{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S4KBDX4XVU4FBJK5HDD32BKNHR","short_pith_number":"pith:S4KBDX4X","schema_version":"1.0","canonical_sha256":"971411df97ad3850a55d38c7bd054d3c54903715a9ddce2e87776ceabc77e434","source":{"kind":"arxiv","id":"2501.16241","version":1},"attestation_state":"computed","paper":{"title":"Phase Transitions in Large Language Models and the $O(N)$ Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","hep-th","physics.data-an"],"primary_cat":"cs.LG","authors_text":"Babak Haghighat, Youran Sun","submitted_at":"2025-01-27T17:36:06Z","abstract_excerpt":"Large language models (LLMs) exhibit unprecedentedly rich scaling behaviors. In physics, scaling behavior is closely related to phase transitions, critical phenomena, and field theory. To investigate the phase transition phenomena in LLMs, we reformulated the Transformer architecture as an $O(N)$ model. Our study reveals two distinct phase transitions corresponding to the temperature used in text generation and the model's parameter size, respectively. The first phase transition enables us to estimate the internal dimension of the model, while the second phase transition is of \\textit{higher-d"},"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":"2501.16241","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-27T17:36:06Z","cross_cats_sorted":["cs.CL","hep-th","physics.data-an"],"title_canon_sha256":"039e3a612d7a46723de3a24a23a36c0cf70339f0e5963f3c5cd80388c7080e7a","abstract_canon_sha256":"cde1b025c48d50e24e30b0b34b0e6c9394b9828df5749a6db5db028a4d758dc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:57.193206Z","signature_b64":"brJ/TYixgY0vsjc/7rNcfqCYs2nP0v7mD0w3x+gOfFCIldVw4lyWf8gdbBWzCfaIZ+a7XYrDqc/2XK/89QYjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"971411df97ad3850a55d38c7bd054d3c54903715a9ddce2e87776ceabc77e434","last_reissued_at":"2026-07-05T10:05:57.192640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:57.192640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phase Transitions in Large Language Models and the $O(N)$ Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","hep-th","physics.data-an"],"primary_cat":"cs.LG","authors_text":"Babak Haghighat, Youran Sun","submitted_at":"2025-01-27T17:36:06Z","abstract_excerpt":"Large language models (LLMs) exhibit unprecedentedly rich scaling behaviors. In physics, scaling behavior is closely related to phase transitions, critical phenomena, and field theory. To investigate the phase transition phenomena in LLMs, we reformulated the Transformer architecture as an $O(N)$ model. Our study reveals two distinct phase transitions corresponding to the temperature used in text generation and the model's parameter size, respectively. The first phase transition enables us to estimate the internal dimension of the model, while the second phase transition is of \\textit{higher-d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16241","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/2501.16241/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":"2501.16241","created_at":"2026-07-05T10:05:57.192713+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16241v1","created_at":"2026-07-05T10:05:57.192713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16241","created_at":"2026-07-05T10:05:57.192713+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4KBDX4XVU4F","created_at":"2026-07-05T10:05:57.192713+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4KBDX4XVU4FBJK5","created_at":"2026-07-05T10:05:57.192713+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4KBDX4X","created_at":"2026-07-05T10:05:57.192713+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06238","citing_title":"Generative Criticality in Large Language Model Temperature Scaling","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06394","citing_title":"Lecture Notes on Statistical Physics and Neural Networks","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S4KBDX4XVU4FBJK5HDD32BKNHR","json":"https://pith.science/pith/S4KBDX4XVU4FBJK5HDD32BKNHR.json","graph_json":"https://pith.science/api/pith-number/S4KBDX4XVU4FBJK5HDD32BKNHR/graph.json","events_json":"https://pith.science/api/pith-number/S4KBDX4XVU4FBJK5HDD32BKNHR/events.json","paper":"https://pith.science/paper/S4KBDX4X"},"agent_actions":{"view_html":"https://pith.science/pith/S4KBDX4XVU4FBJK5HDD32BKNHR","download_json":"https://pith.science/pith/S4KBDX4XVU4FBJK5HDD32BKNHR.json","view_paper":"https://pith.science/paper/S4KBDX4X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16241&json=true","fetch_graph":"https://pith.science/api/pith-number/S4KBDX4XVU4FBJK5HDD32BKNHR/graph.json","fetch_events":"https://pith.science/api/pith-number/S4KBDX4XVU4FBJK5HDD32BKNHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4KBDX4XVU4FBJK5HDD32BKNHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4KBDX4XVU4FBJK5HDD32BKNHR/action/storage_attestation","attest_author":"https://pith.science/pith/S4KBDX4XVU4FBJK5HDD32BKNHR/action/author_attestation","sign_citation":"https://pith.science/pith/S4KBDX4XVU4FBJK5HDD32BKNHR/action/citation_signature","submit_replication":"https://pith.science/pith/S4KBDX4XVU4FBJK5HDD32BKNHR/action/replication_record"}},"created_at":"2026-07-05T10:05:57.192713+00:00","updated_at":"2026-07-05T10:05:57.192713+00:00"}