{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZK4HFI6PWIE2LKHA2GZYBQPM6G","short_pith_number":"pith:ZK4HFI6P","canonical_record":{"source":{"id":"2312.16383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-27T03:07:52Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"ccccf4c09df493d7899b2d391fa69da1d636d8072d1e1b3286f54cb306373347","abstract_canon_sha256":"9642d45b768b580c75c56784b7379f977710c02647c24b45164a34dd456a7298"},"schema_version":"1.0"},"canonical_sha256":"cab872a3cfb209a5a8e0d1b380c1ecf1a1808c51e7f8280c3c6feeb45eb86484","source":{"kind":"arxiv","id":"2312.16383","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16383","created_at":"2026-07-05T07:28:16Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16383v1","created_at":"2026-07-05T07:28:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16383","created_at":"2026-07-05T07:28:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZK4HFI6PWIE2","created_at":"2026-07-05T07:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZK4HFI6PWIE2LKHA","created_at":"2026-07-05T07:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZK4HFI6P","created_at":"2026-07-05T07:28:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZK4HFI6PWIE2LKHA2GZYBQPM6G","target":"record","payload":{"canonical_record":{"source":{"id":"2312.16383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-27T03:07:52Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"ccccf4c09df493d7899b2d391fa69da1d636d8072d1e1b3286f54cb306373347","abstract_canon_sha256":"9642d45b768b580c75c56784b7379f977710c02647c24b45164a34dd456a7298"},"schema_version":"1.0"},"canonical_sha256":"cab872a3cfb209a5a8e0d1b380c1ecf1a1808c51e7f8280c3c6feeb45eb86484","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:16.543693Z","signature_b64":"DCyXpbnd7DYeDhgpcxXE3ppu+jBwgVwlzoD5a87s3L8CcCQ+osbBVfas5sGKvDLhrRAW49IHTKGQlbXq4eCaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cab872a3cfb209a5a8e0d1b380c1ecf1a1808c51e7f8280c3c6feeb45eb86484","last_reissued_at":"2026-07-05T07:28:16.543237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:16.543237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.16383","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":"2026-07-05T07:28:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3d+CbsaOG6r0fWqp2k44uya2qYZKNseWmuix9L6cZb6j1hON4u5PfJyEy5BHEEBWFdMvScIC/YLcU2YebAsIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:57:30.813056Z"},"content_sha256":"73d5ded32a4daa0ce11b456eefdba8da9ad0f1058d97ff47e944d8fd359f2f83","schema_version":"1.0","event_id":"sha256:73d5ded32a4daa0ce11b456eefdba8da9ad0f1058d97ff47e944d8fd359f2f83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZK4HFI6PWIE2LKHA2GZYBQPM6G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Frame-level emotional state alignment method for speech emotion recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Cong Wang, Jinlong Xue, Qifei Li, Ya Li, Yayue Deng, Yichen Han, Yingming Gao","submitted_at":"2023-12-27T03:07:52Z","abstract_excerpt":"Speech emotion recognition (SER) systems aim to recognize human emotional state during human-computer interaction. Most existing SER systems are trained based on utterance-level labels. However, not all frames in an audio have affective states consistent with utterance-level label, which makes it difficult for the model to distinguish the true emotion of the audio and perform poorly. To address this problem, we propose a frame-level emotional state alignment method for SER. First, we fine-tune HuBERT model to obtain a SER system with task-adaptive pretraining (TAPT) method, and extract embeddi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16383","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.16383/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":"2026-07-05T07:28:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AHDCps12pxWNdYpKj3pMa52DwBCigi/TpFCjOALdAB5KJLNfYqKoBlFEuWKi40l37/qKPLoBBia06wHP27fBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:57:30.813547Z"},"content_sha256":"54e56fc116296c070193ddf5f08d6b3eedf83b9f9e4df294b8e3061fae97cf9c","schema_version":"1.0","event_id":"sha256:54e56fc116296c070193ddf5f08d6b3eedf83b9f9e4df294b8e3061fae97cf9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZK4HFI6PWIE2LKHA2GZYBQPM6G/bundle.json","state_url":"https://pith.science