{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GLFHKLWWCTXPB4QBLBYUFQMHIQ","short_pith_number":"pith:GLFHKLWW","canonical_record":{"source":{"id":"2509.02333","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T14:01:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"423eece6c3ea18d337efe7b2174834e32a7a0ebfbdd0fbac6ff955565d66e571","abstract_canon_sha256":"ad01a58c59f654948df96f323eee75946f51c2af4f0db03f15252d1a7b808660"},"schema_version":"1.0"},"canonical_sha256":"32ca752ed614eef0f201587142c187442f38a81f485bf74ea3d29eec42369a36","source":{"kind":"arxiv","id":"2509.02333","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02333","created_at":"2026-07-05T12:06:49Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02333v2","created_at":"2026-07-05T12:06:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02333","created_at":"2026-07-05T12:06:49Z"},{"alias_kind":"pith_short_12","alias_value":"GLFHKLWWCTXP","created_at":"2026-07-05T12:06:49Z"},{"alias_kind":"pith_short_16","alias_value":"GLFHKLWWCTXPB4QB","created_at":"2026-07-05T12:06:49Z"},{"alias_kind":"pith_short_8","alias_value":"GLFHKLWW","created_at":"2026-07-05T12:06:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GLFHKLWWCTXPB4QBLBYUFQMHIQ","target":"record","payload":{"canonical_record":{"source":{"id":"2509.02333","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T14:01:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"423eece6c3ea18d337efe7b2174834e32a7a0ebfbdd0fbac6ff955565d66e571","abstract_canon_sha256":"ad01a58c59f654948df96f323eee75946f51c2af4f0db03f15252d1a7b808660"},"schema_version":"1.0"},"canonical_sha256":"32ca752ed614eef0f201587142c187442f38a81f485bf74ea3d29eec42369a36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:49.491467Z","signature_b64":"QQfVoM6qri3hdCFVH0OCvD3UxjVtDvpQBFVem/0RL3ndM2/Evd0wbUMOqYx9Gq4+zkuvFnrGPXRfhxDsKGtMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32ca752ed614eef0f201587142c187442f38a81f485bf74ea3d29eec42369a36","last_reissued_at":"2026-07-05T12:06:49.490718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:49.490718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.02333","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":"2026-07-05T12:06:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gYfBrYLs5kdD1hNR74xGLg0DUdO3lW6y6HIEjjMAGGZkbSmFGlyVdaurKCkg/CGm9NVfy2PbcflxrqBKwnSfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:46:34.395783Z"},"content_sha256":"2fa120753e09eaf8c59138daa077114bf29f2a4d31dfb49396ca64e95dd8a2cd","schema_version":"1.0","event_id":"sha256:2fa120753e09eaf8c59138daa077114bf29f2a4d31dfb49396ca64e95dd8a2cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GLFHKLWWCTXPB4QBLBYUFQMHIQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DCPO: Dynamic Clipping Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chengfeng Dou, Fei Deng, Kai Lu, Peidong Guo, Qiang Ju, Rihui Xin, Shihui Yang","submitted_at":"2025-09-02T14:01:07Z","abstract_excerpt":"Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a promising framework for enhancing the reasoning capabilities of large language models. However, existing approaches such as GRPO often suffer from zero gradients. This problem arises primarily due to fixed clipping bounds for token-level probability ratios and the standardization of identical rewards, which can lead to ineffective gradient updates and underutilization of generated responses. In this work, we propose Dynamic Clipping Policy Optimization(DCPO), which introduces a dynamic clipping strategy that adaptively adju"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02333","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/2509.02333/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":"2026-07-05T12:06:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aMNlh+mJ7RzgpQ7RCeOGCcj3ddDhb2Hingdz47JbZfREMB2lzLWjmd14w6tOOkiEzV0O6lstopJatEXf7o+MDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:46:34.396657Z"},"content_sha256":"3057c7444479eb178cbc1646b982ccfa46c63aa3e824f9860eb944331ed93b78","schema_version":"1.0","event_id":"sha256:3057c7444479eb178cbc1646b982ccfa46c63aa3e824f9860eb944331ed93b78"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GLFHKLWWCTXPB4QBLBYUFQMHIQ/bundle.json