{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3EHNQDVDBBEKNNDWSJZ3QBOX6B","short_pith_number":"pith:3EHNQDVD","schema_version":"1.0","canonical_sha256":"d90ed80ea30848a6b4769273b805d7f07e316ae753fe18c311178af4efbc87d5","source":{"kind":"arxiv","id":"2607.18934","version":1},"attestation_state":"computed","paper":{"title":"Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bernhard Thallinger (1) ((1) nyra labs), Laurin Wagner (1), Mario Zusag (1)","submitted_at":"2026-07-21T10:19:17Z","abstract_excerpt":"Modern ASR models trained on heterogeneously annotated data treat transcription style (verbatim vs. intended) as an uncontrolled latent variable, causing measurable decoding instability, evaluation confounding (up to 60% of reported WER attributable to style mismatch), and unreliable word-level timing. We show that models already encode both styles; the challenge is controlled activation. Using coverage-aware decoder task tokens trained on parallel verbatim/intended transcript pairs, we raise German disfluency F1 from 10% to 79% zero-shot, despite English-only training. Full English-only fine-"},"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":"2607.18934","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T10:19:17Z","cross_cats_sorted":[],"title_canon_sha256":"13ccfbc9e1ab503b77cbdc082b4686fcfc48f7e07abf1fdea1fc74ac30616ff5","abstract_canon_sha256":"1e117b37054aa6cf056cb21ca735470cf98cc432301f1f57d1cac5b5cb3eec6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:23:20.643836Z","signature_b64":"OtZ5JwHhK3/g7yN+JPu7yRXLQtzECx0MRga3js4Odla0W6w6tTFuvlOaEwpIFLG8AWm6tBTW5Y7cma1TMVGUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d90ed80ea30848a6b4769273b805d7f07e316ae753fe18c311178af4efbc87d5","last_reissued_at":"2026-07-22T01:23:20.642981Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:23:20.642981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bernhard Thallinger (1) ((1) nyra labs), Laurin Wagner (1), Mario Zusag (1)","submitted_at":"2026-07-21T10:19:17Z","abstract_excerpt":"Modern ASR models trained on heterogeneously annotated data treat transcription style (verbatim vs. intended) as an uncontrolled latent variable, causing measurable decoding instability, evaluation confounding (up to 60% of reported WER attributable to style mismatch), and unreliable word-level timing. We show that models already encode both styles; the challenge is controlled activation. Using coverage-aware decoder task tokens trained on parallel verbatim/intended transcript pairs, we raise German disfluency F1 from 10% to 79% zero-shot, despite English-only training. Full English-only fine-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18934","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/2607.18934/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":"2607.18934","created_at":"2026-07-22T01:23:20.643428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18934v1","created_at":"2026-07-22T01:23:20.643428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18934","created_at":"2026-07-22T01:23:20.643428+00:00"},{"alias_kind":"pith_short_12","alias_value":"3EHNQDVDBBEK","created_at":"2026-07-22T01:23:20.643428+00:00"},{"alias_kind":"pith_short_16","alias_value":"3EHNQDVDBBEKNNDW","created_at":"2026-07-22T01:23:20.643428+00:00"},{"alias_kind":"pith_short_8","alias_value":"3EHNQDVD","created_at":"2026-07-22T01:23:20.643428+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/3EHNQDVDBBEKNNDWSJZ3QBOX6B","json":"https://pith.science/pith/3EHNQDVDBBEKNNDWSJZ3QBOX6B.json","graph_json":"https://pith.science/api/pith-number/3EHNQDVDBBEKNNDWSJZ3QBOX6B/graph.json","events_json":"https://pith.science/api/pith-number/3EHNQDVDBBEKNNDWSJZ3QBOX6B/events.json","paper":"https://pith.science/paper/3EHNQDVD"},"agent_actions":{"view_html":"https://pith.science/pith/3EHNQDVDBBEKNNDWSJZ3QBOX6B","download_json":"https://pith.science/pith/3EHNQDVDBBEKNNDWSJZ3QBOX6B.json","view_paper":"https://pith.science/paper/3EHNQDVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18934&json=true","fetch_graph":"https://pith.science/api/pith-number/3EHNQDVDBBEKNNDWSJZ3QBOX6B/graph.json","fetch_events":"https://pith.science/api/pith-number/3EHNQDVDBBEKNNDWSJZ3QBOX6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3EHNQDVDBBEKNNDWSJZ3QBOX6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3EHNQDVDBBEKNNDWSJZ3QBOX6B/action/storage_attestation","attest_author":"https://pith.science/pith/3EHNQDVDBBEKNNDWSJZ3QBOX6B/action/author_attestation","sign_citation":"https://pith.science/pith/3EHNQDVDBBEKNNDWSJZ3QBOX6B/action/citation_signature","submit_replication":"https://pith.science/pith/3EHNQDVDBBEKNNDWSJZ3QBOX6B/action/replication_record"}},"created_at":"2026-07-22T01:23:20.643428+00:00","updated_at":"2026-07-22T01:23:20.643428+00:00"}