{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YWMPEC5MTBWWH2CYFWVCTGAPBM","short_pith_number":"pith:YWMPEC5M","schema_version":"1.0","canonical_sha256":"c598f20bac986d63e8582daa29980f0b2563ff19342d304656fc239b11825f89","source":{"kind":"arxiv","id":"2402.01825","version":2},"attestation_state":"computed","paper":{"title":"Fractal Patterns May Illuminate the Success of Next-Token Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ibrahim Alabdulmohsin, Mostafa Dehghani, Vinh Q. Tran","submitted_at":"2024-02-02T17:09:33Z","abstract_excerpt":"We study the fractal structure of language, aiming to provide a precise formalism for quantifying properties that may have been previously suspected but not formally shown. We establish that language is: (1) self-similar, exhibiting complexities at all levels of granularity, with no particular characteristic context length, and (2) long-range dependent (LRD), with a Hurst parameter of approximately H=0.7. Based on these findings, we argue that short-term patterns/dependencies in language, such as in paragraphs, mirror the patterns/dependencies over larger scopes, like entire documents. This ma"},"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":"2402.01825","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T17:09:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1a400cd9b310e106a87eb0653a66f041d41b01fa62baa37c234e51ce400573bb","abstract_canon_sha256":"3e9b8eeb51f6109901d66802c66c7ce8edbfe5f02f2d1cf8b1a0d703177f16da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:49.136350Z","signature_b64":"ooRpif23QN+f8ywWqB6j3dbDk0j0wRdIAkWK3QTjINeg6KrU8XdADSxL24L09aw/YXPh67DZ0HH3gn8btQ1BDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c598f20bac986d63e8582daa29980f0b2563ff19342d304656fc239b11825f89","last_reissued_at":"2026-07-05T08:21:49.135895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:49.135895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fractal Patterns May Illuminate the Success of Next-Token Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ibrahim Alabdulmohsin, Mostafa Dehghani, Vinh Q. Tran","submitted_at":"2024-02-02T17:09:33Z","abstract_excerpt":"We study the fractal structure of language, aiming to provide a precise formalism for quantifying properties that may have been previously suspected but not formally shown. We establish that language is: (1) self-similar, exhibiting complexities at all levels of granularity, with no particular characteristic context length, and (2) long-range dependent (LRD), with a Hurst parameter of approximately H=0.7. Based on these findings, we argue that short-term patterns/dependencies in language, such as in paragraphs, mirror the patterns/dependencies over larger scopes, like entire documents. This ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01825","kind":"arxiv","version":2},"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/2402.01825/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":"2402.01825","created_at":"2026-07-05T08:21:49.135971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01825v2","created_at":"2026-07-05T08:21:49.135971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01825","created_at":"2026-07-05T08:21:49.135971+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWMPEC5MTBWW","created_at":"2026-07-05T08:21:49.135971+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWMPEC5MTBWWH2CY","created_at":"2026-07-05T08:21:49.135971+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWMPEC5M","created_at":"2026-07-05T08:21:49.135971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YWMPEC5MTBWWH2CYFWVCTGAPBM","json":"https://pith.science/pith/YWMPEC5MTBWWH2CYFWVCTGAPBM.json","graph_json":"https://pith.science/api/pith-number/YWMPEC5MTBWWH2CYFWVCTGAPBM/graph.json","events_json":"https://pith.science/api/pith-number/YWMPEC5MTBWWH2CYFWVCTGAPBM/events.json","paper":"https://pith.science/paper/YWMPEC5M"},"agent_actions":{"view_html":"https://pith.science/pith/YWMPEC5MTBWWH2CYFWVCTGAPBM","download_json":"https://pith.science/pith/YWMPEC5MTBWWH2CYFWVCTGAPBM.json","view_paper":"https://pith.science/paper/YWMPEC5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01825&json=true","fetch_graph":"https://pith.science/api/pith-number/YWMPEC5MTBWWH2CYFWVCTGAPBM/graph.json","fetch_events":"https://pith.science/api/pith-number/YWMPEC5MTBWWH2CYFWVCTGAPBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWMPEC5MTBWWH2CYFWVCTGAPBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWMPEC5MTBWWH2CYFWVCTGAPBM/action/storage_attestation","attest_author":"https://pith.science/pith/YWMPEC5MTBWWH2CYFWVCTGAPBM/action/author_attestation","sign_citation":"https://pith.science/pith/YWMPEC5MTBWWH2CYFWVCTGAPBM/action/citation_signature","submit_replication":"https://pith.science/pith/YWMPEC5MTBWWH2CYFWVCTGAPBM/action/replication_record"}},"created_at":"2026-07-05T08:21:49.135971+00:00","updated_at":"2026-07-05T08:21:49.135971+00:00"}