{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E3JT3FVOBVDRQW5OMDOS4SXALY","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":"2fee804c2f462cac2d06bfbf70158affc3cb82d2ecfbe0ae4836d479bd5bcf6d","cross_cats_sorted":["cs.FL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-02T19:52:19Z","title_canon_sha256":"daab4cf1cf9119dee23700ab8db676777c32fc8dc8744045dd015cb37b2f7791"},"schema_version":"1.0","source":{"id":"2510.02524","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.02524","created_at":"2026-06-12T00:07:48Z"},{"alias_kind":"arxiv_version","alias_value":"2510.02524v3","created_at":"2026-06-12T00:07:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.02524","created_at":"2026-06-12T00:07:48Z"},{"alias_kind":"pith_short_12","alias_value":"E3JT3FVOBVDR","created_at":"2026-06-12T00:07:48Z"},{"alias_kind":"pith_short_16","alias_value":"E3JT3FVOBVDRQW5O","created_at":"2026-06-12T00:07:48Z"},{"alias_kind":"pith_short_8","alias_value":"E3JT3FVO","created_at":"2026-06-12T00:07:48Z"}],"graph_snapshots":[{"event_id":"sha256:8f853787d3e79b9024e4cf300f70a96e9aaca14d14d8c13d61cff9560411a2f8","target":"graph","created_at":"2026-06-12T00:07:48Z","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/2510.02524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While language models achieve impressive results, their learning dynamics are far from understood. Many domains of interest -- such as natural language syntax, coding languages, arithmetic -- are captured by context-free grammars (CFGs). In this work, we extend prior work on neural language modeling of CFGs in a novel direction: how language modeling behaves with respect to CFG substructure, namely subgrammars. We define subgrammars, and prove a set of fundamental theorems connecting language modeling and subgrammars. We show that language modeling loss recurses linearly over its top-level sub","authors_text":"Daniel Mitropolsky, Laura Ying Schulz, Tomaso Poggio","cross_cats":["cs.FL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-02T19:52:19Z","title":"Unraveling Syntax: Language Modeling and the Substructure of Grammars"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.02524","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":"sha256:7da4711facd7a20f33bd0542c951eb0ef0217167450e50a502a07fba293e224b","target":"record","created_at":"2026-06-12T00:07:48Z","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":"2fee804c2f462cac2d06bfbf70158affc3cb82d2ecfbe0ae4836d479bd5bcf6d","cross_cats_sorted":["cs.FL","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-02T19:52:19Z","title_canon_sha256":"daab4cf1cf9119dee23700ab8db676777c32fc8dc8744045dd015cb37b2f7791"},"schema_version":"1.0","source":{"id":"2510.02524","kind":"arxiv","version":3}},"canonical_sha256":"26d33d96ae0d47185bae60dd2e4ae05e2942f2d59350112583897820fdaab78c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26d33d96ae0d47185bae60dd2e4ae05e2942f2d59350112583897820fdaab78c","first_computed_at":"2026-06-12T00:07:48.319769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T00:07:48.319769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7MFJsy4mLKU/XcbfbWMfAADhLFwtN5Fp1LztH36MZP8uV6/NxRPEx7cBr/BHN3Lz7zaEFO2CsV7qJlk7tEOvBA==","signature_status":"signed_v1","signed_at":"2026-06-12T00:07:48.320283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.02524","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7da4711facd7a20f33bd0542c951eb0ef0217167450e50a502a07fba293e224b","sha256:8f853787d3e79b9024e4cf300f70a96e9aaca14d14d8c13d61cff9560411a2f8"],"state_sha256":"ca858895b799ae68971391d087d2e5b9871950e8fb05cb310ca8ab7a101fa8c8"}