{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BFGT5LC7CANYIEQW5ZR7RGST5B","short_pith_number":"pith:BFGT5LC7","canonical_record":{"source":{"id":"2406.05673","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-09T07:06:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"804b6204fc3503b15a529c2b94db7978b975c65e034f65470a8a52e3daaec1db","abstract_canon_sha256":"540cce941127e1e1d638e16ee225570b787e2415ca46b51abb2ef5901625b2e6"},"schema_version":"1.0"},"canonical_sha256":"094d3eac5f101b841216ee63f89a53e87d92a86534ab9e29a4eef39f22b7a80d","source":{"kind":"arxiv","id":"2406.05673","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05673","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05673v6","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05673","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"BFGT5LC7CANY","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"BFGT5LC7CANYIEQW","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"BFGT5LC7","created_at":"2026-07-05T11:09:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BFGT5LC7CANYIEQW5ZR7RGST5B","target":"record","payload":{"canonical_record":{"source":{"id":"2406.05673","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-09T07:06:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"804b6204fc3503b15a529c2b94db7978b975c65e034f65470a8a52e3daaec1db","abstract_canon_sha256":"540cce941127e1e1d638e16ee225570b787e2415ca46b51abb2ef5901625b2e6"},"schema_version":"1.0"},"canonical_sha256":"094d3eac5f101b841216ee63f89a53e87d92a86534ab9e29a4eef39f22b7a80d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:59.223499Z","signature_b64":"4bugUeKhQ508iCDTqozJTZAKczau2P5kd8wkqhsPk+lez1Hkpqu0Cl/efthHXNVndi6FA2luKSMVLghoBMKsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"094d3eac5f101b841216ee63f89a53e87d92a86534ab9e29a4eef39f22b7a80d","last_reissued_at":"2026-07-05T11:09:59.222986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:59.222986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.05673","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ptbzDqHTuVqnyAQrjYR/ebGj/qeH77n3Ev1kVZ1XsSoqFyVCq97prT5c0G/W8LRER3WB/rIG6d7riXuMOWiMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:56:47.104754Z"},"content_sha256":"3781c3342a284a42d31f71a0ee2117858b4ce07594e6193662f297647e5c6fca","schema_version":"1.0","event_id":"sha256:3781c3342a284a42d31f71a0ee2117858b4ce07594e6193662f297647e5c6fca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BFGT5LC7CANYIEQW5ZR7RGST5B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Fangxu Yu, Haoqiang Kang, Lai Jiang, Lianhui Qin, Shibo Hao","submitted_at":"2024-06-09T07:06:58Z","abstract_excerpt":"The ability to generate diverse solutions to a given problem is a hallmark of human creativity. This divergent reasoning is also crucial for machines, enhancing their robustness and enabling them to assist humans in many applications such as scientific discovery. However, existing approaches to multi-step reasoning with large language models (LLMs) have mostly focused only on reasoning accuracy, without further discovering more diverse valid solutions. For example, supervised fine-tuning improves reasoning quality but requires vast labeled data, while reward-maximizing reinforcement learning f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05673","kind":"arxiv","version":6},"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/2406.05673/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":"2026-07-05T11:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tCTPaREYpl9g0jqALCfR0VcIDffRiBJ1QycnnQwnaa3gpnlDakM9nMXyAvMgqkH52evrnzpA+2AM7bCX0IhMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:56:47.105702Z"},"content_sha256":"5e2b3673b7941081f310f270e823b6404f927dd037a74bb58bfb333c28022023","schema_version":"1.0","event_id":"sha256:5e2b3673b7941081f310f270e823b6404f927dd037a74bb58bfb333c28022023"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BFGT5LC7CANYIEQW5ZR7RGST5B/bundle.json","state_url":"https://pith.science/pith/BFGT5LC7CANYIEQW5ZR7RGST5B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BFGT5LC7CANYIEQW5ZR7RGST5B/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":"2026-08-08T05:56:47Z","links":{"resolver":"https://pith.science/pith/BFGT5LC7CANYIEQW5ZR7RGST5B","bundle":"https://pith.science/pith/BFGT5LC7CANYIEQW5ZR7RGST5B/bundle.json","state":"https://pith.science/pith/BFGT5LC7CANYIEQW5ZR7RGST5B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BFGT5LC7CANYIEQW5ZR7RGST5B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BFGT5LC7CANYIEQW5ZR7RGST5B","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":"540cce941127e1e1d638e16ee225570b787e2415ca46b51abb2ef5901625b2e6","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-09T07:06:58Z","title_canon_sha256":"804b6204fc3503b15a529c2b94db7978b975c65e034f65470a8a52e3daaec1db"},"schema_version":"1.0","source":{"id":"2406.05673","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05673","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05673v6","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05673","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"BFGT5LC7CANY","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"BFGT5LC7CANYIEQW","created_at":"2026-07-05T11:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"BFGT5LC7","created_at":"2026-07-05T11:09:59Z"}],"graph_snapshots":[{"event_id":"sha256:5e2b3673b7941081f310f270e823b6404f927dd037a74bb58bfb333c28022023","target":"graph","created_at":"2026-07-05T11:09:59Z","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/2406.05673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to generate diverse solutions to a given problem is a hallmark of human creativity. This divergent reasoning is also crucial for machines, enhancing their robustness and enabling them to assist humans in many applications such as scientific discovery. However, existing approaches to multi-step reasoning with large language models (LLMs) have mostly focused only on reasoning accuracy, without further discovering more diverse valid solutions. For example, supervised fine-tuning improves reasoning quality but requires vast labeled data, while reward-maximizing reinforcement learning f","authors_text":"Fangxu Yu, Haoqiang Kang, Lai Jiang, Lianhui Qin, Shibo Hao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-09T07:06:58Z","title":"Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05673","kind":"arxiv","version":6},"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":"sha256:3781c3342a284a42d31f71a0ee2117858b4ce07594e6193662f297647e5c6fca","target":"record","created_at":"2026-07-05T11:09:59Z","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":"540cce941127e1e1d638e16ee225570b787e2415ca46b51abb2ef5901625b2e6","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-09T07:06:58Z","title_canon_sha256":"804b6204fc3503b15a529c2b94db7978b975c65e034f65470a8a52e3daaec1db"},"schema_version":"1.0","source":{"id":"2406.05673","kind":"arxiv","version":6}},"canonical_sha256":"094d3eac5f101b841216ee63f89a53e87d92a86534ab9e29a4eef39f22b7a80d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"094d3eac5f101b841216ee63f89a53e87d92a86534ab9e29a4eef39f22b7a80d","first_computed_at":"2026-07-05T11:09:59.222986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:59.222986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4bugUeKhQ508iCDTqozJTZAKczau2P5kd8wkqhsPk+lez1Hkpqu0Cl/efthHXNVndi6FA2luKSMVLghoBMKsCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:59.223499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.05673","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3781c3342a284a42d31f71a0ee2117858b4ce07594e6193662f297647e5c6fca","sha256:5e2b3673b7941081f310f270e823b6404f927dd037a74bb58bfb333c28022023"],"state_sha256":"46199b272dc4ee7b4e97c9720a5edf54243f200388642a9a8f7c2bddce410120"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qw5N5XY01ErTTuKt5iRv9Ga7WMEkZ1mQCbZn3njt8DDSUxpj/ZvCbsotrATdM7BKlXoferHmx6aRrfaC+irDAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:56:47.115407Z","bundle_sha256":"36c68a83d2132f70018f3f759d32cf8ee5a3b4f07bce899318a6526b8405098c"}}