{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CHEN7BEIH52JIGQCXJZWHHFGU2","short_pith_number":"pith:CHEN7BEI","canonical_record":{"source":{"id":"2406.09136","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T14:07:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"080347add302e978132574d3bd76cb26fe0d66cae58a702e2f9c013377278efc","abstract_canon_sha256":"2b8a47f9656b937700e61d119a6a9367f3dc17ddc030a4718cd4911acd0f4118"},"schema_version":"1.0"},"canonical_sha256":"11c8df84883f74941a02ba73639ca6a6bad84e5062489018685a90ce4f70f63b","source":{"kind":"arxiv","id":"2406.09136","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09136","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09136v2","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09136","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"pith_short_12","alias_value":"CHEN7BEIH52J","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"pith_short_16","alias_value":"CHEN7BEIH52JIGQC","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"pith_short_8","alias_value":"CHEN7BEI","created_at":"2026-07-05T09:28:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CHEN7BEIH52JIGQCXJZWHHFGU2","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09136","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T14:07:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"080347add302e978132574d3bd76cb26fe0d66cae58a702e2f9c013377278efc","abstract_canon_sha256":"2b8a47f9656b937700e61d119a6a9367f3dc17ddc030a4718cd4911acd0f4118"},"schema_version":"1.0"},"canonical_sha256":"11c8df84883f74941a02ba73639ca6a6bad84e5062489018685a90ce4f70f63b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:51.357095Z","signature_b64":"6SlVS2aNY/qM5Ai3kv0zW1b8aKYkRrR+eqEE2V/jma6+RXbCbsxeCwWg6jh7l0RhqHnQCg9Lb0JYlM38qm9vDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11c8df84883f74941a02ba73639ca6a6bad84e5062489018685a90ce4f70f63b","last_reissued_at":"2026-07-05T09:28:51.356618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:51.356618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09136","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:28:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q+lF/+facxmsrIvtLEhohIahnwcfr3ehI2PCxwJTDvzDJxTy/5RWQZZFcDSESFHRskWFJvb+LyCiUWS+Fb3MBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:49:39.112387Z"},"content_sha256":"a6dd5afe0feccdb7e8841ed08c65fb69b13b0595891f44bb00fa1e4cfe40b0f0","schema_version":"1.0","event_id":"sha256:a6dd5afe0feccdb7e8841ed08c65fb69b13b0595891f44bb00fa1e4cfe40b0f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CHEN7BEIH52JIGQCXJZWHHFGU2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chao Du, Min Lin, Qian Liu, Tianyu Pang, Wei Gao, Xuan Zhang","submitted_at":"2024-06-13T14:07:02Z","abstract_excerpt":"The recent development of chain-of-thought (CoT) decoding has enabled large language models (LLMs) to generate explicit logical reasoning paths for complex problem-solving. However, research indicates that these paths are not always deliberate and optimal. The tree-of-thought (ToT) method employs tree-searching to extensively explore the reasoning space and find better reasoning paths that CoT decoding might overlook. This deliberation, however, comes at the cost of significantly increased inference complexity. In this work, we demonstrate that fine-tuning LLMs leveraging the search tree const"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09136","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/2406.09136/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":"2026-07-05T09:28:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"brsX7LVS5EKVpdhsQTcHAx/I/Y1tDxetyKktBsGeEgPGlDahA36MqGoOhKDKn5ZewWqOfatZKnyJVWeDQR5DBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:49:39.112891Z"},"content_sha256":"b68a1d2804c81da1b43224c9285790801c3bcb04e647be077b17900bf5f96732","schema_version":"1.0","event_id":"sha256:b68a1d2804c81da1b43224c9285790801c3bcb04e647be077b17900bf5f96732"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CHEN7BEIH52JIGQCXJZWHHFGU2/bundle.json","state_url":"https://pith.science/pith/CHEN7BEIH52JIGQCXJZWHHFGU2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CHEN7BEIH52JIGQCXJZWHHFGU2/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":"2026-08-07T05:49:39Z","links":{"resolver":"https://pith.science/pith/CHEN7BEIH52JIGQCXJZWHHFGU2","bundle":"https://pith.science/pith/CHEN7BEIH52JIGQCXJZWHHFGU2/bundle.json","state":"https://pith.science/pith/CHEN7BEIH52JIGQCXJZWHHFGU2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CHEN7BEIH52JIGQCXJZWHHFGU2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CHEN7BEIH52JIGQCXJZWHHFGU2","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":"2b8a47f9656b937700e61d119a6a9367f3dc17ddc030a4718cd4911acd0f4118","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T14:07:02Z","title_canon_sha256":"080347add302e978132574d3bd76cb26fe0d66cae58a702e2f9c013377278efc"},"schema_version":"1.0","source":{"id":"2406.09136","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09136","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09136v2","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09136","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"pith_short_12","alias_value":"CHEN7BEIH52J","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"pith_short_16","alias_value":"CHEN7BEIH52JIGQC","created_at":"2026-07-05T09:28:51Z"},{"alias_kind":"pith_short_8","alias_value":"CHEN7BEI","created_at":"2026-07-05T09:28:51Z"}],"graph_snapshots":[{"event_id":"sha256:b68a1d2804c81da1b43224c9285790801c3bcb04e647be077b17900bf5f96732","target":"graph","created_at":"2026-07-05T09:28:51Z","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/2406.09136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent development of chain-of-thought (CoT) decoding has enabled large language models (LLMs) to generate explicit logical reasoning paths for complex problem-solving. However, research indicates that these paths are not always deliberate and optimal. The tree-of-thought (ToT) method employs tree-searching to extensively explore the reasoning space and find better reasoning paths that CoT decoding might overlook. This deliberation, however, comes at the cost of significantly increased inference complexity. In this work, we demonstrate that fine-tuning LLMs leveraging the search tree const","authors_text":"Chao Du, Min Lin, Qian Liu, Tianyu Pang, Wei Gao, Xuan Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T14:07:02Z","title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09136","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:a6dd5afe0feccdb7e8841ed08c65fb69b13b0595891f44bb00fa1e4cfe40b0f0","target":"record","created_at":"2026-07-05T09:28:51Z","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":"2b8a47f9656b937700e61d119a6a9367f3dc17ddc030a4718cd4911acd0f4118","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T14:07:02Z","title_canon_sha256":"080347add302e978132574d3bd76cb26fe0d66cae58a702e2f9c013377278efc"},"schema_version":"1.0","source":{"id":"2406.09136","kind":"arxiv","version":2}},"canonical_sha256":"11c8df84883f74941a02ba73639ca6a6bad84e5062489018685a90ce4f70f63b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11c8df84883f74941a02ba73639ca6a6bad84e5062489018685a90ce4f70f63b","first_computed_at":"2026-07-05T09:28:51.356618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:51.356618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6SlVS2aNY/qM5Ai3kv0zW1b8aKYkRrR+eqEE2V/jma6+RXbCbsxeCwWg6jh7l0RhqHnQCg9Lb0JYlM38qm9vDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:51.357095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09136","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6dd5afe0feccdb7e8841ed08c65fb69b13b0595891f44bb00fa1e4cfe40b0f0","sha256:b68a1d2804c81da1b43224c9285790801c3bcb04e647be077b17900bf5f96732"],"state_sha256":"5415c015c302ea4ae30e21f2d0cb442e41ab458c28a169ea9122ba74cc369a9b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q9HWUYLatNfVUYPEDehBpAtGHgDV6JtiUBk4pBkPdwxnMjWXkEiNc5eNhOxAiNqRGceReDN+/b4eMweH8g0wAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:49:39.117423Z","bundle_sha256":"825649e03ae06284f86ee6471d427a7ed6c6399c0077aadd4da27ebf47d7f8f2"}}