{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EOTUPBEALDPGY5E5Z3NWXMTWA3","short_pith_number":"pith:EOTUPBEA","schema_version":"1.0","canonical_sha256":"23a747848058de6c749dcedb6bb27606e96c6c6750b6d59b56f277205d93997c","source":{"kind":"arxiv","id":"2501.08618","version":1},"attestation_state":"computed","paper":{"title":"Disjoint Processing Mechanisms of Hierarchical and Linear Grammars in Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aaron Mueller, Aruna Sankaranarayanan, Dylan Hadfield-Menell","submitted_at":"2025-01-15T06:34:34Z","abstract_excerpt":"All natural languages are structured hierarchically. In humans, this structural restriction is neurologically coded: when two grammars are presented with identical vocabularies, brain areas responsible for language processing are only sensitive to hierarchical grammars. Using large language models (LLMs), we investigate whether such functionally distinct hierarchical processing regions can arise solely from exposure to large-scale language distributions. We generate inputs using English, Italian, Japanese, or nonce words, varying the underlying grammars to conform to either hierarchical or lin"},"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":"2501.08618","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-15T06:34:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"08fbb4a7378b7251af2f51ace2e70ce8e81bcc91c00f8e52650320cb0bb61f6d","abstract_canon_sha256":"856d773e911a5dea53da5e9945b4503e2bf04338ab3b8499576b10a09229fbd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:22.034196Z","signature_b64":"KxYOcXeXJg/wNG+WTK1nm3lqTP3kxLMl3smg++dBRpBDb8iD83+0LEC3umzDAR7PEyWE3bvoizgPBn1StG4iCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23a747848058de6c749dcedb6bb27606e96c6c6750b6d59b56f277205d93997c","last_reissued_at":"2026-07-05T10:01:22.033756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:22.033756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disjoint Processing Mechanisms of Hierarchical and Linear Grammars in Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aaron Mueller, Aruna Sankaranarayanan, Dylan Hadfield-Menell","submitted_at":"2025-01-15T06:34:34Z","abstract_excerpt":"All natural languages are structured hierarchically. In humans, this structural restriction is neurologically coded: when two grammars are presented with identical vocabularies, brain areas responsible for language processing are only sensitive to hierarchical grammars. Using large language models (LLMs), we investigate whether such functionally distinct hierarchical processing regions can arise solely from exposure to large-scale language distributions. We generate inputs using English, Italian, Japanese, or nonce words, varying the underlying grammars to conform to either hierarchical or lin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08618","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/2501.08618/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":"2501.08618","created_at":"2026-07-05T10:01:22.033817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08618v1","created_at":"2026-07-05T10:01:22.033817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08618","created_at":"2026-07-05T10:01:22.033817+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOTUPBEALDPG","created_at":"2026-07-05T10:01:22.033817+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOTUPBEALDPGY5E5","created_at":"2026-07-05T10:01:22.033817+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOTUPBEA","created_at":"2026-07-05T10:01:22.033817+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07631","citing_title":"Inference Time Causal Probing in LLMs","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EOTUPBEALDPGY5E5Z3NWXMTWA3","json":"https://pith.science/pith/EOTUPBEALDPGY5E5Z3NWXMTWA3.json","graph_json":"https://pith.science/api/pith-number/EOTUPBEALDPGY5E5Z3NWXMTWA3/graph.json","events_json":"https://pith.science/api/pith-number/EOTUPBEALDPGY5E5Z3NWXMTWA3/events.json","paper":"https://pith.science/paper/EOTUPBEA"},"agent_actions":{"view_html":"https://pith.science/pith/EOTUPBEALDPGY5E5Z3NWXMTWA3","download_json":"https://pith.science/pith/EOTUPBEALDPGY5E5Z3NWXMTWA3.json","view_paper":"https://pith.science/paper/EOTUPBEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08618&json=true","fetch_graph":"https://pith.science/api/pith-number/EOTUPBEALDPGY5E5Z3NWXMTWA3/graph.json","fetch_events":"https://pith.science/api/pith-number/EOTUPBEALDPGY5E5Z3NWXMTWA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOTUPBEALDPGY5E5Z3NWXMTWA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOTUPBEALDPGY5E5Z3NWXMTWA3/action/storage_attestation","attest_author":"https://pith.science/pith/EOTUPBEALDPGY5E5Z3NWXMTWA3/action/author_attestation","sign_citation":"https://pith.science/pith/EOTUPBEALDPGY5E5Z3NWXMTWA3/action/citation_signature","submit_replication":"https://pith.science/pith/EOTUPBEALDPGY5E5Z3NWXMTWA3/action/replication_record"}},"created_at":"2026-07-05T10:01:22.033817+00:00","updated_at":"2026-07-05T10:01:22.033817+00:00"}