{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YSZ2DVQW662FK6NHRUUUKJXTVF","short_pith_number":"pith:YSZ2DVQW","canonical_record":{"source":{"id":"2311.16509","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-28T04:49:17Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"c80fe6720f22ca10a35cc813c17ac2bf836c3587de3c5eb8d8e568b7914d7e10","abstract_canon_sha256":"8d806dd41d670e5abc32fbe14ad3c51d7be46fa4ac6dbaefad5c9a5e61ab0dcc"},"schema_version":"1.0"},"canonical_sha256":"c4b3a1d616f7b45579a78d294526f3a951c561a277845d2d4c4c45b1c27c2700","source":{"kind":"arxiv","id":"2311.16509","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.16509","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"arxiv_version","alias_value":"2311.16509v2","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16509","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"pith_short_12","alias_value":"YSZ2DVQW662F","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"pith_short_16","alias_value":"YSZ2DVQW662FK6NH","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"pith_short_8","alias_value":"YSZ2DVQW","created_at":"2026-07-05T07:28:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YSZ2DVQW662FK6NHRUUUKJXTVF","target":"record","payload":{"canonical_record":{"source":{"id":"2311.16509","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-28T04:49:17Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"c80fe6720f22ca10a35cc813c17ac2bf836c3587de3c5eb8d8e568b7914d7e10","abstract_canon_sha256":"8d806dd41d670e5abc32fbe14ad3c51d7be46fa4ac6dbaefad5c9a5e61ab0dcc"},"schema_version":"1.0"},"canonical_sha256":"c4b3a1d616f7b45579a78d294526f3a951c561a277845d2d4c4c45b1c27c2700","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:12.239493Z","signature_b64":"+qjA8VE9l14lhYeQMqhf5L8D++Wyv5OIYuvzVhn60/G+NXxh9IFFsGQVmbxjiWgj9V3xZhqPtnzsWwnhFDw5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4b3a1d616f7b45579a78d294526f3a951c561a277845d2d4c4c45b1c27c2700","last_reissued_at":"2026-07-05T07:28:12.238983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:12.238983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.16509","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:28:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7POIuOZo73rOFrrkCv+CU7xZjQ7qh0zfnwlNrSX2gc1BNMT5Xocy1zfXi6AbIgM30T+h91xPqK3idjRYSfPICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T01:47:26.158566Z"},"content_sha256":"c7461730ccb103b8cbef1b9cad05270c0e0449cf5ce0e0f4603d57e6dda800af","schema_version":"1.0","event_id":"sha256:c7461730ccb103b8cbef1b9cad05270c0e0449cf5ce0e0f4603d57e6dda800af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YSZ2DVQW662FK6NHRUUUKJXTVF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StyleCap: Automatic Speaking-Style Captioning from Speech Based on Speech and Language Self-supervised Learning Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Kazuki Yamauchi, Yuki Saito, Yusuke Ijima","submitted_at":"2023-11-28T04:49:17Z","abstract_excerpt":"We propose StyleCap, a method to generate natural language descriptions of speaking styles appearing in speech. Although most of conventional techniques for para-/non-linguistic information recognition focus on the category classification or the intensity estimation of pre-defined labels, they cannot provide the reasoning of the recognition result in an interpretable manner. StyleCap is a first step towards an end-to-end method for generating speaking-style prompts from speech, i.e., automatic speaking-style captioning. StyleCap is trained with paired data of speech and natural language descri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16509","kind":"arxiv","version":2},"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/2311.16509/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":"2026-07-05T07:28:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ErGxgKJvjTh33T/cO7dhJhIHnwTtHFcxp6eCclM+zfd/vFHNEDtd4254B3vJsrkeI2uWC06Eyc0AgwfBXVNtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T01:47:26.160074Z"},"content_sha256":"f557e54a43b4a1a1639053a9d030892cea3129934e482a6042f9dfa766430f12","schema_version":"1.0","event_id":"sha256:f557e54a43b4a1a1639053a9d030892cea3129934e482a6042f9dfa766430f12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YSZ2DVQW662FK6NHRUUUKJXTVF/bundle.json","state_url