{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JOOR5MGBOOLYBAEBDRWRCX7LU3","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":"e5747cab7971a88f99894fbb1c1a465f3b4b6819cc50d7802a6c8a8537863e76","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-15T06:30:17Z","title_canon_sha256":"7b23f82559e84b2f670213e409040a177a95e293ef1c01285fbb81f84ab40607"},"schema_version":"1.0","source":{"id":"2501.16344","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16344","created_at":"2026-07-05T11:13:19Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16344v4","created_at":"2026-07-05T11:13:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16344","created_at":"2026-07-05T11:13:19Z"},{"alias_kind":"pith_short_12","alias_value":"JOOR5MGBOOLY","created_at":"2026-07-05T11:13:19Z"},{"alias_kind":"pith_short_16","alias_value":"JOOR5MGBOOLYBAEB","created_at":"2026-07-05T11:13:19Z"},{"alias_kind":"pith_short_8","alias_value":"JOOR5MGB","created_at":"2026-07-05T11:13:19Z"}],"graph_snapshots":[{"event_id":"sha256:2fab8e3ff92d0e9096b5c5de5b0d6f2528e40ba27db13cbcaa95e81f519e9fa7","target":"graph","created_at":"2026-07-05T11:13:19Z","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/2501.16344/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current speech encoding pipelines often rely on an additional text-based LM to get robust representations of human communication, even though SotA speech-to-text models often have a LM within. This work proposes an approach to improve the LM within an audio model such that the subsequent text-LM is unnecessary. We introduce WhiSPA (Whisper with Semantic and Psychological Alignment), which leverages a novel audio training objective: contrastive loss with a language model embedding as a teacher. Using over 500k speech segments from mental health audio interviews, we evaluate the utility of align","authors_text":"Adithya Ganesan, Akshay Raghavan, Benjamin Luft, Camilo Ruggero, H. Andrew Schwartz, Jonah Luby, Neville Ryant, Oscar Kjell, Rajath Rao, Roman Kotov, Ryan L. Boyd, Scott Feltman, Whitney Ringwald","cross_cats":["cs.AI","cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-15T06:30:17Z","title":"WhiSPA: Semantically and Psychologically Aligned Whisper with Self-Supervised Contrastive and Student-Teacher Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16344","kind":"arxiv","version":4},"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":"sha256:936f076b566d2527ac84e1d1c4273da5e2f14854f67e7fda4998ff5bb291b2bf","target":"record","created_at":"2026-07-05T11:13:19Z","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":"e5747cab7971a88f99894fbb1c1a465f3b4b6819cc50d7802a6c8a8537863e76","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-15T06:30:17Z","title_canon_sha256":"7b23f82559e84b2f670213e409040a177a95e293ef1c01285fbb81f84ab40607"},"schema_version":"1.0","source":{"id":"2501.16344","kind":"arxiv","version":4}},"canonical_sha256":"4b9d1eb0c173978080811c6d115feba6c855257f180ec48f5f99cefc4d355ff2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b9d1eb0c173978080811c6d115feba6c855257f180ec48f5f99cefc4d355ff2","first_computed_at":"2026-07-05T11:13:19.339781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:19.339781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3O+8aOPuPhOgyYbyiHBKH+dkcUYGfi5+lBdAssv7XjONgzARiLqsrkq4sTzC/Q4CPb/TCW8prNIFslg8Rw5FDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:19.340252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16344","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:936f076b566d2527ac84e1d1c4273da5e2f14854f67e7fda4998ff5bb291b2bf","sha256:2fab8e3ff92d0e9096b5c5de5b0d6f2528e40ba27db13cbcaa95e81f519e9fa7"],"state_sha256":"357b88c3fb9b8dbe7b3b2b6d85a80cfaac04fa5fa913e2e9de1ccdc26bf00ac4"}