{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:O4VVKVIFGA7CDQQNVD5MP7MF6G","short_pith_number":"pith:O4VVKVIF","canonical_record":{"source":{"id":"1810.04635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-10T16:51:58Z","cross_cats_sorted":[],"title_canon_sha256":"f6c9b45a26096eb2b19e0f9594d19f0b3b3a4e32b86040db79b3351f4a690b0f","abstract_canon_sha256":"0ba8c2b00ceee316abf53b13e5bef8fbca204fb1df9e86a0c8994c4ae8e1f9e1"},"schema_version":"1.0"},"canonical_sha256":"772b555505303e21c20da8fac7fd85f1a84ca6e6d04da445b73cb086d2ecde74","source":{"kind":"arxiv","id":"1810.04635","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04635","created_at":"2026-05-18T00:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04635v1","created_at":"2026-05-18T00:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04635","created_at":"2026-05-18T00:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"O4VVKVIFGA7C","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"O4VVKVIFGA7CDQQN","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"O4VVKVIF","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:O4VVKVIFGA7CDQQNVD5MP7MF6G","target":"record","payload":{"canonical_record":{"source":{"id":"1810.04635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-10T16:51:58Z","cross_cats_sorted":[],"title_canon_sha256":"f6c9b45a26096eb2b19e0f9594d19f0b3b3a4e32b86040db79b3351f4a690b0f","abstract_canon_sha256":"0ba8c2b00ceee316abf53b13e5bef8fbca204fb1df9e86a0c8994c4ae8e1f9e1"},"schema_version":"1.0"},"canonical_sha256":"772b555505303e21c20da8fac7fd85f1a84ca6e6d04da445b73cb086d2ecde74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:39.542125Z","signature_b64":"QiJrvrXbEsDHlTx59s4ke4fa+FGhP7+XYpKNw3d3/3VrOWOdNrh5f6RMMaPOmXeFfjrbFpSPaKNx+XGJwldCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"772b555505303e21c20da8fac7fd85f1a84ca6e6d04da445b73cb086d2ecde74","last_reissued_at":"2026-05-18T00:03:39.541574Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:39.541574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.04635","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":"2026-05-18T00:03:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4fN3DNZCTKIqTSkh5epfN4ojnTRV2XIEzv6BsaHZ+5WMIsv4L8NTksrdDvm6m92zT7T+Lv+Y84KqO4LYKG1TBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:40:49.183217Z"},"content_sha256":"2743ddefb350d41b4353898e7b2be7b6e1514bdb29724e23708d79391149b291","schema_version":"1.0","event_id":"sha256:2743ddefb350d41b4353898e7b2be7b6e1514bdb29724e23708d79391149b291"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:O4VVKVIFGA7CDQQNVD5MP7MF6G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Speech Emotion Recognition Using Audio and Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kyomin Jung, Seokhyun Byun, Seunghyun Yoon","submitted_at":"2018-10-10T16:51:58Z","abstract_excerpt":"Speech emotion recognition is a challenging task, and extensive reliance has been placed on models that use audio features in building well-performing classifiers. In this paper, we propose a novel deep dual recurrent encoder model that utilizes text data and audio signals simultaneously to obtain a better understanding of speech data. As emotional dialogue is composed of sound and spoken content, our model encodes the information from audio and text sequences using dual recurrent neural networks (RNNs) and then combines the information from these sources to predict the emotion class. This arc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04635","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":""},"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":"2026-05-18T00:03:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cAnbfxaNnxHdXYSLDPA0H5HyJXe4RF7dlOm0348HUIgAEspb4a+gIA+aH4bmtaXId4oRfcrQJaYaA+7kMk72Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T23:40:49.183481Z"},"content_sha256":"96c605b7ec2a0d49708f30c2d25577eabc5916d5596e2f38fce62d652890a948","schema_version":"1.0","event_id":"sha256:96c605b7ec2a0d49708f30c2d25577eabc5916d5596e2f38fce62d652890a948"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O4VVKVIFGA7CDQQNVD5MP7MF6G/bundle.json","state_url":"https://pith.science