{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SHWJ7X7P3NQPZ6VBSIE6ZYIDAQ","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":"cb9c9db5fed56ee398f3fe03c231487438d761a193982ec17172fa62a6feba92","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-03-30T17:50:07Z","title_canon_sha256":"0af5c8a9ffd9ddb2a293d1f963cfaff662e69e01232feca046825f6b6c8a315a"},"schema_version":"1.0","source":{"id":"2603.28737","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.28737","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"arxiv_version","alias_value":"2603.28737v2","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.28737","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"pith_short_12","alias_value":"SHWJ7X7P3NQP","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"pith_short_16","alias_value":"SHWJ7X7P3NQPZ6VB","created_at":"2026-06-23T02:13:23Z"},{"alias_kind":"pith_short_8","alias_value":"SHWJ7X7P","created_at":"2026-06-23T02:13:23Z"}],"graph_snapshots":[{"event_id":"sha256:590f1a5eed7e13dca35dcc82e042d27f9cf4bf91c4093087277dc305f6f573d7","target":"graph","created_at":"2026-06-23T02:13:23Z","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/2603.28737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce ParaSpeechCLAP, a family of dual-encoder models that map speech and text style captions into a shared embedding space, supporting rich intrinsic (speaker-level) and situational (utterance-level) descriptors, such as pitch, texture, and emotion, beyond the narrow set handled by existing models. We train separate Intrinsic and Situational models alongside a unified Combined model, finding that specialized models are stronger on individual style dimensions while the unified model excels on compositional evaluation. We further show that ParaSpeechCLAP-Intrinsic benefits from an additi","authors_text":"Anuj Diwan, David Harwath, Eunsol Choi","cross_cats":["cs.AI","cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-03-30T17:50:07Z","title":"ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.28737","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:a1e26af12b7db29ac80895c1d8377ccd5d3c2ccd3c64cd5f1e14d4e181fe7f9d","target":"record","created_at":"2026-06-23T02:13:23Z","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":"cb9c9db5fed56ee398f3fe03c231487438d761a193982ec17172fa62a6feba92","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-03-30T17:50:07Z","title_canon_sha256":"0af5c8a9ffd9ddb2a293d1f963cfaff662e69e01232feca046825f6b6c8a315a"},"schema_version":"1.0","source":{"id":"2603.28737","kind":"arxiv","version":2}},"canonical_sha256":"91ec9fdfefdb60fcfaa19209ece10304292637e962d41b2a320627448db90e61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91ec9fdfefdb60fcfaa19209ece10304292637e962d41b2a320627448db90e61","first_computed_at":"2026-06-23T02:13:23.168018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:23.168018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ldir+OZ6cQZZyG1umfKB0+J2m7S8ZWx59ezWBBC7nDrjw8VhgmJi5REK5AT95utS/W7R4dmr9HBWwUF/fMijAg==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:23.168460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.28737","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1e26af12b7db29ac80895c1d8377ccd5d3c2ccd3c64cd5f1e14d4e181fe7f9d","sha256:590f1a5eed7e13dca35dcc82e042d27f9cf4bf91c4093087277dc305f6f573d7"],"state_sha256":"f30fc4a0b421817ad13963a1833192de9b46d2a38b5bb342ee2be725224c7a9a"}