{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ME5UNA5EPMD6JTELIXQUZG77BC","short_pith_number":"pith:ME5UNA5E","canonical_record":{"source":{"id":"2410.10858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T06:37:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e5c65ddaef0c2ed221ce9c103312a61ca9d5030e1301a913c52cf2f24e817f62","abstract_canon_sha256":"14b24a41b14aaafa260469873b3ed450265a75480211d94870598943feec3ada"},"schema_version":"1.0"},"canonical_sha256":"613b4683a47b07e4cc8b45e14c9bff08866df3013e0f47fb9eb935896406f6b2","source":{"kind":"arxiv","id":"2410.10858","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10858","created_at":"2026-07-05T09:20:26Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10858v1","created_at":"2026-07-05T09:20:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10858","created_at":"2026-07-05T09:20:26Z"},{"alias_kind":"pith_short_12","alias_value":"ME5UNA5EPMD6","created_at":"2026-07-05T09:20:26Z"},{"alias_kind":"pith_short_16","alias_value":"ME5UNA5EPMD6JTEL","created_at":"2026-07-05T09:20:26Z"},{"alias_kind":"pith_short_8","alias_value":"ME5UNA5E","created_at":"2026-07-05T09:20:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ME5UNA5EPMD6JTELIXQUZG77BC","target":"record","payload":{"canonical_record":{"source":{"id":"2410.10858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T06:37:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e5c65ddaef0c2ed221ce9c103312a61ca9d5030e1301a913c52cf2f24e817f62","abstract_canon_sha256":"14b24a41b14aaafa260469873b3ed450265a75480211d94870598943feec3ada"},"schema_version":"1.0"},"canonical_sha256":"613b4683a47b07e4cc8b45e14c9bff08866df3013e0f47fb9eb935896406f6b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:26.100114Z","signature_b64":"Ot/9tzDGEp/t9LeWb7KcX2vEG5LvDHNNO29WVaJcJ8WuQhY1cYYTxv3FfIHO0PrQyRNpHb4YAYodLnYyCJ6dAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"613b4683a47b07e4cc8b45e14c9bff08866df3013e0f47fb9eb935896406f6b2","last_reissued_at":"2026-07-05T09:20:26.099683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:26.099683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.10858","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:20:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lKLoNqJPMkYptI8MckAw7vPP2LOP4nwqzon+y4vgIfzkhZ2JXT99fMEOijXCakQ9P0ujcnhQDyr7PUCpToONCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:48:52.945626Z"},"content_sha256":"f5905545e5a696b8bbf0cb3ce2d23ecfd7e12b1b39137c40247fb435e3ca6b53","schema_version":"1.0","event_id":"sha256:f5905545e5a696b8bbf0cb3ce2d23ecfd7e12b1b39137c40247fb435e3ca6b53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ME5UNA5EPMD6JTELIXQUZG77BC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Guizhen Chen, Lidong Bing, Luu Anh Tuan, Soujanya Poria, Weiwen Xu, Yew Ken Chia","submitted_at":"2024-10-07T06:37:25Z","abstract_excerpt":"Advanced models such as OpenAI o1 exhibit impressive problem-solving capabilities through step-by-step reasoning. However, they may still falter on more complex problems, making errors that disrupt their reasoning paths. We attribute this to the expansive solution space, where each step has the risk of diverging into mistakes. To enhance language model reasoning, we introduce a specialized training framework called Reasoning Paths Optimization (RPO), which enables learning to reason and explore from diverse paths. Our approach encourages favorable branches at each reasoning step while penalizi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10858","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/2410.10858/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":"2026-07-05T09:20:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KBkuXaodJ14HTvSyd2bViOGRRjRbqcuxAm8qNwDn/fldxDL7aliBQPTySoujmguljuMfj/+0hQEPZhxQeay0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:48:52.946015Z"},"content_sha256":"965c1e04d55ff6ba13c52882311ca47555e8261a6e8da92c3474649c3f1576a8","schema_version":"1.0","event_id":"sha256:965c1e04d55ff6ba13c52882311ca47555e8261a6e8da92c3474649c3f1576a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ME5UNA5EPMD6JTELIXQUZG77BC/bundle.json","state_url":"https://pith.science/pith/ME5UNA5EPMD6JTELIXQUZG77BC