{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:E3JT3FVOBVDRQW5OMDOS4SXALY","short_pith_number":"pith:E3JT3FVO","canonical_record":{"source":{"id":"2510.02524","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-02T19:52:19Z","cross_cats_sorted":["cs.FL","cs.LG"],"title_canon_sha256":"daab4cf1cf9119dee23700ab8db676777c32fc8dc8744045dd015cb37b2f7791","abstract_canon_sha256":"2fee804c2f462cac2d06bfbf70158affc3cb82d2ecfbe0ae4836d479bd5bcf6d"},"schema_version":"1.0"},"canonical_sha256":"26d33d96ae0d47185bae60dd2e4ae05e2942f2d59350112583897820fdaab78c","source":{"kind":"arxiv","id":"2510.02524","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:E3JT3FVOBVDRQW5OMDOS4SXALY","target":"record","payload":{"canonical_record":{"source":{"id":"2510.02524","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-02T19:52:19Z","cross_cats_sorted":["cs.FL","cs.LG"],"title_canon_sha256":"daab4cf1cf9119dee23700ab8db676777c32fc8dc8744045dd015cb37b2f7791","abstract_canon_sha256":"2fee804c2f462cac2d06bfbf70158affc3cb82d2ecfbe0ae4836d479bd5bcf6d"},"schema_version":"1.0"},"canonical_sha256":"26d33d96ae0d47185bae60dd2e4ae05e2942f2d59350112583897820fdaab78c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T00:07:48.320283Z","signature_b64":"7MFJsy4mLKU/XcbfbWMfAADhLFwtN5Fp1LztH36MZP8uV6/NxRPEx7cBr/BHN3Lz7zaEFO2CsV7qJlk7tEOvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26d33d96ae0d47185bae60dd2e4ae05e2942f2d59350112583897820fdaab78c","last_reissued_at":"2026-06-12T00:07:48.319769Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T00:07:48.319769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.02524","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-12T00:07:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j8I6BvPKKFqaquxHfBh4CIXxtIeza6+SBAPEcnsbCBToEXEfFP9kNeVuSP9RntWo2v8SLlEuCzirD542D8wmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T17:04:12.972023Z"},"content_sha256":"7da4711facd7a20f33bd0542c951eb0ef0217167450e50a502a07fba293e224b","schema_version":"1.0","event_id":"sha256:7da4711facd7a20f33bd0542c951eb0ef0217167450e50a502a07fba293e224b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:E3JT3FVOBVDRQW5OMDOS4SXALY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unraveling Syntax: Language Modeling and the Substructure of Grammars","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.FL","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel Mitropolsky, Laura Ying Schulz, Tomaso Poggio","submitted_at":"2025-10-02T19:52:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.02524","kind":"arxiv","version":3},"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/2510.02524/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-12T00:07:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TN5O0jmzsV6TUsvR/ShzRnfpPLQofP0kPpkVhvs2ARPheBArkL1Ne/AQIUZ3Fo/lUveotqujAFeoj2fhgHBUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T17:04:12.972423Z"},"content_sha256":"8f853787d3e79b9024e4cf300f70a96e9aaca14d14d8c13d61cff9560411a2f8","schema_version":"1.0","event_id":"sha256:8f853787d3e79b9024e4cf300f70a96e9aaca14d14d8c13d61cff9560411a2f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E3JT3FVOBVDRQW5OMDOS4SXALY/bundle.json","state_url":"https://pith.science/pith/E3JT3FVOBVDRQW5OMDOS4SXALY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E3JT3FVOBVDRQW5OMDOS4SXALY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-30T17:04:12Z","links":{"resolver":"https://pith.science/pith/E3JT3FVOBVDRQW5OMDOS4SXALY","bundle":"https://pith.science/pith/E3JT3FVOBVDRQW5OMDOS4SXALY/bundle.json","state":"https://pith.science/pith/E3JT3FVOBVDRQW5OMDOS4SXALY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E3JT3FVOBVDRQW5OMDOS4SXALY/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wadpWZzjGHa/xxGk3Gq5/3i+M2ETe/Awofwwkmyk7pvgEd0oYMf9RziSbXrHkCXMC2rJiLCxt13Tbc9Nw/t8Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T17:04:12.974405Z","bundle_sha256":"839c7d631fe2e44b7f79479e2172fe48eed5595e641342f80a9179069216e8bd"}}