":"https://pith.science/pith/YSZ2DVQW662FK6NHRUUUKJXTVF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YSZ2DVQW662FK6NHRUUUKJXTVF/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":"2026-08-17T01:47:26Z","links":{"resolver":"https://pith.science/pith/YSZ2DVQW662FK6NHRUUUKJXTVF","bundle":"https://pith.science/pith/YSZ2DVQW662FK6NHRUUUKJXTVF/bundle.json","state":"https://pith.science/pith/YSZ2DVQW662FK6NHRUUUKJXTVF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YSZ2DVQW662FK6NHRUUUKJXTVF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YSZ2DVQW662FK6NHRUUUKJXTVF","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":"8d806dd41d670e5abc32fbe14ad3c51d7be46fa4ac6dbaefad5c9a5e61ab0dcc","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-28T04:49:17Z","title_canon_sha256":"c80fe6720f22ca10a35cc813c17ac2bf836c3587de3c5eb8d8e568b7914d7e10"},"schema_version":"1.0","source":{"id":"2311.16509","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.16509","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"arxiv_version","alias_value":"2311.16509v2","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16509","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"pith_short_12","alias_value":"YSZ2DVQW662F","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"pith_short_16","alias_value":"YSZ2DVQW662FK6NH","created_at":"2026-07-05T07:28:12Z"},{"alias_kind":"pith_short_8","alias_value":"YSZ2DVQW","created_at":"2026-07-05T07:28:12Z"}],"graph_snapshots":[{"event_id":"sha256:f557e54a43b4a1a1639053a9d030892cea3129934e482a6042f9dfa766430f12","target":"graph","created_at":"2026-07-05T07:28:12Z","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/2311.16509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose StyleCap, a method to generate natural language descriptions of speaking styles appearing in speech. Although most of conventional techniques for para-/non-linguistic information recognition focus on the category classification or the intensity estimation of pre-defined labels, they cannot provide the reasoning of the recognition result in an interpretable manner. StyleCap is a first step towards an end-to-end method for generating speaking-style prompts from speech, i.e., automatic speaking-style captioning. StyleCap is trained with paired data of speech and natural language descri","authors_text":"Kazuki Yamauchi, Yuki Saito, Yusuke Ijima","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-28T04:49:17Z","title":"StyleCap: Automatic Speaking-Style Captioning from Speech Based on Speech and Language Self-supervised Learning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16509","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:c7461730ccb103b8cbef1b9cad05270c0e0449cf5ce0e0f4603d57e6dda800af","target":"record","created_at":"2026-07-05T07:28:12Z","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":"8d806dd41d670e5abc32fbe14ad3c51d7be46fa4ac6dbaefad5c9a5e61ab0dcc","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-28T04:49:17Z","title_canon_sha256":"c80fe6720f22ca10a35cc813c17ac2bf836c3587de3c5eb8d8e568b7914d7e10"},"schema_version":"1.0","source":{"id":"2311.16509","kind":"arxiv","version":2}},"canonical_sha256":"c4b3a1d616f7b45579a78d294526f3a951c561a277845d2d4c4c45b1c27c2700","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4b3a1d616f7b45579a78d294526f3a951c561a277845d2d4c4c45b1c27c2700","first_computed_at":"2026-07-05T07:28:12.238983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:12.238983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+qjA8VE9l14lhYeQMqhf5L8D++Wyv5OIYuvzVhn60/G+NXxh9IFFsGQVmbxjiWgj9V3xZhqPtnzsWwnhFDw5BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:12.239493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.16509","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7461730ccb103b8cbef1b9cad05270c0e0449cf5ce0e0f4603d57e6dda800af","sha256:f557e54a43b4a1a1639053a9d030892cea3129934e482a6042f9dfa766430f12"],"state_sha256":"3c92f2b0dc7a939b53aad662d22ba4c3828e3c8fd036f1b36f5c2214d5d7ab0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lckBUsatIWOY4Q59y+PRZ8lLIuuep4eKp6kYXFA0d1AICbPBa6i89Pfb+wxEmgY625TVwATnFBAbrF1HKNEjCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T01:47:26.168107Z","bundle_sha256":"072c32c074f00ac7af01d9d9746e21b6baf7cab81a6d8d0094903e3f7516ccd5"}}