/pith/O4VVKVIFGA7CDQQNVD5MP7MF6G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O4VVKVIFGA7CDQQNVD5MP7MF6G/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":"2026-07-31T23:40:49Z","links":{"resolver":"https://pith.science/pith/O4VVKVIFGA7CDQQNVD5MP7MF6G","bundle":"https://pith.science/pith/O4VVKVIFGA7CDQQNVD5MP7MF6G/bundle.json","state":"https://pith.science/pith/O4VVKVIFGA7CDQQNVD5MP7MF6G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O4VVKVIFGA7CDQQNVD5MP7MF6G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:O4VVKVIFGA7CDQQNVD5MP7MF6G","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":"0ba8c2b00ceee316abf53b13e5bef8fbca204fb1df9e86a0c8994c4ae8e1f9e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-10T16:51:58Z","title_canon_sha256":"f6c9b45a26096eb2b19e0f9594d19f0b3b3a4e32b86040db79b3351f4a690b0f"},"schema_version":"1.0","source":{"id":"1810.04635","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04635","created_at":"2026-05-18T00:03:39Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04635v1","created_at":"2026-05-18T00:03:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04635","created_at":"2026-05-18T00:03:39Z"},{"alias_kind":"pith_short_12","alias_value":"O4VVKVIFGA7C","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"O4VVKVIFGA7CDQQN","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"O4VVKVIF","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:96c605b7ec2a0d49708f30c2d25577eabc5916d5596e2f38fce62d652890a948","target":"graph","created_at":"2026-05-18T00:03:39Z","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"},"paper":{"abstract_excerpt":"Speech emotion recognition is a challenging task, and extensive reliance has been placed on models that use audio features in building well-performing classifiers. In this paper, we propose a novel deep dual recurrent encoder model that utilizes text data and audio signals simultaneously to obtain a better understanding of speech data. As emotional dialogue is composed of sound and spoken content, our model encodes the information from audio and text sequences using dual recurrent neural networks (RNNs) and then combines the information from these sources to predict the emotion class. This arc","authors_text":"Kyomin Jung, Seokhyun Byun, Seunghyun Yoon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-10T16:51:58Z","title":"Multimodal Speech Emotion Recognition Using Audio and Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04635","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":"sha256:2743ddefb350d41b4353898e7b2be7b6e1514bdb29724e23708d79391149b291","target":"record","created_at":"2026-05-18T00:03:39Z","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":"0ba8c2b00ceee316abf53b13e5bef8fbca204fb1df9e86a0c8994c4ae8e1f9e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-10T16:51:58Z","title_canon_sha256":"f6c9b45a26096eb2b19e0f9594d19f0b3b3a4e32b86040db79b3351f4a690b0f"},"schema_version":"1.0","source":{"id":"1810.04635","kind":"arxiv","version":1}},"canonical_sha256":"772b555505303e21c20da8fac7fd85f1a84ca6e6d04da445b73cb086d2ecde74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"772b555505303e21c20da8fac7fd85f1a84ca6e6d04da445b73cb086d2ecde74","first_computed_at":"2026-05-18T00:03:39.541574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:39.541574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QiJrvrXbEsDHlTx59s4ke4fa+FGhP7+XYpKNw3d3/3VrOWOdNrh5f6RMMaPOmXeFfjrbFpSPaKNx+XGJwldCBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:39.542125Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.04635","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2743ddefb350d41b4353898e7b2be7b6e1514bdb29724e23708d79391149b291","sha256:96c605b7ec2a0d49708f30c2d25577eabc5916d5596e2f38fce62d652890a948"],"state_sha256":"e2e690af4f4d5959bc6f7b2bcd176c350e98e13922cc7fa43df2449a0e088b51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vdLGRHPB/6bCqooz83wCpHp8oMy797mr55te2EnHZj4kzr52wuUhQzRJjHIIkCSE17DHfUFa6deoOb8PgFexDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T23:40:49.186613Z","bundle_sha256":"fb571c11eee8557b29fe04a74f7ed40eec7de5e6556eeb8adaf81e8d72efbd98"}}