{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CBUFUHO2NNOCQYELWD3TBXFFGN","short_pith_number":"pith:CBUFUHO2","canonical_record":{"source":{"id":"2310.13571","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T15:09:46Z","cross_cats_sorted":[],"title_canon_sha256":"dfba042cd15255f900b2b387a34adfd21acb6ca89e581fcad5827c381f799afd","abstract_canon_sha256":"10cdbfdb0870beac38dbea453ad48ce3a0eae834bc9214a36555824b89bd72bb"},"schema_version":"1.0"},"canonical_sha256":"10685a1dda6b5c28608bb0f730dca53351f0abfcc78d69175f8ad85c79fd94b6","source":{"kind":"arxiv","id":"2310.13571","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13571","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13571v4","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13571","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"CBUFUHO2NNOC","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"CBUFUHO2NNOCQYEL","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"CBUFUHO2","created_at":"2026-07-05T08:28:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CBUFUHO2NNOCQYELWD3TBXFFGN","target":"record","payload":{"canonical_record":{"source":{"id":"2310.13571","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T15:09:46Z","cross_cats_sorted":[],"title_canon_sha256":"dfba042cd15255f900b2b387a34adfd21acb6ca89e581fcad5827c381f799afd","abstract_canon_sha256":"10cdbfdb0870beac38dbea453ad48ce3a0eae834bc9214a36555824b89bd72bb"},"schema_version":"1.0"},"canonical_sha256":"10685a1dda6b5c28608bb0f730dca53351f0abfcc78d69175f8ad85c79fd94b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:03.294369Z","signature_b64":"Vx+q3u0SsIjM29MgqPzIrSgWnZMdv1zP2TrWTzFRzaCM8sQejMLCFeYQYEpcpnBtca5Fi+fmBSNJZeOpkNQoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10685a1dda6b5c28608bb0f730dca53351f0abfcc78d69175f8ad85c79fd94b6","last_reissued_at":"2026-07-05T08:28:03.293944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:03.293944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.13571","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+TQJ86uvDTDDYFXMAm9dsvBcy9jOsTL5hIIW6oi+VmmfMhnIFMjVzenLLJyL6jW+wh1k1++ZP5EFtjB51w12BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:56:07.252932Z"},"content_sha256":"1965bae3be004126ff0167befad54e77892776c76b44735923870cb355626f76","schema_version":"1.0","event_id":"sha256:1965bae3be004126ff0167befad54e77892776c76b44735923870cb355626f76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CBUFUHO2NNOCQYELWD3TBXFFGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Can Large Language Models Generate Correct Chain-of-Thoughts?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antoine Grosnit, Haitham Bou-Ammar, Juliusz Ziomek, Jun Wang, Rasul Tutunov","submitted_at":"2023-10-20T15:09:46Z","abstract_excerpt":"This paper delves into the capabilities of large language models (LLMs), specifically focusing on advancing the theoretical comprehension of chain-of-thought prompting. We investigate how LLMs can be effectively induced to generate a coherent chain of thoughts. To achieve this, we introduce a two-level hierarchical graphical model tailored for natural language generation. Within this framework, we establish a compelling geometrical convergence rate that gauges the likelihood of an LLM-generated chain of thoughts compared to those originating from the true language. Our findings provide a theor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13571","kind":"arxiv","version":4},"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/2310.13571/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wYqPMU3dpMcfWaWH5iYT6bV6SA2sYbJXJJKWjh5UqL/95DN+7jyyB7/xvgbpq42rCQVldO/KukT1OG/4nkRtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:56:07.253298Z"},"content_sha256":"67dc411f8029bc42275ae90872a3580678de4ab2968dab5241bf32088f5046c7","schema_version":"1.0","event_id":"sha256:67dc411f8029bc42275ae90872a3580678de4ab2968dab5241bf32088f5046c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CBUFUHO2NNOCQYELWD3TBXFFGN/bundle.json","state_url":"https://pith.science/pith/CBUFUHO2NNOCQYELWD3TBXFFGