{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2009:MEKXXV4WXW3MMUA6RRHNZ3HCRT","short_pith_number":"pith:MEKXXV4W","schema_version":"1.0","canonical_sha256":"61157bd796bdb6c6501e8c4edcece28cec4edf767ccbcce3739f04fc82f59494","source":{"kind":"arxiv","id":"0911.3944","version":1},"attestation_state":"computed","paper":{"title":"Likelihood-based semi-supervised model selection with applications to speech processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","stat.AP"],"primary_cat":"stat.ML","authors_text":"Christopher M. White, Patrick J. Wolfe, Sanjeev P. Khudanpur","submitted_at":"2009-11-20T01:30:36Z","abstract_excerpt":"In conventional supervised pattern recognition tasks, model selection is typically accomplished by minimizing the classification error rate on a set of so-called development data, subject to ground-truth labeling by human experts or some other means. In the context of speech processing systems and other large-scale practical applications, however, such labeled development data are typically costly and difficult to obtain. This article proposes an alternative semi-supervised framework for likelihood-based model selection that leverages unlabeled data by using trained classifiers representing ea"},"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":"0911.3944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2009-11-20T01:30:36Z","cross_cats_sorted":["cs.CL","cs.LG","stat.AP"],"title_canon_sha256":"d194141290e392b29ddebe4e17be19dcebdc4b71af22bf677f9d16bec8a1a652","abstract_canon_sha256":"74fae6776a619f1f2e676beb3aec7b606646809fe65e8c06ef00fa590d0bc210"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:14:53.628803Z","signature_b64":"t/PVJYIZouedb9bD8ExEWeEywUmgxjWmK9vAup+xoC0FgRlqKBHLq4t9KIwkn4nxozfNAkyzDQp2KUfkExDJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61157bd796bdb6c6501e8c4edcece28cec4edf767ccbcce3739f04fc82f59494","last_reissued_at":"2026-05-18T04:14:53.628064Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:14:53.628064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Likelihood-based semi-supervised model selection with applications to speech processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","stat.AP"],"primary_cat":"stat.ML","authors_text":"Christopher M. White, Patrick J. Wolfe, Sanjeev P. Khudanpur","submitted_at":"2009-11-20T01:30:36Z","abstract_excerpt":"In conventional supervised pattern recognition tasks, model selection is typically accomplished by minimizing the classification error rate on a set of so-called development data, subject to ground-truth labeling by human experts or some other means. In the context of speech processing systems and other large-scale practical applications, however, such labeled development data are typically costly and difficult to obtain. This article proposes an alternative semi-supervised framework for likelihood-based model selection that leverages unlabeled data by using trained classifiers representing ea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0911.3944","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":""},"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":"0911.3944","created_at":"2026-05-18T04:14:53.628206+00:00"},{"alias_kind":"arxiv_version","alias_value":"0911.3944v1","created_at":"2026-05-18T04:14:53.628206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0911.3944","created_at":"2026-05-18T04:14:53.628206+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEKXXV4WXW3M","created_at":"2026-05-18T12:26:00.592388+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEKXXV4WXW3MMUA6","created_at":"2026-05-18T12:26:00.592388+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEKXXV4W","created_at":"2026-05-18T12:26:00.592388+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/MEKXXV4WXW3MMUA6RRHNZ3HCRT","json":"https://pith.science/pith/MEKXXV4WXW3MMUA6RRHNZ3HCRT.json","graph_json":"https://pith.science/api/pith-number/MEKXXV4WXW3MMUA6RRHNZ3HCRT/graph.json","events_json":"https://pith.science/api/pith-number/MEKXXV4WXW3MMUA6RRHNZ3HCRT/events.json","paper":"https://pith.science/paper/MEKXXV4W"},"agent_actions":{"view_html":"https://pith.science/pith/MEKXXV4WXW3MMUA6RRHNZ3HCRT","download_json":"https://pith.science/pith/MEKXXV4WXW3MMUA6RRHNZ3HCRT.json","view_paper":"https://pith.science/paper/MEKXXV4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=0911.3944&json=true","fetch_graph":"https://pith.science/api/pith-number/MEKXXV4WXW3MMUA6RRHNZ3HCRT/graph.json","fetch_events":"https://pith.science/api/pith-number/MEKXXV4WXW3MMUA6RRHNZ3HCRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEKXXV4WXW3MMUA6RRHNZ3HCRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEKXXV4WXW3MMUA6RRHNZ3HCRT/action/storage_attestation","attest_author":"https://pith.science/pith/MEKXXV4WXW3MMUA6RRHNZ3HCRT/action/author_attestation","sign_citation":"https://pith.science/pith/MEKXXV4WXW3MMUA6RRHNZ3HCRT/action/citation_signature","submit_replication":"https://pith.science/pith/MEKXXV4WXW3MMUA6RRHNZ3HCRT/action/replication_record"}},"created_at":"2026-05-18T04:14:53.628206+00:00","updated_at":"2026-05-18T04:14:53.628206+00:00"}