{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FSQBATQUWZCE7TAKEBVO3VLI7O","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":"1897462845f2ac24be450b1dd5469de7ef842bb68f5371680861df1e779ffb0c","cross_cats_sorted":["cs.SD","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-30T19:31:03Z","title_canon_sha256":"b11a722bc6b5f064e8fe705ecc2a439b996447b7b20592edd7f8a3b1aedba615"},"schema_version":"1.0","source":{"id":"2012.00063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.00063","created_at":"2026-07-05T01:55:31Z"},{"alias_kind":"arxiv_version","alias_value":"2012.00063v1","created_at":"2026-07-05T01:55:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.00063","created_at":"2026-07-05T01:55:31Z"},{"alias_kind":"pith_short_12","alias_value":"FSQBATQUWZCE","created_at":"2026-07-05T01:55:31Z"},{"alias_kind":"pith_short_16","alias_value":"FSQBATQUWZCE7TAK","created_at":"2026-07-05T01:55:31Z"},{"alias_kind":"pith_short_8","alias_value":"FSQBATQU","created_at":"2026-07-05T01:55:31Z"}],"graph_snapshots":[{"event_id":"sha256:f93311e996c98bc8ac8cb7b2cfff339e8df99b38b31852114bd86f2e34a27715","target":"graph","created_at":"2026-07-05T01:55:31Z","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/2012.00063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing machine learning algorithms to understand person-to-person engagement can result in natural user experiences for communal devices such as Amazon Alexa. Among other cues such as voice activity and gaze, a person's audio-visual expression that includes tone of the voice and facial expression serves as an implicit signal of engagement between parties in a dialog. This study investigates deep-learning algorithms for audio-visual detection of user's expression. We first implement an audio-visual baseline model with recurrent layers that shows competitive results compared to current state","authors_text":"Shiva Sundaram, Srinivas Parthasarathy","cross_cats":["cs.SD","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-30T19:31:03Z","title":"Detecting expressions with multimodal transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.00063","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":"sha256:476fe6476802f8eb8aeafda5b993755e6a6471ff1aa1a04715decd3c4fb0735a","target":"record","created_at":"2026-07-05T01:55:31Z","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":"1897462845f2ac24be450b1dd5469de7ef842bb68f5371680861df1e779ffb0c","cross_cats_sorted":["cs.SD","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-30T19:31:03Z","title_canon_sha256":"b11a722bc6b5f064e8fe705ecc2a439b996447b7b20592edd7f8a3b1aedba615"},"schema_version":"1.0","source":{"id":"2012.00063","kind":"arxiv","version":1}},"canonical_sha256":"2ca0104e14b6444fcc0a206aedd568fbbafb5ca6159b9c94c2aa2af6d3a60872","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ca0104e14b6444fcc0a206aedd568fbbafb5ca6159b9c94c2aa2af6d3a60872","first_computed_at":"2026-07-05T01:55:31.904792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:55:31.904792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aTiL+UyXxn4ruDDoW+KsEYE49vLDPiljTEWi/IAojyQFYC5qXqcYmXXGv8w2HPjDuDOQStv0QECEquJiX4e5BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:55:31.905207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.00063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:476fe6476802f8eb8aeafda5b993755e6a6471ff1aa1a04715decd3c4fb0735a","sha256:f93311e996c98bc8ac8cb7b2cfff339e8df99b38b31852114bd86f2e34a27715"],"state_sha256":"26872a4d6417073c9224f0dd860b537e261271b727427843e9808fafc81c244a"}