{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HG3HA653OTHWG32KIPUC5XIDXT","short_pith_number":"pith:HG3HA653","schema_version":"1.0","canonical_sha256":"39b6707bbb74cf636f4a43e82edd03bcef3d5a4438a36924929aefa6eb4ddad1","source":{"kind":"arxiv","id":"2406.04289","version":5},"attestation_state":"computed","paper":{"title":"What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anej Svete, Eleanor Chodroff, Franz Nowak, Isabelle Augenstein, Josef Valvoda, Nadav Borenstein, Robin Chan, Ryan Cotterell","submitted_at":"2024-06-06T17:34:24Z","abstract_excerpt":"What can large language models learn? By definition, language models (LM) are distributions over strings. Therefore, an intuitive way of addressing the above question is to formalize it as a matter of learnability of classes of distributions over strings. While prior work in this direction focused on assessing the theoretical limits, in contrast, we seek to understand the empirical learnability. Unlike prior empirical work, we evaluate neural LMs on their home turf-learning probabilistic languages-rather than as classifiers of formal languages. In particular, we investigate the learnability of"},"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":"2406.04289","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T17:34:24Z","cross_cats_sorted":[],"title_canon_sha256":"d443ddb8e7ed2d4f7171fc8e2d1dc07f0b5ec26c3677c5a681fdbbf3523a7a11","abstract_canon_sha256":"ff7e0adcbc46133749ac3585b68d9f56d2e9089c0d57e55248b0ead1e8b222e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:48.091937Z","signature_b64":"Gl0yQRY+HRKC9RVMGjfiP0qeoH1FDg9sBr+mmhEPX2xAVGP1VT0vn52jktXsOwIEMR429sHuxXeZCz8btrexCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39b6707bbb74cf636f4a43e82edd03bcef3d5a4438a36924929aefa6eb4ddad1","last_reissued_at":"2026-07-05T09:59:48.091397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:48.091397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anej Svete, Eleanor Chodroff, Franz Nowak, Isabelle Augenstein, Josef Valvoda, Nadav Borenstein, Robin Chan, Ryan Cotterell","submitted_at":"2024-06-06T17:34:24Z","abstract_excerpt":"What can large language models learn? By definition, language models (LM) are distributions over strings. Therefore, an intuitive way of addressing the above question is to formalize it as a matter of learnability of classes of distributions over strings. While prior work in this direction focused on assessing the theoretical limits, in contrast, we seek to understand the empirical learnability. Unlike prior empirical work, we evaluate neural LMs on their home turf-learning probabilistic languages-rather than as classifiers of formal languages. In particular, we investigate the learnability of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04289","kind":"arxiv","version":5},"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/2406.04289/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":"2406.04289","created_at":"2026-07-05T09:59:48.091467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04289v5","created_at":"2026-07-05T09:59:48.091467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04289","created_at":"2026-07-05T09:59:48.091467+00:00"},{"alias_kind":"pith_short_12","alias_value":"HG3HA653OTHW","created_at":"2026-07-05T09:59:48.091467+00:00"},{"alias_kind":"pith_short_16","alias_value":"HG3HA653OTHWG32K","created_at":"2026-07-05T09:59:48.091467+00:00"},{"alias_kind":"pith_short_8","alias_value":"HG3HA653","created_at":"2026-07-05T09:59:48.091467+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/HG3HA653OTHWG32KIPUC5XIDXT","json":"https://pith.science/pith/HG3HA653OTHWG32KIPUC5XIDXT.json","graph_json":"https://pith.science/api/pith-number/HG3HA653OTHWG32KIPUC5XIDXT/graph.json","events_json":"https://pith.science/api/pith-number/HG3HA653OTHWG32KIPUC5XIDXT/events.json","paper":"https://pith.science/paper/HG3HA653"},"agent_actions":{"view_html":"https://pith.science/pith/HG3HA653OTHWG32KIPUC5XIDXT","download_json":"https://pith.science/pith/HG3HA653OTHWG32KIPUC5XIDXT.json","view_paper":"https://pith.science/paper/HG3HA653","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04289&json=true","fetch_graph":"https://pith.science/api/pith-number/HG3HA653OTHWG32KIPUC5XIDXT/graph.json","fetch_events":"https://pith.science/api/pith-number/HG3HA653OTHWG32KIPUC5XIDXT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HG3HA653OTHWG32KIPUC5XIDXT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HG3HA653OTHWG32KIPUC5XIDXT/action/storage_attestation","attest_author":"https://pith.science/pith/HG3HA653OTHWG32KIPUC5XIDXT/action/author_attestation","sign_citation":"https://pith.science/pith/HG3HA653OTHWG32KIPUC5XIDXT/action/citation_signature","submit_replication":"https://pith.science/pith/HG3HA653OTHWG32KIPUC5XIDXT/action/replication_record"}},"created_at":"2026-07-05T09:59:48.091467+00:00","updated_at":"2026-07-05T09:59:48.091467+00:00"}