{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:1996:KINCGHJWJUDKXBTZBADOA23CXV","short_pith_number":"pith:KINCGHJW","schema_version":"1.0","canonical_sha256":"521a231d364d06ab86790806e06b62bd46fddfb89e86a6517aad28711d53b3a0","source":{"kind":"arxiv","id":"cmp-lg/9611002","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Language Acquisition","license":"","headline":"","cross_cats":["cs.CL"],"primary_cat":"cmp-lg","authors_text":"Carl de Marcken (MIT)","submitted_at":"1996-11-12T19:17:31Z","abstract_excerpt":"This thesis presents a computational theory of unsupervised language acquisition, precisely defining procedures for learning language from ordinary spoken or written utterances, with no explicit help from a teacher. The theory is based heavily on concepts borrowed from machine learning and statistical estimation. In particular, learning takes place by fitting a stochastic, generative model of language to the evidence. Much of the thesis is devoted to explaining conditions that must hold for this general learning strategy to arrive at linguistically desirable grammars. The thesis introduces a v"},"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":"cmp-lg/9611002","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cmp-lg","submitted_at":"1996-11-12T19:17:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9be343be48c9d8ec631a0cfe059a94441940f8a8064f1aad735a22846d77717e","abstract_canon_sha256":"9793aeaa2836197889e203d2ec95e2a07234cfd88bff3e6ed15336b3ff322c93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T15:08:30.024615Z","signature_b64":"pZVh4rc3wZM55zoiiY0ootH+YNzTNt38jK7oU0atAYDCYBu+TsUn1pW6hZG/mJQiVErrx1FKqvJA60sOR+pLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"521a231d364d06ab86790806e06b62bd46fddfb89e86a6517aad28711d53b3a0","last_reissued_at":"2026-07-04T15:08:30.024253Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T15:08:30.024253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Language Acquisition","license":"","headline":"","cross_cats":["cs.CL"],"primary_cat":"cmp-lg","authors_text":"Carl de Marcken (MIT)","submitted_at":"1996-11-12T19:17:31Z","abstract_excerpt":"This thesis presents a computational theory of unsupervised language acquisition, precisely defining procedures for learning language from ordinary spoken or written utterances, with no explicit help from a teacher. The theory is based heavily on concepts borrowed from machine learning and statistical estimation. In particular, learning takes place by fitting a stochastic, generative model of language to the evidence. Much of the thesis is devoted to explaining conditions that must hold for this general learning strategy to arrive at linguistically desirable grammars. The thesis introduces a v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cmp-lg/9611002","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/cmp-lg/9611002/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":"cmp-lg/9611002","created_at":"2026-07-04T15:08:30.024325+00:00"},{"alias_kind":"arxiv_version","alias_value":"cmp-lg/9611002v1","created_at":"2026-07-04T15:08:30.024325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cmp-lg/9611002","created_at":"2026-07-04T15:08:30.024325+00:00"},{"alias_kind":"pith_short_12","alias_value":"KINCGHJWJUDK","created_at":"2026-07-04T15:08:30.024325+00:00"},{"alias_kind":"pith_short_16","alias_value":"KINCGHJWJUDKXBTZ","created_at":"2026-07-04T15:08:30.024325+00:00"},{"alias_kind":"pith_short_8","alias_value":"KINCGHJW","created_at":"2026-07-04T15:08:30.024325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13398","citing_title":"A Minimum Description Length Approach to Regularization in Neural Networks","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KINCGHJWJUDKXBTZBADOA23CXV","json":"https://pith.science/pith/KINCGHJWJUDKXBTZBADOA23CXV.json","graph_json":"https://pith.science/api/pith-number/KINCGHJWJUDKXBTZBADOA23CXV/graph.json","events_json":"https://pith.science/api/pith-number/KINCGHJWJUDKXBTZBADOA23CXV/events.json","paper":"https://pith.science/paper/KINCGHJW"},"agent_actions":{"view_html":"https://pith.science/pith/KINCGHJWJUDKXBTZBADOA23CXV","download_json":"https://pith.science/pith/KINCGHJWJUDKXBTZBADOA23CXV.json","view_paper":"https://pith.science/paper/KINCGHJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cmp-lg/9611002&json=true","fetch_graph":"https://pith.science/api/pith-number/KINCGHJWJUDKXBTZBADOA23CXV/graph.json","fetch_events":"https://pith.science/api/pith-number/KINCGHJWJUDKXBTZBADOA23CXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KINCGHJWJUDKXBTZBADOA23CXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KINCGHJWJUDKXBTZBADOA23CXV/action/storage_attestation","attest_author":"https://pith.science/pith/KINCGHJWJUDKXBTZBADOA23CXV/action/author_attestation","sign_citation":"https://pith.science/pith/KINCGHJWJUDKXBTZBADOA23CXV/action/citation_signature","submit_replication":"https://pith.science/pith/KINCGHJWJUDKXBTZBADOA23CXV/action/replication_record"}},"created_at":"2026-07-04T15:08:30.024325+00:00","updated_at":"2026-07-04T15:08:30.024325+00:00"}