{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:X6R4EMZ657YRVTIEFARQHIUTL6","short_pith_number":"pith:X6R4EMZ6","canonical_record":{"source":{"id":"2508.11187","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-15T03:38:21Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"5723e545b090e4f40568e90f26187236b20a40ff692fecb2f021f14918b51038","abstract_canon_sha256":"0a325b864bebe387f1d88077aab4478f37356532f38eb41597e5546c03953878"},"schema_version":"1.0"},"canonical_sha256":"bfa3c2333eeff11acd04282303a2935f89c366d3c009fc5620fe8dba6cb4e568","source":{"kind":"arxiv","id":"2508.11187","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11187","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11187v1","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11187","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"pith_short_12","alias_value":"X6R4EMZ657YR","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"pith_short_16","alias_value":"X6R4EMZ657YRVTIE","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"pith_short_8","alias_value":"X6R4EMZ6","created_at":"2026-07-05T11:54:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:X6R4EMZ657YRVTIEFARQHIUTL6","target":"record","payload":{"canonical_record":{"source":{"id":"2508.11187","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-15T03:38:21Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"5723e545b090e4f40568e90f26187236b20a40ff692fecb2f021f14918b51038","abstract_canon_sha256":"0a325b864bebe387f1d88077aab4478f37356532f38eb41597e5546c03953878"},"schema_version":"1.0"},"canonical_sha256":"bfa3c2333eeff11acd04282303a2935f89c366d3c009fc5620fe8dba6cb4e568","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:20.229371Z","signature_b64":"D29Jpoh3+V9jbcPqXXHYcbA1LEnZlyF7oDoQ3s0sN9SBiE19nb1LporBbNaKWYt2LvyRuTK4J5iUsCTvBVcaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfa3c2333eeff11acd04282303a2935f89c366d3c009fc5620fe8dba6cb4e568","last_reissued_at":"2026-07-05T11:54:20.228945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:20.228945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.11187","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":"2026-07-05T11:54:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a7XrilQItmRehx3hgIT7hVk0NK8QMA/UUgN+dO15F66I+2J5Be82qk4b/9UjyRgzRkoRdEuseTluGILYHQmCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:21:41.894827Z"},"content_sha256":"c1ed1a7769b886edb8ea16d815efe3963a249fdcb52fd62f882c76bd1e62a3cd","schema_version":"1.0","event_id":"sha256:c1ed1a7769b886edb8ea16d815efe3963a249fdcb52fd62f882c76bd1e62a3cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:X6R4EMZ657YRVTIEFARQHIUTL6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Expressive Speech Retrieval using Natural Language Descriptions of Speaking Style","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Deb Roy, Wonjune Kang","submitted_at":"2025-08-15T03:38:21Z","abstract_excerpt":"We introduce the task of expressive speech retrieval, where the goal is to retrieve speech utterances spoken in a given style based on a natural language description of that style. While prior work has primarily focused on performing speech retrieval based on what was said in an utterance, we aim to do so based on how something was said. We train speech and text encoders to embed speech and text descriptions of speaking styles into a joint latent space, which enables using free-form text prompts describing emotions or styles as queries to retrieve matching expressive speech segments. We perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11187","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/2508.11187/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":"2026-07-05T11:54:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VnZu4AFJUhdCaqxDN6jIQyNOMOYFHWq5K8ePeR9Op7TYxcPP1ABtfeBess1Uob+ULSlRlFPLscxM0sBhTQBbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:21:41.895356Z"},"content_sha256":"b7f97241941ddd6a2e402b39bb73e786144bed34f9e166056f0f1c2e32978043","schema_version":"1.0","event_id":"sha256:b7f97241941ddd6a2e402b39bb73e786144bed34f9e166056f0f1c2e32978043"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X6R4EMZ657YRVTIEFARQHIUTL6/bundle.json","state_url":"