{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:UKLZEKNE25L54G27MMWI655NAR","short_pith_number":"pith:UKLZEKNE","schema_version":"1.0","canonical_sha256":"a2979229a4d757de1b5f632c8f77ad04658182bc95e2fba8d88487d4f7acf917","source":{"kind":"arxiv","id":"1512.08269","version":1},"attestation_state":"computed","paper":{"title":"Statistical and Computational Guarantees for the Baum-Welch Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Fanny Yang, Martin J. Wainwright, Sivaraman Balakrishnan","submitted_at":"2015-12-27T20:10:20Z","abstract_excerpt":"The Hidden Markov Model (HMM) is one of the mainstays of statistical modeling of discrete time series, with applications including speech recognition, computational biology, computer vision and econometrics. Estimating an HMM from its observation process is often addressed via the Baum-Welch algorithm, which is known to be susceptible to local optima. In this paper, we first give a general characterization of the basin of attraction associated with any global optimum of the population likelihood. By exploiting this characterization, we provide non-asymptotic finite sample guarantees on the Bau"},"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":"1512.08269","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-12-27T20:10:20Z","cross_cats_sorted":["cs.IT","math.IT","math.ST","stat.TH"],"title_canon_sha256":"ff1d177eb5d2d8817d6aff3398df1bd23842b98e5b26b129e5106384b06e71b9","abstract_canon_sha256":"45a306049d64c9b14dcf32b686a12810a0c2deac37f83505e163d72c60ee2833"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:42.744771Z","signature_b64":"8VrkoVnfADB8RlwK84WTYYsZGMbj2KOs80wR2+TNiSIHqlJ5mDAv68/hvOKVCA9B1PEysKFesYU2p0V+nXUGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2979229a4d757de1b5f632c8f77ad04658182bc95e2fba8d88487d4f7acf917","last_reissued_at":"2026-05-18T01:23:42.744058Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:42.744058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical and Computational Guarantees for the Baum-Welch Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Fanny Yang, Martin J. Wainwright, Sivaraman Balakrishnan","submitted_at":"2015-12-27T20:10:20Z","abstract_excerpt":"The Hidden Markov Model (HMM) is one of the mainstays of statistical modeling of discrete time series, with applications including speech recognition, computational biology, computer vision and econometrics. Estimating an HMM from its observation process is often addressed via the Baum-Welch algorithm, which is known to be susceptible to local optima. In this paper, we first give a general characterization of the basin of attraction associated with any global optimum of the population likelihood. By exploiting this characterization, we provide non-asymptotic finite sample guarantees on the Bau"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.08269","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":"1512.08269","created_at":"2026-05-18T01:23:42.744180+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.08269v1","created_at":"2026-05-18T01:23:42.744180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.08269","created_at":"2026-05-18T01:23:42.744180+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKLZEKNE25L5","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKLZEKNE25L54G27","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKLZEKNE","created_at":"2026-05-18T12:29:44.643036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23048","citing_title":"StanBKT: Rethinking Parameter Estimation in Bayesian Knowledge Tracing","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UKLZEKNE25L54G27MMWI655NAR","json":"https://pith.science/pith/UKLZEKNE25L54G27MMWI655NAR.json","graph_json":"https://pith.science/api/pith-number/UKLZEKNE25L54G27MMWI655NAR/graph.json","events_json":"https://pith.science/api/pith-number/UKLZEKNE25L54G27MMWI655NAR/events.json","paper":"https://pith.science/paper/UKLZEKNE"},"agent_actions":{"view_html":"https://pith.science/pith/UKLZEKNE25L54G27MMWI655NAR","download_json":"https://pith.science/pith/UKLZEKNE25L54G27MMWI655NAR.json","view_paper":"https://pith.science/paper/UKLZEKNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.08269&json=true","fetch_graph":"https://pith.science/api/pith-number/UKLZEKNE25L54G27MMWI655NAR/graph.json","fetch_events":"https://pith.science/api/pith-number/UKLZEKNE25L54G27MMWI655NAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKLZEKNE25L54G27MMWI655NAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKLZEKNE25L54G27MMWI655NAR/action/storage_attestation","attest_author":"https://pith.science/pith/UKLZEKNE25L54G27MMWI655NAR/action/author_attestation","sign_citation":"https://pith.science/pith/UKLZEKNE25L54G27MMWI655NAR/action/citation_signature","submit_replication":"https://pith.science/pith/UKLZEKNE25L54G27MMWI655NAR/action/replication_record"}},"created_at":"2026-05-18T01:23:42.744180+00:00","updated_at":"2026-05-18T01:23:42.744180+00:00"}