{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LIBEC3GOB5UN3ICQNQ3NK3XF54","short_pith_number":"pith:LIBEC3GO","canonical_record":{"source":{"id":"2505.02142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-04T15:09:49Z","cross_cats_sorted":[],"title_canon_sha256":"2cd8b800e831bf21a9fc1ce2ca6c3bded61b892c4573fc36887b927901c92f51","abstract_canon_sha256":"2affffc0f121bf5f2e50e8a48339202d1f4b4f502ab465d05d0b396a44ddc6cc"},"schema_version":"1.0"},"canonical_sha256":"5a02416cce0f68dda0506c36d56ee5ef232de4e81183bc588aac89952856fe73","source":{"kind":"arxiv","id":"2505.02142","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02142","created_at":"2026-07-05T10:58:32Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02142v1","created_at":"2026-07-05T10:58:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02142","created_at":"2026-07-05T10:58:32Z"},{"alias_kind":"pith_short_12","alias_value":"LIBEC3GOB5UN","created_at":"2026-07-05T10:58:32Z"},{"alias_kind":"pith_short_16","alias_value":"LIBEC3GOB5UN3ICQ","created_at":"2026-07-05T10:58:32Z"},{"alias_kind":"pith_short_8","alias_value":"LIBEC3GO","created_at":"2026-07-05T10:58:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LIBEC3GOB5UN3ICQNQ3NK3XF54","target":"record","payload":{"canonical_record":{"source":{"id":"2505.02142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-04T15:09:49Z","cross_cats_sorted":[],"title_canon_sha256":"2cd8b800e831bf21a9fc1ce2ca6c3bded61b892c4573fc36887b927901c92f51","abstract_canon_sha256":"2affffc0f121bf5f2e50e8a48339202d1f4b4f502ab465d05d0b396a44ddc6cc"},"schema_version":"1.0"},"canonical_sha256":"5a02416cce0f68dda0506c36d56ee5ef232de4e81183bc588aac89952856fe73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:32.671879Z","signature_b64":"EspzfhqNijIwRiPF28HVbdM9/0Kr4wIO3N94V2gCIxlO0CU2H3MncbUSqyi2GCT1P5WF77zBTERxJDT96BsCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a02416cce0f68dda0506c36d56ee5ef232de4e81183bc588aac89952856fe73","last_reissued_at":"2026-07-05T10:58:32.671376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:32.671376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.02142","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":"2026-07-05T10:58:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wC9pRAAJnpRtRSs/wNkBXqJhqliZjySxDMacS61O3q0+jaXs/pVsTK1vZrNanuUJ2lCTNINDgCC+VylaKW9tDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:41:20.040197Z"},"content_sha256":"dfa744800f4b19dda7033f32a2ab64865e3ad6408e596d8dd393af8147dd2571","schema_version":"1.0","event_id":"sha256:dfa744800f4b19dda7033f32a2ab64865e3ad6408e596d8dd393af8147dd2571"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LIBEC3GOB5UN3ICQNQ3NK3XF54","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Zhao, Haotian Wang, Shuaiting Chen, Sitong Zhao, Xiangang Li, Xiaoyu Tian, Yiping Peng, Yunjie Ji","submitted_at":"2025-05-04T15:09:49Z","abstract_excerpt":"Despite significant advances in long-context reasoning by large language models (LLMs), primarily through Online Reinforcement Learning (RL) methods, these approaches incur substantial computational costs and complexity. In contrast, simpler and more economical Offline RL methods remain underexplored. To address this gap, we investigate the effectiveness of Offline RL methods, specifically Direct Preference Optimization (DPO) and its length-desensitized variant LD-DPO, in enhancing the reasoning capabilities of LLMs. Extensive experiments across multiple reasoning benchmarks demonstrate that t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02142","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/2505.02142/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":"2026-07-05T10:58:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hWNtvS2hFIO009Xo2xaqj7VvsY8u3x/aEzZ3v2S+VGYPw/r3N5CUqetGEgfYZ84lG++lZYwx4A7ctoZbCgtpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:41:20.040591Z"},"content_sha256":"923d6306665671c98f84169790f575493427fc86479c473729848b6c3d36cf2c","schema_version":"1.0","event_id":"sha256:923d6306665671c98f84169790f575493427fc86479c473729848b6c3d36cf2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LIBEC3GOB5UN3ICQNQ3NK3XF54/bundle.json","state_url":"https