{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QOZAHQ7ARA7QJ3RBE3567NQPAA","short_pith_number":"pith:QOZAHQ7A","schema_version":"1.0","canonical_sha256":"83b203c3e0883f04ee2126fbefb60f00018960e7d04dace72903df41e66cfc89","source":{"kind":"arxiv","id":"2306.03586","version":1},"attestation_state":"computed","paper":{"title":"Language acquisition: do children and language models follow similar learning stages?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jean-R\\'emi King, Linnea Evanson, Yair Lakretz","submitted_at":"2023-06-06T11:08:20Z","abstract_excerpt":"During language acquisition, children follow a typical sequence of learning stages, whereby they first learn to categorize phonemes before they develop their lexicon and eventually master increasingly complex syntactic structures. However, the computational principles that lead to this learning trajectory remain largely unknown. To investigate this, we here compare the learning trajectories of deep language models to those of children. Specifically, we test whether, during its training, GPT-2 exhibits stages of language acquisition comparable to those observed in children aged between 18 month"},"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":"2306.03586","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-06T11:08:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e1a4a95dd795e420c8f540fa3ec6686509751ddf532298815b7940a54043ecf","abstract_canon_sha256":"ac1a47f1cecd85c789e495fe5f5004aef92f4502f1e7643970c693266ed0a44c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:59.839435Z","signature_b64":"l/BQ6oY2bCZZq1t7tHYbyDaWXar9m6wuzkgnBrCa1VyrIJ2VnINSP4bkpQbEP79FMZhGRKhBuQmn1B7ZYJLSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83b203c3e0883f04ee2126fbefb60f00018960e7d04dace72903df41e66cfc89","last_reissued_at":"2026-07-05T06:17:59.839027Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:59.839027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language acquisition: do children and language models follow similar learning stages?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jean-R\\'emi King, Linnea Evanson, Yair Lakretz","submitted_at":"2023-06-06T11:08:20Z","abstract_excerpt":"During language acquisition, children follow a typical sequence of learning stages, whereby they first learn to categorize phonemes before they develop their lexicon and eventually master increasingly complex syntactic structures. However, the computational principles that lead to this learning trajectory remain largely unknown. To investigate this, we here compare the learning trajectories of deep language models to those of children. Specifically, we test whether, during its training, GPT-2 exhibits stages of language acquisition comparable to those observed in children aged between 18 month"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03586","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/2306.03586/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":"2306.03586","created_at":"2026-07-05T06:17:59.839086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03586v1","created_at":"2026-07-05T06:17:59.839086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03586","created_at":"2026-07-05T06:17:59.839086+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOZAHQ7ARA7Q","created_at":"2026-07-05T06:17:59.839086+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOZAHQ7ARA7QJ3RB","created_at":"2026-07-05T06:17:59.839086+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOZAHQ7A","created_at":"2026-07-05T06:17:59.839086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23520","citing_title":"ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOZAHQ7ARA7QJ3RBE3567NQPAA","json":"https://pith.science/pith/QOZAHQ7ARA7QJ3RBE3567NQPAA.json","graph_json":"https://pith.science/api/pith-number/QOZAHQ7ARA7QJ3RBE3567NQPAA/graph.json","events_json":"https://pith.science/api/pith-number/QOZAHQ7ARA7QJ3RBE3567NQPAA/events.json","paper":"https://pith.science/paper/QOZAHQ7A"},"agent_actions":{"view_html":"https://pith.science/pith/QOZAHQ7ARA7QJ3RBE3567NQPAA","download_json":"https://pith.science/pith/QOZAHQ7ARA7QJ3RBE3567NQPAA.json","view_paper":"https://pith.science/paper/QOZAHQ7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03586&json=true","fetch_graph":"https://pith.science/api/pith-number/QOZAHQ7ARA7QJ3RBE3567NQPAA/graph.json","fetch_events":"https://pith.science/api/pith-number/QOZAHQ7ARA7QJ3RBE3567NQPAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOZAHQ7ARA7QJ3RBE3567NQPAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOZAHQ7ARA7QJ3RBE3567NQPAA/action/storage_attestation","attest_author":"https://pith.science/pith/QOZAHQ7ARA7QJ3RBE3567NQPAA/action/author_attestation","sign_citation":"https://pith.science/pith/QOZAHQ7ARA7QJ3RBE3567NQPAA/action/citation_signature","submit_replication":"https://pith.science/pith/QOZAHQ7ARA7QJ3RBE3567NQPAA/action/replication_record"}},"created_at":"2026-07-05T06:17:59.839086+00:00","updated_at":"2026-07-05T06:17:59.839086+00:00"}