{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q6WBZERTK4Z6D3TQCAAIL4A5NJ","short_pith_number":"pith:Q6WBZERT","schema_version":"1.0","canonical_sha256":"87ac1c92335733e1ee70100085f01d6a7960768e5b0a133f05c96e9ad88498db","source":{"kind":"arxiv","id":"2607.09020","version":1},"attestation_state":"computed","paper":{"title":"Phone Segmentation and Recognition through Phonological Activation Mapping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chin-Jou Li, Daisuke Saito, David Harwath, David R. Mortensen, Eunjung Yeo, Jian Zhu, Kwanghee Choi, Nobuaki Minematsu, Shikhar Bharadwaj, Shinji Watanabe, Stephen McIntosh","submitted_at":"2026-07-10T01:05:30Z","abstract_excerpt":"Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately. We argue that phonetic structure is already latent in the representations of self-supervised speech models (S3Ms), and one only needs to steer them to solve both tasks. We leverage S3M-based Phonological Activation Mapping (SPAM), which maps each S3M representation frame to a vector of phonological feature activations, such as voicing and nasality. On top of SPAM, we introduce two simple but effective lightweight, gradient-descent-free prediction heads: a recognition head and"},"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":"2607.09020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-10T01:05:30Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"488c3e99f0f2f8c5cf6116bf2c7cb1b0a4e475a15aa5a5c6b534b329d9ec3aaf","abstract_canon_sha256":"c41430d487a05c35c732b06eaca08fad6f258e0ce8981b3b8ac133f7eeda80ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:34.791205Z","signature_b64":"QaYrgR6eNNFYKOzb9zdIrexkYWW4MMqv8EW8CG7GIRWtmhwMji9WerwRgclSRKZxA4Fr3Bg0hRG6QAITiNArAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87ac1c92335733e1ee70100085f01d6a7960768e5b0a133f05c96e9ad88498db","last_reissued_at":"2026-07-13T00:17:34.789374Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:34.789374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phone Segmentation and Recognition through Phonological Activation Mapping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chin-Jou Li, Daisuke Saito, David Harwath, David R. Mortensen, Eunjung Yeo, Jian Zhu, Kwanghee Choi, Nobuaki Minematsu, Shikhar Bharadwaj, Shinji Watanabe, Stephen McIntosh","submitted_at":"2026-07-10T01:05:30Z","abstract_excerpt":"Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately. We argue that phonetic structure is already latent in the representations of self-supervised speech models (S3Ms), and one only needs to steer them to solve both tasks. We leverage S3M-based Phonological Activation Mapping (SPAM), which maps each S3M representation frame to a vector of phonological feature activations, such as voicing and nasality. On top of SPAM, we introduce two simple but effective lightweight, gradient-descent-free prediction heads: a recognition head and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09020","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/2607.09020/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":"2607.09020","created_at":"2026-07-13T00:17:34.790591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09020v1","created_at":"2026-07-13T00:17:34.790591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09020","created_at":"2026-07-13T00:17:34.790591+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6WBZERTK4Z6","created_at":"2026-07-13T00:17:34.790591+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6WBZERTK4Z6D3TQ","created_at":"2026-07-13T00:17:34.790591+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6WBZERT","created_at":"2026-07-13T00:17:34.790591+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/Q6WBZERTK4Z6D3TQCAAIL4A5NJ","json":"https://pith.science/pith/Q6WBZERTK4Z6D3TQCAAIL4A5NJ.json","graph_json":"https://pith.science/api/pith-number/Q6WBZERTK4Z6D3TQCAAIL4A5NJ/graph.json","events_json":"https://pith.science/api/pith-number/Q6WBZERTK4Z6D3TQCAAIL4A5NJ/events.json","paper":"https://pith.science/paper/Q6WBZERT"},"agent_actions":{"view_html":"https://pith.science/pith/Q6WBZERTK4Z6D3TQCAAIL4A5NJ","download_json":"https://pith.science/pith/Q6WBZERTK4Z6D3TQCAAIL4A5NJ.json","view_paper":"https://pith.science/paper/Q6WBZERT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09020&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6WBZERTK4Z6D3TQCAAIL4A5NJ/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6WBZERTK4Z6D3TQCAAIL4A5NJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6WBZERTK4Z6D3TQCAAIL4A5NJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6WBZERTK4Z6D3TQCAAIL4A5NJ/action/storage_attestation","attest_author":"https://pith.science/pith/Q6WBZERTK4Z6D3TQCAAIL4A5NJ/action/author_attestation","sign_citation":"https://pith.science/pith/Q6WBZERTK4Z6D3TQCAAIL4A5NJ/action/citation_signature","submit_replication":"https://pith.science/pith/Q6WBZERTK4Z6D3TQCAAIL4A5NJ/action/replication_record"}},"created_at":"2026-07-13T00:17:34.790591+00:00","updated_at":"2026-07-13T00:17:34.790591+00:00"}