{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6ZVHSXTWLKW7HVOC36XKP3KS7H","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":"609b717db4baf2f40908474654e8afd934fbf264b0a20ca7d58305148c3a16e4","cross_cats_sorted":["cs.SD","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-14T10:30:34Z","title_canon_sha256":"fb418d5b334102f6de0cf10b2de9356e31c8dc9b64e52aa008001d85daab2ab1"},"schema_version":"1.0","source":{"id":"2107.06592","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.06592","created_at":"2026-07-05T03:00:34Z"},{"alias_kind":"arxiv_version","alias_value":"2107.06592v2","created_at":"2026-07-05T03:00:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06592","created_at":"2026-07-05T03:00:34Z"},{"alias_kind":"pith_short_12","alias_value":"6ZVHSXTWLKW7","created_at":"2026-07-05T03:00:34Z"},{"alias_kind":"pith_short_16","alias_value":"6ZVHSXTWLKW7HVOC","created_at":"2026-07-05T03:00:34Z"},{"alias_kind":"pith_short_8","alias_value":"6ZVHSXTW","created_at":"2026-07-05T03:00:34Z"}],"graph_snapshots":[{"event_id":"sha256:37e117d36e20d26906a4d6596b1fc204d482941f5a833e7d542eaaa0e57a3f30","target":"graph","created_at":"2026-07-05T03:00:34Z","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/2107.06592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Active speaker detection (ASD) seeks to detect who is speaking in a visual scene of one or more speakers. The successful ASD depends on accurate interpretation of short-term and long-term audio and visual information, as well as audio-visual interaction. Unlike the prior work where systems make decision instantaneously using short-term features, we propose a novel framework, named TalkNet, that makes decision by taking both short-term and long-term features into consideration. TalkNet consists of audio and visual temporal encoders for feature representation, audio-visual cross-attention mechan","authors_text":"Haizhou Li, Mike Zheng Shou, Rohan Kumar Das, Ruijie Tao, Xinyuan Qian, Zexu Pan","cross_cats":["cs.SD","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-14T10:30:34Z","title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06592","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":"sha256:048ec00158124da47941ed6b76f9c985c48606e2fb5674237a461e6935f7954e","target":"record","created_at":"2026-07-05T03:00:34Z","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":"609b717db4baf2f40908474654e8afd934fbf264b0a20ca7d58305148c3a16e4","cross_cats_sorted":["cs.SD","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-14T10:30:34Z","title_canon_sha256":"fb418d5b334102f6de0cf10b2de9356e31c8dc9b64e52aa008001d85daab2ab1"},"schema_version":"1.0","source":{"id":"2107.06592","kind":"arxiv","version":2}},"canonical_sha256":"f66a795e765aadf3d5c2dfaea7ed52f9c946ca1a80d7a45bc40dead0211d1f8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f66a795e765aadf3d5c2dfaea7ed52f9c946ca1a80d7a45bc40dead0211d1f8c","first_computed_at":"2026-07-05T03:00:34.742015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:00:34.742015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ngLlhipDqVyh3ucrevQ2quAjnXiSPTdbIWV2ocR62vEVcahba+RO9qP/qW42bZVNmQyFq81iTcmvX+OlYoHDCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:00:34.742426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.06592","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:048ec00158124da47941ed6b76f9c985c48606e2fb5674237a461e6935f7954e","sha256:37e117d36e20d26906a4d6596b1fc204d482941f5a833e7d542eaaa0e57a3f30"],"state_sha256":"6718a793f7389e2a0fb62d06bf2fd5f0059b75f4988617895fa010c1d01cccfa"}