{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Z3A4K7VYIBK722UBMCDN4MZ3F3","short_pith_number":"pith:Z3A4K7VY","canonical_record":{"source":{"id":"2203.02216","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-04T09:53:19Z","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"title_canon_sha256":"b12025da83040a9e2ec1ff160f3e2aeab5bc0b414b4818f24ed237213d8aabe0","abstract_canon_sha256":"b5290310683a954e044a3bef15152aca0a34bcaa77bf8d2e9c4eed5a83db8857"},"schema_version":"1.0"},"canonical_sha256":"cec1c57eb84055fd6a816086de333b2efb969fdbaee0dff9558a01fb77943069","source":{"kind":"arxiv","id":"2203.02216","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02216","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02216v2","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02216","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"Z3A4K7VYIBK7","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"pith_short_16","alias_value":"Z3A4K7VYIBK722UB","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"pith_short_8","alias_value":"Z3A4K7VY","created_at":"2026-07-05T04:38:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Z3A4K7VYIBK722UBMCDN4MZ3F3","target":"record","payload":{"canonical_record":{"source":{"id":"2203.02216","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-04T09:53:19Z","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"title_canon_sha256":"b12025da83040a9e2ec1ff160f3e2aeab5bc0b414b4818f24ed237213d8aabe0","abstract_canon_sha256":"b5290310683a954e044a3bef15152aca0a34bcaa77bf8d2e9c4eed5a83db8857"},"schema_version":"1.0"},"canonical_sha256":"cec1c57eb84055fd6a816086de333b2efb969fdbaee0dff9558a01fb77943069","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:14.007558Z","signature_b64":"bInQo+Mam9mgIYWWYkevBC86Bg8MBPBV7zcJlozFqARonePwEUHLYYs4NabyQMnqmLmqmTNuFIg6AwbM0RN9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cec1c57eb84055fd6a816086de333b2efb969fdbaee0dff9558a01fb77943069","last_reissued_at":"2026-07-05T04:38:14.007144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:14.007144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.02216","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GMyJSmVvMj/3Q5QI8PysHpU0DzKQyoR9QFYbfqEzJQPr+zNAEfWb7uBcfMTiwR74FwqHf73sfCFgxwl+fsEoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T21:46:14.119310Z"},"content_sha256":"51ebf1b461d1e4ef62690b504543aad2e0d0f890bc7441f2f5da85382e506e76","schema_version":"1.0","event_id":"sha256:51ebf1b461d1e4ef62690b504543aad2e0d0f890bc7441f2f5da85382e506e76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Z3A4K7VYIBK722UBMCDN4MZ3F3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Look\\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Junwen Xiong, Lei Xie, Peng Zhang, Wei Huang, Yufei zha, Yu Zhou","submitted_at":"2022-03-04T09:53:19Z","abstract_excerpt":"Active speaker detection and speech enhancement have become two increasingly attractive topics in audio-visual scenario understanding. According to their respective characteristics, the scheme of independently designed architecture has been widely used in correspondence to each single task. This may lead to the representation learned by the model being task-specific, and inevitably result in the lack of generalization ability of the feature based on multi-modal modeling. More recent studies have shown that establishing cross-modal relationship between auditory and visual stream is a promising "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02216","kind":"arxiv","version":2},"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/2203.02216/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":"2026-07-05T04:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P5Npf0lrsrl6+RvDROFQGHpThQIcYhr+wX7Wj8swSdhxKGksQDHx12ai/BP391tti4a7roA88jcTR7hcuwfGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T21:46:14.119692Z"},"content_sha256":"1550b901498070d7491778b88736c9c2c084e5a1ce56c1abf72a910cd5727b25","schema_version":"1.0","event_id":"sha256:1550b901498070d7491778b88736c9c2c084e5a1ce56c1abf72a910cd5727b25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z3A4K7VYIBK722UBMCDN4MZ3F3/bundle.json","state_url":"https://pith.science/pith/Z3A4K7VYIBK722