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ME5UNA5EPMD6JTELIXQUZG77BC/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":"2026-07-06T18:48:52Z","links":{"resolver":"https://pith.science/pith/ME5UNA5EPMD6JTELIXQUZG77BC","bundle":"https://pith.science/pith/ME5UNA5EPMD6JTELIXQUZG77BC/bundle.json","state":"https://pith.science/pith/ME5UNA5EPMD6JTELIXQUZG77BC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ME5UNA5EPMD6JTELIXQUZG77BC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ME5UNA5EPMD6JTELIXQUZG77BC","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":"14b24a41b14aaafa260469873b3ed450265a75480211d94870598943feec3ada","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T06:37:25Z","title_canon_sha256":"e5c65ddaef0c2ed221ce9c103312a61ca9d5030e1301a913c52cf2f24e817f62"},"schema_version":"1.0","source":{"id":"2410.10858","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10858","created_at":"2026-07-05T09:20:26Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10858v1","created_at":"2026-07-05T09:20:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10858","created_at":"2026-07-05T09:20:26Z"},{"alias_kind":"pith_short_12","alias_value":"ME5UNA5EPMD6","created_at":"2026-07-05T09:20:26Z"},{"alias_kind":"pith_short_16","alias_value":"ME5UNA5EPMD6JTEL","created_at":"2026-07-05T09:20:26Z"},{"alias_kind":"pith_short_8","alias_value":"ME5UNA5E","created_at":"2026-07-05T09:20:26Z"}],"graph_snapshots":[{"event_id":"sha256:965c1e04d55ff6ba13c52882311ca47555e8261a6e8da92c3474649c3f1576a8","target":"graph","created_at":"2026-07-05T09:20:26Z","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/2410.10858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advanced models such as OpenAI o1 exhibit impressive problem-solving capabilities through step-by-step reasoning. However, they may still falter on more complex problems, making errors that disrupt their reasoning paths. We attribute this to the expansive solution space, where each step has the risk of diverging into mistakes. To enhance language model reasoning, we introduce a specialized training framework called Reasoning Paths Optimization (RPO), which enables learning to reason and explore from diverse paths. Our approach encourages favorable branches at each reasoning step while penalizi","authors_text":"Guizhen Chen, Lidong Bing, Luu Anh Tuan, Soujanya Poria, Weiwen Xu, Yew Ken Chia","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T06:37:25Z","title":"Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10858","kind":"arxiv","version":1},"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:f5905545e5a696b8bbf0cb3ce2d23ecfd7e12b1b39137c40247fb435e3ca6b53","target":"record","created_at":"2026-07-05T09:20:26Z","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":"14b24a41b14aaafa260469873b3ed450265a75480211d94870598943feec3ada","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-07T06:37:25Z","title_canon_sha256":"e5c65ddaef0c2ed221ce9c103312a61ca9d5030e1301a913c52cf2f24e817f62"},"schema_version":"1.0","source":{"id":"2410.10858","kind":"arxiv","version":1}},"canonical_sha256":"613b4683a47b07e4cc8b45e14c9bff08866df3013e0f47fb9eb935896406f6b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"613b4683a47b07e4cc8b45e14c9bff08866df3013e0f47fb9eb935896406f6b2","first_computed_at":"2026-07-05T09:20:26.099683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:26.099683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ot/9tzDGEp/t9LeWb7KcX2vEG5LvDHNNO29WVaJcJ8WuQhY1cYYTxv3FfIHO0PrQyRNpHb4YAYodLnYyCJ6dAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:26.100114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10858","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5905545e5a696b8bbf0cb3ce2d23ecfd7e12b1b39137c40247fb435e3ca6b53","sha256:965c1e04d55ff6ba13c52882311ca47555e8261a6e8da92c3474649c3f1576a8"],"state_sha256":"5926df487bbb0c7a0ec50a38ddb38aa2cee9680f06fd964bce4b68b998b4ee34"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ec4qT7f2e/1U9V0cSZjN2qMxjy7XRjsYqRuGEqOwPqJkj7Z25F/t36ABcsruUWomIqTkFemjcYwO7NqExYUdCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:48:52.947989Z","bundle_sha256":"ffaff2072601e86047b32921cfa6ce91119b9a0ba834d00df61c8388f5872f99"}}