","state_url":"https://pith.science/pith/GLFHKLWWCTXPB4QBLBYUFQMHIQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GLFHKLWWCTXPB4QBLBYUFQMHIQ/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":"2026-08-10T12:46:34Z","links":{"resolver":"https://pith.science/pith/GLFHKLWWCTXPB4QBLBYUFQMHIQ","bundle":"https://pith.science/pith/GLFHKLWWCTXPB4QBLBYUFQMHIQ/bundle.json","state":"https://pith.science/pith/GLFHKLWWCTXPB4QBLBYUFQMHIQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GLFHKLWWCTXPB4QBLBYUFQMHIQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GLFHKLWWCTXPB4QBLBYUFQMHIQ","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":"ad01a58c59f654948df96f323eee75946f51c2af4f0db03f15252d1a7b808660","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T14:01:07Z","title_canon_sha256":"423eece6c3ea18d337efe7b2174834e32a7a0ebfbdd0fbac6ff955565d66e571"},"schema_version":"1.0","source":{"id":"2509.02333","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02333","created_at":"2026-07-05T12:06:49Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02333v2","created_at":"2026-07-05T12:06:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02333","created_at":"2026-07-05T12:06:49Z"},{"alias_kind":"pith_short_12","alias_value":"GLFHKLWWCTXP","created_at":"2026-07-05T12:06:49Z"},{"alias_kind":"pith_short_16","alias_value":"GLFHKLWWCTXPB4QB","created_at":"2026-07-05T12:06:49Z"},{"alias_kind":"pith_short_8","alias_value":"GLFHKLWW","created_at":"2026-07-05T12:06:49Z"}],"graph_snapshots":[{"event_id":"sha256:3057c7444479eb178cbc1646b982ccfa46c63aa3e824f9860eb944331ed93b78","target":"graph","created_at":"2026-07-05T12:06:49Z","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/2509.02333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a promising framework for enhancing the reasoning capabilities of large language models. However, existing approaches such as GRPO often suffer from zero gradients. This problem arises primarily due to fixed clipping bounds for token-level probability ratios and the standardization of identical rewards, which can lead to ineffective gradient updates and underutilization of generated responses. In this work, we propose Dynamic Clipping Policy Optimization(DCPO), which introduces a dynamic clipping strategy that adaptively adju","authors_text":"Chengfeng Dou, Fei Deng, Kai Lu, Peidong Guo, Qiang Ju, Rihui Xin, Shihui Yang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T14:01:07Z","title":"DCPO: Dynamic Clipping Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02333","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":"sha256:2fa120753e09eaf8c59138daa077114bf29f2a4d31dfb49396ca64e95dd8a2cd","target":"record","created_at":"2026-07-05T12:06:49Z","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":"ad01a58c59f654948df96f323eee75946f51c2af4f0db03f15252d1a7b808660","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T14:01:07Z","title_canon_sha256":"423eece6c3ea18d337efe7b2174834e32a7a0ebfbdd0fbac6ff955565d66e571"},"schema_version":"1.0","source":{"id":"2509.02333","kind":"arxiv","version":2}},"canonical_sha256":"32ca752ed614eef0f201587142c187442f38a81f485bf74ea3d29eec42369a36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32ca752ed614eef0f201587142c187442f38a81f485bf74ea3d29eec42369a36","first_computed_at":"2026-07-05T12:06:49.490718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:49.490718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QQfVoM6qri3hdCFVH0OCvD3UxjVtDvpQBFVem/0RL3ndM2/Evd0wbUMOqYx9Gq4+zkuvFnrGPXRfhxDsKGtMCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:49.491467Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02333","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fa120753e09eaf8c59138daa077114bf29f2a4d31dfb49396ca64e95dd8a2cd","sha256:3057c7444479eb178cbc1646b982ccfa46c63aa3e824f9860eb944331ed93b78"],"state_sha256":"d33792f9022a0a65cef53ec2a34bb3dccf8a54f7296a656afc2609c039cbd77d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VMwSBs2NHz/zjHLZ30ZvU0thiasTqPwtBCnBK+oIYJBQrhhEm6ah15ribtOp7XpJ9CVoP73YijPJ7uFHd1l9Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:46:34.405058Z","bundle_sha256":"d0f7d32880b41085d10a4e3ed09a9d36abbbceae789d917357484e603a610859"}}