UBMCDN4MZ3F3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z3A4K7VYIBK722UBMCDN4MZ3F3/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":"2026-07-15T21:46:14Z","links":{"resolver":"https://pith.science/pith/Z3A4K7VYIBK722UBMCDN4MZ3F3","bundle":"https://pith.science/pith/Z3A4K7VYIBK722UBMCDN4MZ3F3/bundle.json","state":"https://pith.science/pith/Z3A4K7VYIBK722UBMCDN4MZ3F3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z3A4K7VYIBK722UBMCDN4MZ3F3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Z3A4K7VYIBK722UBMCDN4MZ3F3","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":"b5290310683a954e044a3bef15152aca0a34bcaa77bf8d2e9c4eed5a83db8857","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-04T09:53:19Z","title_canon_sha256":"b12025da83040a9e2ec1ff160f3e2aeab5bc0b414b4818f24ed237213d8aabe0"},"schema_version":"1.0","source":{"id":"2203.02216","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02216","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02216v2","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02216","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"Z3A4K7VYIBK7","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"pith_short_16","alias_value":"Z3A4K7VYIBK722UB","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"pith_short_8","alias_value":"Z3A4K7VY","created_at":"2026-07-05T04:38:14Z"}],"graph_snapshots":[{"event_id":"sha256:1550b901498070d7491778b88736c9c2c084e5a1ce56c1abf72a910cd5727b25","target":"graph","created_at":"2026-07-05T04:38:14Z","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/2203.02216/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Active speaker detection and speech enhancement have become two increasingly attractive topics in audio-visual scenario understanding. According to their respective characteristics, the scheme of independently designed architecture has been widely used in correspondence to each single task. This may lead to the representation learned by the model being task-specific, and inevitably result in the lack of generalization ability of the feature based on multi-modal modeling. More recent studies have shown that establishing cross-modal relationship between auditory and visual stream is a promising ","authors_text":"Junwen Xiong, Lei Xie, Peng Zhang, Wei Huang, Yufei zha, Yu Zhou","cross_cats":["cs.AI","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-04T09:53:19Z","title":"Look\\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02216","kind":"arxiv","version":2},"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":"sha256:51ebf1b461d1e4ef62690b504543aad2e0d0f890bc7441f2f5da85382e506e76","target":"record","created_at":"2026-07-05T04:38:14Z","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":"b5290310683a954e044a3bef15152aca0a34bcaa77bf8d2e9c4eed5a83db8857","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-04T09:53:19Z","title_canon_sha256":"b12025da83040a9e2ec1ff160f3e2aeab5bc0b414b4818f24ed237213d8aabe0"},"schema_version":"1.0","source":{"id":"2203.02216","kind":"arxiv","version":2}},"canonical_sha256":"cec1c57eb84055fd6a816086de333b2efb969fdbaee0dff9558a01fb77943069","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cec1c57eb84055fd6a816086de333b2efb969fdbaee0dff9558a01fb77943069","first_computed_at":"2026-07-05T04:38:14.007144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:38:14.007144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bInQo+Mam9mgIYWWYkevBC86Bg8MBPBV7zcJlozFqARonePwEUHLYYs4NabyQMnqmLmqmTNuFIg6AwbM0RN9Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:38:14.007558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.02216","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51ebf1b461d1e4ef62690b504543aad2e0d0f890bc7441f2f5da85382e506e76","sha256:1550b901498070d7491778b88736c9c2c084e5a1ce56c1abf72a910cd5727b25"],"state_sha256":"39efc125efed3cce86fa16dfaa841113b505089f4027a3397aa643e452c4d106"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oCmUidkkdXpVvNb8vabG8HjheBxNqQZAgcEzorkgKVUWOtqiK2r4vGssNh30eWpDQR8RUt+6G2ltiTEgm6bqCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-15T21:46:14.122249Z","bundle_sha256":"c4060824d1ed52e9dbdaf53af415d2d94a60e82296443905cdaa3aab0318d797"}}