{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O2IOEKP53JKJ54QPO2AGLKRXJM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9a4b6e3b3fe7d47733de2c5ad62cb0741f440dae00e76cd6e8aec59b4b647d15","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T20:35:10Z","title_canon_sha256":"3638283d80d395fd031501f90f9cda90e878ec21a493e5b62845d56c02f572d7"},"schema_version":"1.0","source":{"id":"2403.19827","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19827","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19827v3","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19827","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"pith_short_12","alias_value":"O2IOEKP53JKJ","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"pith_short_16","alias_value":"O2IOEKP53JKJ54QP","created_at":"2026-07-05T11:26:42Z"},{"alias_kind":"pith_short_8","alias_value":"O2IOEKP5","created_at":"2026-07-05T11:26:42Z"}],"graph_snapshots":[{"event_id":"sha256:ff35f58568ed4c596a5981fc323e5fb8560cc0e98a5ded9bbf65190e9ce75b7b","target":"graph","created_at":"2026-07-05T11:26:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.19827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models learn rare syntactic phenomena, but the extent to which this is attributable to generalization vs. memorization is a major open question. To that end, we iteratively trained transformer language models on systematically manipulated corpora which were human-scale in size, and then evaluated their learning of a rare grammatical phenomenon: the English Article+Adjective+Numeral+Noun (AANN) construction (``a beautiful five days''). We compared how well this construction was learned on the default corpus relative to a counterfactual corpus in which AANN sentences were removed. We fo","authors_text":"Kanishka Misra, Kyle Mahowald","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T20:35:10Z","title":"Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19827","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a4781b5142c220e44b8b5a68aa68e1dbf72987d0781c14bc4962f6d5f9922227","target":"record","created_at":"2026-07-05T11:26:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9a4b6e3b3fe7d47733de2c5ad62cb0741f440dae00e76cd6e8aec59b4b647d15","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T20:35:10Z","title_canon_sha256":"3638283d80d395fd031501f90f9cda90e878ec21a493e5b62845d56c02f572d7"},"schema_version":"1.0","source":{"id":"2403.19827","kind":"arxiv","version":3}},"canonical_sha256":"7690e229fdda549ef20f768065aa374b141705ea0248dc009902403b817a3ff5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7690e229fdda549ef20f768065aa374b141705ea0248dc009902403b817a3ff5","first_computed_at":"2026-07-05T11:26:42.231488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:42.231488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8ZosaQbruLFyqy4QAysiW1+wt67lUgvUAnV+K5wBGMWuET27eV0aEQJapQ9a5zN7bOC1Y5WzKXR3aQUjORmQCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:42.232022Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19827","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4781b5142c220e44b8b5a68aa68e1dbf72987d0781c14bc4962f6d5f9922227","sha256:ff35f58568ed4c596a5981fc323e5fb8560cc0e98a5ded9bbf65190e9ce75b7b"],"state_sha256":"bd1c7169bfc668d992aa61ff4b9935f942239d6e44d78b3a3598d10fa0ce865c"}