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CBUFUHO2NNOCQYELWD3TBXFFGN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T09:56:07Z","links":{"resolver":"https://pith.science/pith/CBUFUHO2NNOCQYELWD3TBXFFGN","bundle":"https://pith.science/pith/CBUFUHO2NNOCQYELWD3TBXFFGN/bundle.json","state":"https://pith.science/pith/CBUFUHO2NNOCQYELWD3TBXFFGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CBUFUHO2NNOCQYELWD3TBXFFGN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CBUFUHO2NNOCQYELWD3TBXFFGN","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":"10cdbfdb0870beac38dbea453ad48ce3a0eae834bc9214a36555824b89bd72bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T15:09:46Z","title_canon_sha256":"dfba042cd15255f900b2b387a34adfd21acb6ca89e581fcad5827c381f799afd"},"schema_version":"1.0","source":{"id":"2310.13571","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13571","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13571v4","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13571","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"CBUFUHO2NNOC","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"CBUFUHO2NNOCQYEL","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"CBUFUHO2","created_at":"2026-07-05T08:28:03Z"}],"graph_snapshots":[{"event_id":"sha256:67dc411f8029bc42275ae90872a3580678de4ab2968dab5241bf32088f5046c7","target":"graph","created_at":"2026-07-05T08:28:03Z","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/2310.13571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper delves into the capabilities of large language models (LLMs), specifically focusing on advancing the theoretical comprehension of chain-of-thought prompting. We investigate how LLMs can be effectively induced to generate a coherent chain of thoughts. To achieve this, we introduce a two-level hierarchical graphical model tailored for natural language generation. Within this framework, we establish a compelling geometrical convergence rate that gauges the likelihood of an LLM-generated chain of thoughts compared to those originating from the true language. Our findings provide a theor","authors_text":"Antoine Grosnit, Haitham Bou-Ammar, Juliusz Ziomek, Jun Wang, Rasul Tutunov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T15:09:46Z","title":"Why Can Large Language Models Generate Correct Chain-of-Thoughts?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13571","kind":"arxiv","version":4},"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":"sha256:1965bae3be004126ff0167befad54e77892776c76b44735923870cb355626f76","target":"record","created_at":"2026-07-05T08:28:03Z","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":"10cdbfdb0870beac38dbea453ad48ce3a0eae834bc9214a36555824b89bd72bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T15:09:46Z","title_canon_sha256":"dfba042cd15255f900b2b387a34adfd21acb6ca89e581fcad5827c381f799afd"},"schema_version":"1.0","source":{"id":"2310.13571","kind":"arxiv","version":4}},"canonical_sha256":"10685a1dda6b5c28608bb0f730dca53351f0abfcc78d69175f8ad85c79fd94b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10685a1dda6b5c28608bb0f730dca53351f0abfcc78d69175f8ad85c79fd94b6","first_computed_at":"2026-07-05T08:28:03.293944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:03.293944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vx+q3u0SsIjM29MgqPzIrSgWnZMdv1zP2TrWTzFRzaCM8sQejMLCFeYQYEpcpnBtca5Fi+fmBSNJZeOpkNQoDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:03.294369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13571","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1965bae3be004126ff0167befad54e77892776c76b44735923870cb355626f76","sha256:67dc411f8029bc42275ae90872a3580678de4ab2968dab5241bf32088f5046c7"],"state_sha256":"41f95c50039daacd397a3fd237d4907338c38c19f61db6e2724ed69ea3d972b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j7uOXnjdMS00FryeOXe/5RBt4F1rrUdSHdpBVkHVGHePvqii+ySM6AiEMHGsAcVUvjjtm/ik7vH13UIAYwYZAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:56:07.255188Z","bundle_sha256":"10c5a0deff9085065305c2df22d725f2502f9d7714fca096afbb1f548b207806"}}