{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NPAXUZKLS5E2VIOUILJOTFOZ3H","short_pith_number":"pith:NPAXUZKL","canonical_record":{"source":{"id":"2410.19134","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T20:05:31Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"6617d4dd0f7ac21625f4a2acfd0f825a912496235705f5e3a50ead3027ed4733","abstract_canon_sha256":"39a01e21158dbecd14b35fa8e5796226cef36e3098bd23c174b0223953122b63"},"schema_version":"1.0"},"canonical_sha256":"6bc17a654b9749aaa1d442d2e995d9d9f7fd214475327971bb8635e5e6fd0950","source":{"kind":"arxiv","id":"2410.19134","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19134","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19134v1","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19134","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"pith_short_12","alias_value":"NPAXUZKLS5E2","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"pith_short_16","alias_value":"NPAXUZKLS5E2VIOU","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"pith_short_8","alias_value":"NPAXUZKL","created_at":"2026-07-05T09:25:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NPAXUZKLS5E2VIOUILJOTFOZ3H","target":"record","payload":{"canonical_record":{"source":{"id":"2410.19134","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T20:05:31Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"6617d4dd0f7ac21625f4a2acfd0f825a912496235705f5e3a50ead3027ed4733","abstract_canon_sha256":"39a01e21158dbecd14b35fa8e5796226cef36e3098bd23c174b0223953122b63"},"schema_version":"1.0"},"canonical_sha256":"6bc17a654b9749aaa1d442d2e995d9d9f7fd214475327971bb8635e5e6fd0950","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:51.877456Z","signature_b64":"aKDsDMzuiLXT6EFXawLBPi4vAcIVSkwwFz0D36HKbI15uySdnoLD1oIvIYnZzEZM/wAdk5vGsl3QZkeIP9BADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bc17a654b9749aaa1d442d2e995d9d9f7fd214475327971bb8635e5e6fd0950","last_reissued_at":"2026-07-05T09:25:51.876861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:51.876861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.19134","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":"2026-07-05T09:25:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LoFjdhnpF0ZpPqPfZ/6SeawAezYEN0aUkO8rxB0Df6Q/P+9+dACF16wwMXTevoNclfh72KNDw26NxMOTwwr5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T14:52:41.648485Z"},"content_sha256":"869b3a14b60beade40cf9b62e97d538fbd9c8c768f2953b02656d3c2ec1ce223","schema_version":"1.0","event_id":"sha256:869b3a14b60beade40cf9b62e97d538fbd9c8c768f2953b02656d3c2ec1ce223"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NPAXUZKLS5E2VIOUILJOTFOZ3H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AlignCap: Aligning Speech Emotion Captioning to Human Preferences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hanhui Chen, Haoxiang Shi, Ziqi Liang","submitted_at":"2024-10-24T20:05:31Z","abstract_excerpt":"Speech Emotion Captioning (SEC) has gradually become an active research task. The emotional content conveyed through human speech are often complex, and classifying them into fixed categories may not be enough to fully capture speech emotions. Describing speech emotions through natural language may be a more effective approach. However, existing SEC methods often produce hallucinations and lose generalization on unseen speech. To overcome these problems, we propose AlignCap, which Aligning Speech Emotion Captioning to Human Preferences based on large language model (LLM) with two properties: 1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19134","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/2410.19134/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":"2026-07-05T09:25:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n2VVbEofS1zsiLyDSDFGvuG48zDCZPsDFL1o3i40d5zD0QsGdpcKTdrp2cnpOfsNDNiKHyaQ//iz3PPSe1gIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T14:52:41.648858Z"},"content_sha256":"c82d7351f9d668eca5b74428496e134b2919347aee17742bebad44d2717a9b39","schema_version":"1.0","event_id":"sha256:c82d7351f9d668eca5b74428496e134b2919347aee17742bebad44d2717a9b39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NPAXUZKLS5E2VIOUILJOTFOZ3H/bundle.json","state_url":