://pith.science/pith/LIBEC3GOB5UN3ICQNQ3NK3XF54/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LIBEC3GOB5UN3ICQNQ3NK3XF54/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":"2026-07-07T08:41:20Z","links":{"resolver":"https://pith.science/pith/LIBEC3GOB5UN3ICQNQ3NK3XF54","bundle":"https://pith.science/pith/LIBEC3GOB5UN3ICQNQ3NK3XF54/bundle.json","state":"https://pith.science/pith/LIBEC3GOB5UN3ICQNQ3NK3XF54/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LIBEC3GOB5UN3ICQNQ3NK3XF54/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LIBEC3GOB5UN3ICQNQ3NK3XF54","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":"2affffc0f121bf5f2e50e8a48339202d1f4b4f502ab465d05d0b396a44ddc6cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-04T15:09:49Z","title_canon_sha256":"2cd8b800e831bf21a9fc1ce2ca6c3bded61b892c4573fc36887b927901c92f51"},"schema_version":"1.0","source":{"id":"2505.02142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02142","created_at":"2026-07-05T10:58:32Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02142v1","created_at":"2026-07-05T10:58:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02142","created_at":"2026-07-05T10:58:32Z"},{"alias_kind":"pith_short_12","alias_value":"LIBEC3GOB5UN","created_at":"2026-07-05T10:58:32Z"},{"alias_kind":"pith_short_16","alias_value":"LIBEC3GOB5UN3ICQ","created_at":"2026-07-05T10:58:32Z"},{"alias_kind":"pith_short_8","alias_value":"LIBEC3GO","created_at":"2026-07-05T10:58:32Z"}],"graph_snapshots":[{"event_id":"sha256:923d6306665671c98f84169790f575493427fc86479c473729848b6c3d36cf2c","target":"graph","created_at":"2026-07-05T10:58:32Z","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/2505.02142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant advances in long-context reasoning by large language models (LLMs), primarily through Online Reinforcement Learning (RL) methods, these approaches incur substantial computational costs and complexity. In contrast, simpler and more economical Offline RL methods remain underexplored. To address this gap, we investigate the effectiveness of Offline RL methods, specifically Direct Preference Optimization (DPO) and its length-desensitized variant LD-DPO, in enhancing the reasoning capabilities of LLMs. Extensive experiments across multiple reasoning benchmarks demonstrate that t","authors_text":"Han Zhao, Haotian Wang, Shuaiting Chen, Sitong Zhao, Xiangang Li, Xiaoyu Tian, Yiping Peng, Yunjie Ji","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-04T15:09:49Z","title":"Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02142","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:dfa744800f4b19dda7033f32a2ab64865e3ad6408e596d8dd393af8147dd2571","target":"record","created_at":"2026-07-05T10:58:32Z","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":"2affffc0f121bf5f2e50e8a48339202d1f4b4f502ab465d05d0b396a44ddc6cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-04T15:09:49Z","title_canon_sha256":"2cd8b800e831bf21a9fc1ce2ca6c3bded61b892c4573fc36887b927901c92f51"},"schema_version":"1.0","source":{"id":"2505.02142","kind":"arxiv","version":1}},"canonical_sha256":"5a02416cce0f68dda0506c36d56ee5ef232de4e81183bc588aac89952856fe73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a02416cce0f68dda0506c36d56ee5ef232de4e81183bc588aac89952856fe73","first_computed_at":"2026-07-05T10:58:32.671376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:32.671376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EspzfhqNijIwRiPF28HVbdM9/0Kr4wIO3N94V2gCIxlO0CU2H3MncbUSqyi2GCT1P5WF77zBTERxJDT96BsCCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:32.671879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfa744800f4b19dda7033f32a2ab64865e3ad6408e596d8dd393af8147dd2571","sha256:923d6306665671c98f84169790f575493427fc86479c473729848b6c3d36cf2c"],"state_sha256":"a95049d73a2407564af0160430c2b127c2883f97c85e62202bfa6e31e0caf948"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4gCFN2X292vM4wZ8cRa6EU/FIB/LNEpd5yMatEde/qYGhHKxF7sNYYbwjim0igHiH8VZeyVF+xWudg8Yvh80DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:41:20.042479Z","bundle_sha256":"6335abac08d7cdf6a4d5a817ef2b245e4ea38a8b5ed97d3af104ef2dc20c9cc5"}}