{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JFXACJAKUQMV22HMEZRIUK4XPN","short_pith_number":"pith:JFXACJAK","canonical_record":{"source":{"id":"2509.06024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-07T11:52:18Z","cross_cats_sorted":[],"title_canon_sha256":"51db15bc6c06cf65d6fb592dea8360a05a58cacc5b65c6aa0c3ef2aea4116415","abstract_canon_sha256":"fd2436fd581f229960aa7312a05496d033fab95bfc5cf7ea2fac33bde48edc9d"},"schema_version":"1.0"},"canonical_sha256":"496e01240aa4195d68ec26628a2b977b71f878ec9e4941bd2492be6e78c9b0a7","source":{"kind":"arxiv","id":"2509.06024","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06024","created_at":"2026-07-05T12:06:28Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06024v1","created_at":"2026-07-05T12:06:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06024","created_at":"2026-07-05T12:06:28Z"},{"alias_kind":"pith_short_12","alias_value":"JFXACJAKUQMV","created_at":"2026-07-05T12:06:28Z"},{"alias_kind":"pith_short_16","alias_value":"JFXACJAKUQMV22HM","created_at":"2026-07-05T12:06:28Z"},{"alias_kind":"pith_short_8","alias_value":"JFXACJAK","created_at":"2026-07-05T12:06:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JFXACJAKUQMV22HMEZRIUK4XPN","target":"record","payload":{"canonical_record":{"source":{"id":"2509.06024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-07T11:52:18Z","cross_cats_sorted":[],"title_canon_sha256":"51db15bc6c06cf65d6fb592dea8360a05a58cacc5b65c6aa0c3ef2aea4116415","abstract_canon_sha256":"fd2436fd581f229960aa7312a05496d033fab95bfc5cf7ea2fac33bde48edc9d"},"schema_version":"1.0"},"canonical_sha256":"496e01240aa4195d68ec26628a2b977b71f878ec9e4941bd2492be6e78c9b0a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:28.502641Z","signature_b64":"FqcMQW3knzPUHz9x3Sf8j92U3j2I4j9XcChQWVXWFK8yj9mx/1I8kE1VxLmCzw0ENJNejzss2oRbChSu7iMjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"496e01240aa4195d68ec26628a2b977b71f878ec9e4941bd2492be6e78c9b0a7","last_reissued_at":"2026-07-05T12:06:28.502065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:28.502065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.06024","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":"2026-07-05T12:06:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hjlWlclJilJB6nd2OXeaJzYbqlB3iYc2VEWCNh3h+M1V3a+ryudAD6X/EDz2YF/J8bzJGTA06FRs+8KkUE3ICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:04:22.983682Z"},"content_sha256":"25d54bbc5afa9243bab9c9e0814757172c6269b7d8d4d78554b21a06e6fdb9b9","schema_version":"1.0","event_id":"sha256:25d54bbc5afa9243bab9c9e0814757172c6269b7d8d4d78554b21a06e6fdb9b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JFXACJAKUQMV22HMEZRIUK4XPN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenyang Li, Chong Xia, Haoyang He, Honggang Zhang, Kun Ji, Lan Yang, Qing Huang, Zihua Rong","submitted_at":"2025-09-07T11:52:18Z","abstract_excerpt":"Reinforcement learning (RL) has recently become the dominant paradigm for strengthening the reasoning abilities of large language models (LLMs). Yet the rule-based reward functions commonly used on mathematical or programming benchmarks assess only answer format and correctness, providing no signal as to whether the induced Chain-of-Thought (CoT) actually improves the answer. Furthermore, such task-specific training offers limited control over logical depth and therefore may fail to reveal a model's genuine reasoning capacity. We propose Dynamic Reasoning Efficiency Reward (DRER) -- a plug-and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06024","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/2509.06024/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":"2026-07-05T12:06:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YpWpgt6JpkWOfX7p3OnNY9vTHaM/JZYF1D7rfsilC6d5Uv5ysizoec0t9jVC+s+FxkC5MfCZvcEBKclcnck9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:04:22.995513Z"},"content_sha256":"1f5c08abc31e3655554f5b61cc1e175bb48cdfe58f6e4d4655c6be859d8b2221","schema_version":"1.0","event_id":"sha256:1f5c08abc31e3655554f5b61cc1e175bb48cdfe58f6e4d4655c6be859d8b2221"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JFXACJAKUQMV22HMEZRIUK4XPN/bundle.json","state_url":"https://pith.science/pith/JFXACJAKUQMV22HMEZRIUK4XPN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JFXACJAKUQMV22HMEZRIUK4XPN/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":"2026-08-14T19:04:23Z","links":{"resolver":"https://pith.science/pith/JFXACJAKUQMV22HMEZRIUK4XPN","bundle":"https://pith.science/pith/JFXACJAKUQMV22HMEZRIUK4XPN/bundle.json","state":"https://pith.science/pith/JFXACJAKUQMV22HMEZRIUK4XPN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JFXACJAKUQMV22HMEZRIUK4XPN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JFXACJAKUQMV22HMEZRIUK4XPN","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":"fd2436fd581f229960aa7312a05496d033fab95bfc5cf7ea2fac33bde48edc9d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-07T11:52:18Z","title_canon_sha256":"51db15bc6c06cf65d6fb592dea8360a05a58cacc5b65c6aa0c3ef2aea4116415"},"schema_version":"1.0","source":{"id":"2509.06024","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06024","created_at":"2026-07-05T12:06:28Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06024v1","created_at":"2026-07-05T12:06:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06024","created_at":"2026-07-05T12:06:28Z"},{"alias_kind":"pith_short_12","alias_value":"JFXACJAKUQMV","created_at":"2026-07-05T12:06:28Z"},{"alias_kind":"pith_short_16","alias_value":"JFXACJAKUQMV22HM","created_at":"2026-07-05T12:06:28Z"},{"alias_kind":"pith_short_8","alias_value":"JFXACJAK","created_at":"2026-07-05T12:06:28Z"}],"graph_snapshots":[{"event_id":"sha256:1f5c08abc31e3655554f5b61cc1e175bb48cdfe58f6e4d4655c6be859d8b2221","target":"graph","created_at":"2026-07-05T12:06:28Z","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/2509.06024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has recently become the dominant paradigm for strengthening the reasoning abilities of large language models (LLMs). Yet the rule-based reward functions commonly used on mathematical or programming benchmarks assess only answer format and correctness, providing no signal as to whether the induced Chain-of-Thought (CoT) actually improves the answer. Furthermore, such task-specific training offers limited control over logical depth and therefore may fail to reveal a model's genuine reasoning capacity. We propose Dynamic Reasoning Efficiency Reward (DRER) -- a plug-and","authors_text":"Chenyang Li, Chong Xia, Haoyang He, Honggang Zhang, Kun Ji, Lan Yang, Qing Huang, Zihua Rong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-07T11:52:18Z","title":"Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06024","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":"sha256:25d54bbc5afa9243bab9c9e0814757172c6269b7d8d4d78554b21a06e6fdb9b9","target":"record","created_at":"2026-07-05T12:06:28Z","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":"fd2436fd581f229960aa7312a05496d033fab95bfc5cf7ea2fac33bde48edc9d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-07T11:52:18Z","title_canon_sha256":"51db15bc6c06cf65d6fb592dea8360a05a58cacc5b65c6aa0c3ef2aea4116415"},"schema_version":"1.0","source":{"id":"2509.06024","kind":"arxiv","version":1}},"canonical_sha256":"496e01240aa4195d68ec26628a2b977b71f878ec9e4941bd2492be6e78c9b0a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"496e01240aa4195d68ec26628a2b977b71f878ec9e4941bd2492be6e78c9b0a7","first_computed_at":"2026-07-05T12:06:28.502065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:28.502065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FqcMQW3knzPUHz9x3Sf8j92U3j2I4j9XcChQWVXWFK8yj9mx/1I8kE1VxLmCzw0ENJNejzss2oRbChSu7iMjAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:28.502641Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06024","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25d54bbc5afa9243bab9c9e0814757172c6269b7d8d4d78554b21a06e6fdb9b9","sha256:1f5c08abc31e3655554f5b61cc1e175bb48cdfe58f6e4d4655c6be859d8b2221"],"state_sha256":"da55bcd1efbe7141fec19e107ef6384737d416ff5a42e990c149da6b1042361c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rq7dUEByJRwQFJTdfMUYNELr69avjEdVpyozgY00/+ftKF/Lp8/Y/C1PHJDoCKYCENoXBlRwZQp+8MxsDG/ECA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:04:23.051224Z","bundle_sha256":"5498ae632c2ad0b4c08abe69ef407f201b7470119ffa6f31e194673fac4fcd92"}}