"https://pith.science/pith/NPAXUZKLS5E2VIOUILJOTFOZ3H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NPAXUZKLS5E2VIOUILJOTFOZ3H/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":"2026-07-10T14:52:41Z","links":{"resolver":"https://pith.science/pith/NPAXUZKLS5E2VIOUILJOTFOZ3H","bundle":"https://pith.science/pith/NPAXUZKLS5E2VIOUILJOTFOZ3H/bundle.json","state":"https://pith.science/pith/NPAXUZKLS5E2VIOUILJOTFOZ3H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NPAXUZKLS5E2VIOUILJOTFOZ3H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NPAXUZKLS5E2VIOUILJOTFOZ3H","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":"39a01e21158dbecd14b35fa8e5796226cef36e3098bd23c174b0223953122b63","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T20:05:31Z","title_canon_sha256":"6617d4dd0f7ac21625f4a2acfd0f825a912496235705f5e3a50ead3027ed4733"},"schema_version":"1.0","source":{"id":"2410.19134","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19134","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19134v1","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19134","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"pith_short_12","alias_value":"NPAXUZKLS5E2","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"pith_short_16","alias_value":"NPAXUZKLS5E2VIOU","created_at":"2026-07-05T09:25:51Z"},{"alias_kind":"pith_short_8","alias_value":"NPAXUZKL","created_at":"2026-07-05T09:25:51Z"}],"graph_snapshots":[{"event_id":"sha256:c82d7351f9d668eca5b74428496e134b2919347aee17742bebad44d2717a9b39","target":"graph","created_at":"2026-07-05T09:25:51Z","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/2410.19134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech Emotion Captioning (SEC) has gradually become an active research task. The emotional content conveyed through human speech are often complex, and classifying them into fixed categories may not be enough to fully capture speech emotions. Describing speech emotions through natural language may be a more effective approach. However, existing SEC methods often produce hallucinations and lose generalization on unseen speech. To overcome these problems, we propose AlignCap, which Aligning Speech Emotion Captioning to Human Preferences based on large language model (LLM) with two properties: 1","authors_text":"Hanhui Chen, Haoxiang Shi, Ziqi Liang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T20:05:31Z","title":"AlignCap: Aligning Speech Emotion Captioning to Human Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19134","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":"sha256:869b3a14b60beade40cf9b62e97d538fbd9c8c768f2953b02656d3c2ec1ce223","target":"record","created_at":"2026-07-05T09:25:51Z","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":"39a01e21158dbecd14b35fa8e5796226cef36e3098bd23c174b0223953122b63","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T20:05:31Z","title_canon_sha256":"6617d4dd0f7ac21625f4a2acfd0f825a912496235705f5e3a50ead3027ed4733"},"schema_version":"1.0","source":{"id":"2410.19134","kind":"arxiv","version":1}},"canonical_sha256":"6bc17a654b9749aaa1d442d2e995d9d9f7fd214475327971bb8635e5e6fd0950","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bc17a654b9749aaa1d442d2e995d9d9f7fd214475327971bb8635e5e6fd0950","first_computed_at":"2026-07-05T09:25:51.876861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:51.876861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aKDsDMzuiLXT6EFXawLBPi4vAcIVSkwwFz0D36HKbI15uySdnoLD1oIvIYnZzEZM/wAdk5vGsl3QZkeIP9BADQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:51.877456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.19134","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:869b3a14b60beade40cf9b62e97d538fbd9c8c768f2953b02656d3c2ec1ce223","sha256:c82d7351f9d668eca5b74428496e134b2919347aee17742bebad44d2717a9b39"],"state_sha256":"0cb321fea0b1abbd435d131a94844374c95d3cfcd017d1e59ed34fe98c3eda3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XQNwR5JYxut9wUSwXeTDEagB+m/TfEp0SHGc7PTTYYJ1bD1TTo+Om/vnLbE6aAzM542Emcd8l8ns2sW65FtnAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T14:52:41.650812Z","bundle_sha256":"8419e51d33c38f43b1b1890e677999426ca1d2a2b80a22246fa59037898e0543"}}