{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DGQZNJEEWDOUZYBQWAG5GFCWCI","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":"ee10239a0ee8077ab5b7a007114fbb52e33801c0bbef1a3c7b465b166f580bf6","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T17:01:22Z","title_canon_sha256":"78b71155938f87dbbf6f36ad1d13925d6e2cff97b4ac4e3e125af48a3250eaea"},"schema_version":"1.0","source":{"id":"2406.00048","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00048","created_at":"2026-07-05T09:27:54Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00048v3","created_at":"2026-07-05T09:27:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00048","created_at":"2026-07-05T09:27:54Z"},{"alias_kind":"pith_short_12","alias_value":"DGQZNJEEWDOU","created_at":"2026-07-05T09:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"DGQZNJEEWDOUZYBQ","created_at":"2026-07-05T09:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"DGQZNJEE","created_at":"2026-07-05T09:27:54Z"}],"graph_snapshots":[{"event_id":"sha256:f31fee414e17daaaa3e7b86db988452f7495bdc684fbc63b5250c3d054fe17a8","target":"graph","created_at":"2026-07-05T09:27:54Z","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/2406.00048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How much data is required to learn the structure of a language via next-token prediction? We study this question for synthetic datasets generated via a Probabilistic Context-Free Grammar (PCFG) -- a tree-like generative model that captures many of the hierarchical structures found in natural languages. We determine token-token correlations analytically in our model and show that they can be used to build a representation of the grammar's hidden variables, the longer the range the deeper the variable. In addition, a finite training set limits the resolution of correlations to an effective range","authors_text":"Francesco Cagnetta, Matthieu Wyart","cross_cats":["cond-mat.dis-nn","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T17:01:22Z","title":"Towards a theory of how the structure of language is acquired by deep neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00048","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:a483f1d4bf4225fb865fa273533694ec117276608d5742cfeddcadb9c343cb4a","target":"record","created_at":"2026-07-05T09:27:54Z","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":"ee10239a0ee8077ab5b7a007114fbb52e33801c0bbef1a3c7b465b166f580bf6","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T17:01:22Z","title_canon_sha256":"78b71155938f87dbbf6f36ad1d13925d6e2cff97b4ac4e3e125af48a3250eaea"},"schema_version":"1.0","source":{"id":"2406.00048","kind":"arxiv","version":3}},"canonical_sha256":"19a196a484b0dd4ce030b00dd31456121f152ee524e41306fac20dafdb06c07c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19a196a484b0dd4ce030b00dd31456121f152ee524e41306fac20dafdb06c07c","first_computed_at":"2026-07-05T09:27:54.725356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:54.725356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BhC9dZBIXtOCqv2CDlC5awbohZK/vmG1PNNEcKdQNORem/3baznpVYCSVTn6p9dgeTZnRNGt44ez9BsbCIUaDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:54.725861Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00048","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a483f1d4bf4225fb865fa273533694ec117276608d5742cfeddcadb9c343cb4a","sha256:f31fee414e17daaaa3e7b86db988452f7495bdc684fbc63b5250c3d054fe17a8"],"state_sha256":"71621999bf60eeb345b5efe789405962d2246a2e6642687ec8ccdded07b1a17d"}