/pith/ZK4HFI6PWIE2LKHA2GZYBQPM6G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZK4HFI6PWIE2LKHA2GZYBQPM6G/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":"2026-08-05T15:57:30Z","links":{"resolver":"https://pith.science/pith/ZK4HFI6PWIE2LKHA2GZYBQPM6G","bundle":"https://pith.science/pith/ZK4HFI6PWIE2LKHA2GZYBQPM6G/bundle.json","state":"https://pith.science/pith/ZK4HFI6PWIE2LKHA2GZYBQPM6G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZK4HFI6PWIE2LKHA2GZYBQPM6G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZK4HFI6PWIE2LKHA2GZYBQPM6G","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":"9642d45b768b580c75c56784b7379f977710c02647c24b45164a34dd456a7298","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-27T03:07:52Z","title_canon_sha256":"ccccf4c09df493d7899b2d391fa69da1d636d8072d1e1b3286f54cb306373347"},"schema_version":"1.0","source":{"id":"2312.16383","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16383","created_at":"2026-07-05T07:28:16Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16383v1","created_at":"2026-07-05T07:28:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16383","created_at":"2026-07-05T07:28:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZK4HFI6PWIE2","created_at":"2026-07-05T07:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZK4HFI6PWIE2LKHA","created_at":"2026-07-05T07:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZK4HFI6P","created_at":"2026-07-05T07:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:54e56fc116296c070193ddf5f08d6b3eedf83b9f9e4df294b8e3061fae97cf9c","target":"graph","created_at":"2026-07-05T07:28:16Z","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/2312.16383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech emotion recognition (SER) systems aim to recognize human emotional state during human-computer interaction. Most existing SER systems are trained based on utterance-level labels. However, not all frames in an audio have affective states consistent with utterance-level label, which makes it difficult for the model to distinguish the true emotion of the audio and perform poorly. To address this problem, we propose a frame-level emotional state alignment method for SER. First, we fine-tune HuBERT model to obtain a SER system with task-adaptive pretraining (TAPT) method, and extract embeddi","authors_text":"Cong Wang, Jinlong Xue, Qifei Li, Ya Li, Yayue Deng, Yichen Han, Yingming Gao","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-27T03:07:52Z","title":"Frame-level emotional state alignment method for speech emotion recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16383","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":"sha256:73d5ded32a4daa0ce11b456eefdba8da9ad0f1058d97ff47e944d8fd359f2f83","target":"record","created_at":"2026-07-05T07:28:16Z","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":"9642d45b768b580c75c56784b7379f977710c02647c24b45164a34dd456a7298","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-27T03:07:52Z","title_canon_sha256":"ccccf4c09df493d7899b2d391fa69da1d636d8072d1e1b3286f54cb306373347"},"schema_version":"1.0","source":{"id":"2312.16383","kind":"arxiv","version":1}},"canonical_sha256":"cab872a3cfb209a5a8e0d1b380c1ecf1a1808c51e7f8280c3c6feeb45eb86484","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cab872a3cfb209a5a8e0d1b380c1ecf1a1808c51e7f8280c3c6feeb45eb86484","first_computed_at":"2026-07-05T07:28:16.543237Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:16.543237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DCyXpbnd7DYeDhgpcxXE3ppu+jBwgVwlzoD5a87s3L8CcCQ+osbBVfas5sGKvDLhrRAW49IHTKGQlbXq4eCaAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:16.543693Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.16383","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73d5ded32a4daa0ce11b456eefdba8da9ad0f1058d97ff47e944d8fd359f2f83","sha256:54e56fc116296c070193ddf5f08d6b3eedf83b9f9e4df294b8e3061fae97cf9c"],"state_sha256":"b3ba0d1fa5b043e93ee13ef6bf188cb46c1f216709c663cf0f19604556e89dd6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fEGsHrJSqmfF590RKmw3V1KWMEyA3dLbzGP/ZjuvX0O91ONXDge9TGbVPNzcYKLfch6E4XGduD6vWVNs7y45Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:57:30.817265Z","bundle_sha256":"a650dea76baf0086d09bb9c9ba2970c8e9f669f2fff5f39484376835e96fd820"}}