{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XNTJLU7XY6BHU7DBAJE3IMLN5X","short_pith_number":"pith:XNTJLU7X","schema_version":"1.0","canonical_sha256":"bb6695d3f7c7827a7c610249b4316dede8457fceda98b29008a3fdb6e1eb0402","source":{"kind":"arxiv","id":"2411.00660","version":2},"attestation_state":"computed","paper":{"title":"Physics in Next-token Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hongjun An, Xuelong Li, Yiliang Song","submitted_at":"2024-11-01T15:26:15Z","abstract_excerpt":"We discovered the underlying physics in Next-token Prediction (NTP). We identified the law of information conservation within NTP and proposed the First Law of Information Capacity (IC-1), demonstrating that the essence of intelligence emergence in auto-regressive models is fundamentally a process of information transfer. We also introduced Landauer's Principle into NTP, formulating the Second Law of Information Capacity (IC-2), which establishes the relationship between auto-regressive model training and energy consumption. Additionally, we presented several corollaries, which hold practical "},"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":"2411.00660","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T15:26:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"107b56ab4cba8e2cb8bdfa24ad903d7c8d8d430564a6805a79a07667c9f2cc1d","abstract_canon_sha256":"1fb105faf3914fd6b096c99a287fd443d751233925ca17682493f865b6d229b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:15.752832Z","signature_b64":"YSeB+SEJJNydohEvmbmoJia87HIjtRMr5vVXqUHSU5BcRtNAtFY6aIRnW2n2tGNyRr99oXoCDAhNjaNexvPBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb6695d3f7c7827a7c610249b4316dede8457fceda98b29008a3fdb6e1eb0402","last_reissued_at":"2026-07-05T09:36:15.752360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:15.752360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Physics in Next-token Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hongjun An, Xuelong Li, Yiliang Song","submitted_at":"2024-11-01T15:26:15Z","abstract_excerpt":"We discovered the underlying physics in Next-token Prediction (NTP). We identified the law of information conservation within NTP and proposed the First Law of Information Capacity (IC-1), demonstrating that the essence of intelligence emergence in auto-regressive models is fundamentally a process of information transfer. We also introduced Landauer's Principle into NTP, formulating the Second Law of Information Capacity (IC-2), which establishes the relationship between auto-regressive model training and energy consumption. Additionally, we presented several corollaries, which hold practical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00660","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/2411.00660/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":"2411.00660","created_at":"2026-07-05T09:36:15.752424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00660v2","created_at":"2026-07-05T09:36:15.752424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00660","created_at":"2026-07-05T09:36:15.752424+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNTJLU7XY6BH","created_at":"2026-07-05T09:36:15.752424+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNTJLU7XY6BHU7DB","created_at":"2026-07-05T09:36:15.752424+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNTJLU7X","created_at":"2026-07-05T09:36:15.752424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06042","citing_title":"Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNTJLU7XY6BHU7DBAJE3IMLN5X","json":"https://pith.science/pith/XNTJLU7XY6BHU7DBAJE3IMLN5X.json","graph_json":"https://pith.science/api/pith-number/XNTJLU7XY6BHU7DBAJE3IMLN5X/graph.json","events_json":"https://pith.science/api/pith-number/XNTJLU7XY6BHU7DBAJE3IMLN5X/events.json","paper":"https://pith.science/paper/XNTJLU7X"},"agent_actions":{"view_html":"https://pith.science/pith/XNTJLU7XY6BHU7DBAJE3IMLN5X","download_json":"https://pith.science/pith/XNTJLU7XY6BHU7DBAJE3IMLN5X.json","view_paper":"https://pith.science/paper/XNTJLU7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00660&json=true","fetch_graph":"https://pith.science/api/pith-number/XNTJLU7XY6BHU7DBAJE3IMLN5X/graph.json","fetch_events":"https://pith.science/api/pith-number/XNTJLU7XY6BHU7DBAJE3IMLN5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNTJLU7XY6BHU7DBAJE3IMLN5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNTJLU7XY6BHU7DBAJE3IMLN5X/action/storage_attestation","attest_author":"https://pith.science/pith/XNTJLU7XY6BHU7DBAJE3IMLN5X/action/author_attestation","sign_citation":"https://pith.science/pith/XNTJLU7XY6BHU7DBAJE3IMLN5X/action/citation_signature","submit_replication":"https://pith.science/pith/XNTJLU7XY6BHU7DBAJE3IMLN5X/action/replication_record"}},"created_at":"2026-07-05T09:36:15.752424+00:00","updated_at":"2026-07-05T09:36:15.752424+00:00"}