{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XBTLWXKQB4SX5GET6UD3HTENS6","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":"dff3dfbb00e4484b18b52f5ae642b1e4d0c930f08c0a32253252192a63fe24be","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-04-14T03:25:00Z","title_canon_sha256":"f3c5dae93991c42e36e953ad4b0c1086b56c92c0ec1c7048d8074e79860ea0b0"},"schema_version":"1.0","source":{"id":"2304.06910","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.06910","created_at":"2026-07-05T07:31:27Z"},{"alias_kind":"arxiv_version","alias_value":"2304.06910v2","created_at":"2026-07-05T07:31:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06910","created_at":"2026-07-05T07:31:27Z"},{"alias_kind":"pith_short_12","alias_value":"XBTLWXKQB4SX","created_at":"2026-07-05T07:31:27Z"},{"alias_kind":"pith_short_16","alias_value":"XBTLWXKQB4SX5GET","created_at":"2026-07-05T07:31:27Z"},{"alias_kind":"pith_short_8","alias_value":"XBTLWXKQ","created_at":"2026-07-05T07:31:27Z"}],"graph_snapshots":[{"event_id":"sha256:bbe160e21951a20219ab0d62711af192b2f94facc56d3a4c053e6d4e70f90ea6","target":"graph","created_at":"2026-07-05T07:31:27Z","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/2304.06910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Emotion recognition in conversations is challenging due to the multi-modal nature of the emotion expression. We propose a hierarchical cross-attention model (HCAM) approach to multi-modal emotion recognition using a combination of recurrent and co-attention neural network models. The input to the model consists of two modalities, i) audio data, processed through a learnable wav2vec approach and, ii) text data represented using a bidirectional encoder representations from transformers (BERT) model. The audio and text representations are processed using a set of bi-directional recurrent neural n","authors_text":"Soumya Dutta, Sriram Ganapathy","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-04-14T03:25:00Z","title":"HCAM -- Hierarchical Cross Attention Model for Multi-modal Emotion Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06910","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":"sha256:29b44f129135ed0b048b257bdcb51091479cacb38f81dd02cabd0e42dfcf2ea2","target":"record","created_at":"2026-07-05T07:31:27Z","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":"dff3dfbb00e4484b18b52f5ae642b1e4d0c930f08c0a32253252192a63fe24be","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-04-14T03:25:00Z","title_canon_sha256":"f3c5dae93991c42e36e953ad4b0c1086b56c92c0ec1c7048d8074e79860ea0b0"},"schema_version":"1.0","source":{"id":"2304.06910","kind":"arxiv","version":2}},"canonical_sha256":"b866bb5d500f257e9893f507b3cc8d97b66c359ed06ff4265ebffe2ea058f21e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b866bb5d500f257e9893f507b3cc8d97b66c359ed06ff4265ebffe2ea058f21e","first_computed_at":"2026-07-05T07:31:27.518977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:31:27.518977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AfPsBNpGubyhUYKvErLIxj1COxXgCmF+lNLHMKPtks7evgeIrtQH1kx29REi1X0HRpWlRhz51UySuMp79s9VAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:31:27.519698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.06910","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29b44f129135ed0b048b257bdcb51091479cacb38f81dd02cabd0e42dfcf2ea2","sha256:bbe160e21951a20219ab0d62711af192b2f94facc56d3a4c053e6d4e70f90ea6"],"state_sha256":"fecf7d248410046ed078ffcd60e14685c3d5f5eca6ccbdb2186d1162dee4172d"}