version":"1.0","event_id":"sha256:ba12763f2f4a7892cf0787166af6feb6a1b5ad2addd86a4679ebc55eefd38c3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RHZTNIGXWQ34RM5AXHFL3JMJHE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FaceFilter: Audio-visual speech separation using still images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hong-Goo Kang, Joon Son Chung, Soo-Whan Chung, Soyeon Choe","submitted_at":"2020-05-14T15:42:31Z","abstract_excerpt":"The objective of this paper is to separate a target speaker's speech from a mixture of two speakers using a deep audio-visual speech separation network. Unlike previous works that used lip movement on video clips or pre-enrolled speaker information as an auxiliary conditional feature, we use a single face image of the target speaker. In this task, the conditional feature is obtained from facial appearance in cross-modal biometric task, where audio and visual identity representations are shared in latent space. Learnt identities from facial images enforce the network to isolate matched speakers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07074","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/2005.07074/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":"2026-07-05T01:49:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NcUwQrYNLaetu/gh0OEFgdNyHTz536gjRmuKKSQW2Vsr4rdoZbMb/DKd7ep2axblwf7KTkO4tT2rBjUstZjmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:13:37.894250Z"},"content_sha256":"02713955b10b82699c5809e65059f1ab71d0e0c840b824297fc0a0636ba1fa81","schema_version":"1.0","event_id":"sha256:02713955b10b82699c5809e65059f1ab71d0e0c840b824297fc0a0636ba1fa81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RHZTNIGXWQ34RM5AXHFL3JMJHE/bundle.json","state_url":"https://pith.science/pith/RHZTNIGXWQ34RM5AXHFL3JMJHE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RHZTNIGXWQ34RM5AXHFL3JMJHE/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":"2026-07-05T11:13:37Z","links":{"resolver":"https://pith.science/pith/RHZTNIGXWQ34RM5AXHFL3JMJHE","bundle":"https://pith.science/pith/RHZTNIGXWQ34RM5AXHFL3JMJHE/bundle.json","state":"https://pith.science/pith/RHZTNIGXWQ34RM5AXHFL3JMJHE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RHZTNIGXWQ34RM5AXHFL3JMJHE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RHZTNIGXWQ34RM5AXHFL3JMJHE","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":"c4efd2788e9e9750e48f3053289e0b786c34780ef33e043515ac67063faa2aa7","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-14T15:42:31Z","title_canon_sha256":"cfb99ae99c309ee8b384000930874d721b331c135b1627ecd2a252b41dd0991a"},"schema_version":"1.0","source":{"id":"2005.07074","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.07074","created_at":"2026-07-05T01:49:03Z"},{"alias_kind":"arxiv_version","alias_value":"2005.07074v1","created_at":"2026-07-05T01:49:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07074","created_at":"2026-07-05T01:49:03Z"},{"alias_kind":"pith_short_12","alias_value":"RHZTNIGXWQ34","created_at":"2026-07-05T01:49:03Z"},{"alias_kind":"pith_short_16","alias_value":"RHZTNIGXWQ34RM5A","created_at":"2026-07-05T01:49:03Z"},{"alias_kind":"pith_short_8","alias_value":"RHZTNIGX","created_at":"2026-07-05T01:49:03Z"}],"graph_snapshots":[{"event_id":"sha256:02713955b10b82699c5809e65059f1ab71d0e0c840b824297fc0a0636ba1fa81","target":"graph","created_at":"2026-07-05T01:49:03Z","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/2005.07074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The objective of this paper is to separate a target speaker's speech from a mixture of two speakers using a deep audio-visual speech separation network. Unlike previous works that used lip movement on video clips or pre-enrolled speaker information as an auxiliary conditional feature, we use a single face image of the target speaker. In this task, the conditional feature is obtained from facial appearance in cross-modal biometric task, where audio and visual identity representations are shared in latent space. Learnt identities from facial images enforce the network to isolate matched speakers","authors_text":"Hong-Goo Kang, Joon Son Chung, Soo-Whan Chung, Soyeon Choe","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-14T15:42:31Z","title":"FaceFilter: Audio-visual speech separation using still images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07074","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:ba12763f2f4a7892cf0787166af6feb6a1b5ad2addd86a4679ebc55eefd38c3e","target":"record","created_at":"2026-07-05T01:49:03Z","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":"c4efd2788e9e9750e48f3053289e0b786c34780ef33e043515ac67063faa2aa7","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-14T15:42:31Z","title_canon_sha256":"cfb99ae99c309ee8b384000930874d721b331c135b1627ecd2a252b41dd0991a"},"schema_version":"1.0","source":{"id":"2005.07074","kind":"arxiv","version":1}},"canonical_sha256":"89f336a0d7b437c8b3a0b9cabda589391b178fbcbfeb8067cc7580c73d945ae4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89f336a0d7b437c8b3a0b9cabda589391b178fbcbfeb8067cc7580c73d945ae4","first_computed_at":"2026-07-05T01:49:03.057621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:03.057621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y2fEN+2/lE8k74jSv08Os/0OH9J88s3u0tuxgHFl5CX+9RiskMc08g0ux10/VEMqinxFZtCEXxZRc1R2osi4Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:03.058037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.07074","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba12763f2f4a7892cf0787166af6feb6a1b5ad2addd86a4679ebc55eefd38c3e","sha256:02713955b10b82699c5809e65059f1ab71d0e0c840b824297fc0a0636ba1fa81"],"state_sha256":"cf0347cde2f2e97512290ca0038dafa665758dd05bbb5932c3b2ee2b214628ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OXSKNF72qPgdsgyR7wlSBpndeC4mMokn66XVKPisw7mFRaDAUozCtDcGIew7DG48lOvTIPg8qe9+xvlqNbGODw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T11:13:37.896409Z","bundle_sha256":"d3e7bb32184ab3e37a4597afa7a43c3b0f5529139b1baae84d453ea4feb96e93"}}