{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YD6FTEDSNJ67XSPZXLRYMFDJPX","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":"0659a7980987392b8b27c3dfd6d51150bea83584cc67a40ee612bc6dc6466c4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T19:04:57Z","title_canon_sha256":"f290ac6ae94b14f5a6fcb1f7a3b5b89c2bc239fb4ea286625da2b1ec7b591ece"},"schema_version":"1.0","source":{"id":"2501.07641","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07641","created_at":"2026-07-05T10:08:27Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07641v2","created_at":"2026-07-05T10:08:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07641","created_at":"2026-07-05T10:08:27Z"},{"alias_kind":"pith_short_12","alias_value":"YD6FTEDSNJ67","created_at":"2026-07-05T10:08:27Z"},{"alias_kind":"pith_short_16","alias_value":"YD6FTEDSNJ67XSPZ","created_at":"2026-07-05T10:08:27Z"},{"alias_kind":"pith_short_8","alias_value":"YD6FTEDS","created_at":"2026-07-05T10:08:27Z"}],"graph_snapshots":[{"event_id":"sha256:182ecb1ac527c79b68afd380ae3aea90a3007873f1cea18f0761520059fc7df2","target":"graph","created_at":"2026-07-05T10:08:27Z","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/2501.07641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), such as GPT, are considered to learn the latent distributions within large-scale web-crawl datasets and accomplish natural language processing (NLP) tasks by predicting the next token. However, this mechanism of latent distribution modeling lacks quantitative understanding and analysis. In this paper, we propose a novel perspective that any language dataset can be represented by a Monte Carlo Language Tree (abbreviated as ``Data-Tree''), where each node denotes a token, each edge denotes a token transition probability, and each sequence has a unique path. Any GPT-","authors_text":"Jia-Yu Yao, Kun-Peng Ning, Li Yuan, Mu-Nan Ning, Yu-Yang Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T19:04:57Z","title":"GPT as a Monte Carlo Language Tree: A Probabilistic Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07641","kind":"arxiv","version":2},"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":"sha256:497e3131844285d146766b1c6b42529da0f8c419431d7f8cb52669ca441876bc","target":"record","created_at":"2026-07-05T10:08:27Z","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":"0659a7980987392b8b27c3dfd6d51150bea83584cc67a40ee612bc6dc6466c4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-13T19:04:57Z","title_canon_sha256":"f290ac6ae94b14f5a6fcb1f7a3b5b89c2bc239fb4ea286625da2b1ec7b591ece"},"schema_version":"1.0","source":{"id":"2501.07641","kind":"arxiv","version":2}},"canonical_sha256":"c0fc5990726a7dfbc9f9bae38614697dd41b25dd5336247eba5ff5e1464d84dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0fc5990726a7dfbc9f9bae38614697dd41b25dd5336247eba5ff5e1464d84dc","first_computed_at":"2026-07-05T10:08:27.613706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:27.613706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mxxLyOWVtXvFY+nOKki0Pdjlw93PCRoAVgw8gB2r+3cojN9NtYBQpKzdQncNSteALzlk4Iljmmz1scfQPwofDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:27.614160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07641","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:497e3131844285d146766b1c6b42529da0f8c419431d7f8cb52669ca441876bc","sha256:182ecb1ac527c79b68afd380ae3aea90a3007873f1cea18f0761520059fc7df2"],"state_sha256":"2d0f071effc97b03a585381d75243f6e3e2e5aa6a03c5debae8147eb225eeefd"}