{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JOOR5MGBOOLYBAEBDRWRCX7LU3","short_pith_number":"pith:JOOR5MGB","schema_version":"1.0","canonical_sha256":"4b9d1eb0c173978080811c6d115feba6c855257f180ec48f5f99cefc4d355ff2","source":{"kind":"arxiv","id":"2501.16344","version":4},"attestation_state":"computed","paper":{"title":"WhiSPA: Semantically and Psychologically Aligned Whisper with Self-Supervised Contrastive and Student-Teacher Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","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","submitted_at":"2025-01-15T06:30:17Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.16344","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-15T06:30:17Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"7b23f82559e84b2f670213e409040a177a95e293ef1c01285fbb81f84ab40607","abstract_canon_sha256":"e5747cab7971a88f99894fbb1c1a465f3b4b6819cc50d7802a6c8a8537863e76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:19.340252Z","signature_b64":"3O+8aOPuPhOgyYbyiHBKH+dkcUYGfi5+lBdAssv7XjONgzARiLqsrkq4sTzC/Q4CPb/TCW8prNIFslg8Rw5FDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b9d1eb0c173978080811c6d115feba6c855257f180ec48f5f99cefc4d355ff2","last_reissued_at":"2026-07-05T11:13:19.339781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:19.339781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WhiSPA: Semantically and Psychologically Aligned Whisper with Self-Supervised Contrastive and Student-Teacher Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","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","submitted_at":"2025-01-15T06:30:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16344","kind":"arxiv","version":4},"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/2501.16344/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.16344","created_at":"2026-07-05T11:13:19.339834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16344v4","created_at":"2026-07-05T11:13:19.339834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16344","created_at":"2026-07-05T11:13:19.339834+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOOR5MGBOOLY","created_at":"2026-07-05T11:13:19.339834+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOOR5MGBOOLYBAEB","created_at":"2026-07-05T11:13:19.339834+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOOR5MGB","created_at":"2026-07-05T11:13:19.339834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOOR5MGBOOLYBAEBDRWRCX7LU3","json":"https://pith.science/pith/JOOR5MGBOOLYBAEBDRWRCX7LU3.json","graph_json":"https://pith.science/api/pith-number/JOOR5MGBOOLYBAEBDRWRCX7LU3/graph.json","events_json":"https://pith.science/api/pith-number/JOOR5MGBOOLYBAEBDRWRCX7LU3/events.json","paper":"https://pith.science/paper/JOOR5MGB"},"agent_actions":{"view_html":"https://pith.science/pith/JOOR5MGBOOLYBAEBDRWRCX7LU3","download_json":"https://pith.science/pith/JOOR5MGBOOLYBAEBDRWRCX7LU3.json","view_paper":"https://pith.science/paper/JOOR5MGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16344&json=true","fetch_graph":"https://pith.science/api/pith-number/JOOR5MGBOOLYBAEBDRWRCX7LU3/graph.json","fetch_events":"https://pith.science/api/pith-number/JOOR5MGBOOLYBAEBDRWRCX7LU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOOR5MGBOOLYBAEBDRWRCX7LU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOOR5MGBOOLYBAEBDRWRCX7LU3/action/storage_attestation","attest_author":"https://pith.science/pith/JOOR5MGBOOLYBAEBDRWRCX7LU3/action/author_attestation","sign_citation":"https://pith.science/pith/JOOR5MGBOOLYBAEBDRWRCX7LU3/action/citation_signature","submit_replication":"https://pith.science/pith/JOOR5MGBOOLYBAEBDRWRCX7LU3/action/replication_record"}},"created_at":"2026-07-05T11:13:19.339834+00:00","updated_at":"2026-07-05T11:13:19.339834+00:00"}