https://pith.science/pith/X6R4EMZ657YRVTIEFARQHIUTL6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X6R4EMZ657YRVTIEFARQHIUTL6/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":"2026-08-09T13:21:41Z","links":{"resolver":"https://pith.science/pith/X6R4EMZ657YRVTIEFARQHIUTL6","bundle":"https://pith.science/pith/X6R4EMZ657YRVTIEFARQHIUTL6/bundle.json","state":"https://pith.science/pith/X6R4EMZ657YRVTIEFARQHIUTL6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X6R4EMZ657YRVTIEFARQHIUTL6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X6R4EMZ657YRVTIEFARQHIUTL6","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":"0a325b864bebe387f1d88077aab4478f37356532f38eb41597e5546c03953878","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-15T03:38:21Z","title_canon_sha256":"5723e545b090e4f40568e90f26187236b20a40ff692fecb2f021f14918b51038"},"schema_version":"1.0","source":{"id":"2508.11187","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11187","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11187v1","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11187","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"pith_short_12","alias_value":"X6R4EMZ657YR","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"pith_short_16","alias_value":"X6R4EMZ657YRVTIE","created_at":"2026-07-05T11:54:20Z"},{"alias_kind":"pith_short_8","alias_value":"X6R4EMZ6","created_at":"2026-07-05T11:54:20Z"}],"graph_snapshots":[{"event_id":"sha256:b7f97241941ddd6a2e402b39bb73e786144bed34f9e166056f0f1c2e32978043","target":"graph","created_at":"2026-07-05T11:54:20Z","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/2508.11187/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce the task of expressive speech retrieval, where the goal is to retrieve speech utterances spoken in a given style based on a natural language description of that style. While prior work has primarily focused on performing speech retrieval based on what was said in an utterance, we aim to do so based on how something was said. We train speech and text encoders to embed speech and text descriptions of speaking styles into a joint latent space, which enables using free-form text prompts describing emotions or styles as queries to retrieve matching expressive speech segments. We perfor","authors_text":"Deb Roy, Wonjune Kang","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-15T03:38:21Z","title":"Expressive Speech Retrieval using Natural Language Descriptions of Speaking Style"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11187","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:c1ed1a7769b886edb8ea16d815efe3963a249fdcb52fd62f882c76bd1e62a3cd","target":"record","created_at":"2026-07-05T11:54:20Z","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":"0a325b864bebe387f1d88077aab4478f37356532f38eb41597e5546c03953878","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-15T03:38:21Z","title_canon_sha256":"5723e545b090e4f40568e90f26187236b20a40ff692fecb2f021f14918b51038"},"schema_version":"1.0","source":{"id":"2508.11187","kind":"arxiv","version":1}},"canonical_sha256":"bfa3c2333eeff11acd04282303a2935f89c366d3c009fc5620fe8dba6cb4e568","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfa3c2333eeff11acd04282303a2935f89c366d3c009fc5620fe8dba6cb4e568","first_computed_at":"2026-07-05T11:54:20.228945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:20.228945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D29Jpoh3+V9jbcPqXXHYcbA1LEnZlyF7oDoQ3s0sN9SBiE19nb1LporBbNaKWYt2LvyRuTK4J5iUsCTvBVcaAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:20.229371Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.11187","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1ed1a7769b886edb8ea16d815efe3963a249fdcb52fd62f882c76bd1e62a3cd","sha256:b7f97241941ddd6a2e402b39bb73e786144bed34f9e166056f0f1c2e32978043"],"state_sha256":"a47d6cd7a65e6c2fde1a51188d02b038bb1fcd2989ee9407b60d0eac9403312d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sx1B4+Ve70gZ0l3atmMNjAsFCLSHppntNL8+wUgLe/LF2P7x/uBUir4agAV4O19kbjWyof63Q77NkXbl9bcSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:21:41.899263Z","bundle_sha256":"9982f9689b58d1962219582528c8acd3d498a82094617883d8be8cb19709598c"}}