{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RJI3Y26BO5QAUFML4PODRBGVS7","short_pith_number":"pith:RJI3Y26B","canonical_record":{"source":{"id":"2509.09675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T17:59:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3b6e46bc8dedb7d95d09e44192df8b049c555ff3f4db6039d0774ad39370f176","abstract_canon_sha256":"3ecb76f0b22d37b88bbf44feb06f33607a2d423cf3145a5eaac095b52a413e96"},"schema_version":"1.0"},"canonical_sha256":"8a51bc6bc177600a158be3dc3884d597c65b5fedf992d39836596ed7d2ecf0fe","source":{"kind":"arxiv","id":"2509.09675","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09675","created_at":"2026-07-05T12:09:40Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09675v1","created_at":"2026-07-05T12:09:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09675","created_at":"2026-07-05T12:09:40Z"},{"alias_kind":"pith_short_12","alias_value":"RJI3Y26BO5QA","created_at":"2026-07-05T12:09:40Z"},{"alias_kind":"pith_short_16","alias_value":"RJI3Y26BO5QAUFML","created_at":"2026-07-05T12:09:40Z"},{"alias_kind":"pith_short_8","alias_value":"RJI3Y26B","created_at":"2026-07-05T12:09:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RJI3Y26BO5QAUFML4PODRBGVS7","target":"record","payload":{"canonical_record":{"source":{"id":"2509.09675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T17:59:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3b6e46bc8dedb7d95d09e44192df8b049c555ff3f4db6039d0774ad39370f176","abstract_canon_sha256":"3ecb76f0b22d37b88bbf44feb06f33607a2d423cf3145a5eaac095b52a413e96"},"schema_version":"1.0"},"canonical_sha256":"8a51bc6bc177600a158be3dc3884d597c65b5fedf992d39836596ed7d2ecf0fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:40.695608Z","signature_b64":"zU1VhdJX/8AKC9gj9wM/ZjEIqZ0pSzANC1V497C6xIrsJVadBpkmxi7Ynasjen52pUcImwi9eL1f40rgD0u+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a51bc6bc177600a158be3dc3884d597c65b5fedf992d39836596ed7d2ecf0fe","last_reissued_at":"2026-07-05T12:09:40.695061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:40.695061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.09675","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":"2026-07-05T12:09:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qhb1VqbKOKoOtAPYmE7pwV5OdNq33DbHoqwz1oqFsAB1Y+VtB2Uf+3Yh0JLG4AGu9z6baxwDa2OrXfh9w0fCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:25:31.358972Z"},"content_sha256":"c7700b5587391c1b062a378dcf48089ea585d0f1c1e87bce3323ff941a15bd5a","schema_version":"1.0","event_id":"sha256:c7700b5587391c1b062a378dcf48089ea585d0f1c1e87bce3323ff941a15bd5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RJI3Y26BO5QAUFML4PODRBGVS7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dian Yu, Dong Yu, Haitao Mi, Haolin Liu, Hongtu Zhu, Linfeng Song, Rui Liu, Runpeng Dai, Tong Zheng, Zhaopeng Tu, Zhenwen Liang","submitted_at":"2025-09-11T17:59:17Z","abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for enhancing the reasoning ability of Large Language Models (LLMs). Yet current RLVR methods often explore poorly, leading to premature convergence and entropy collapse. To address this challenge, we introduce Curiosity-Driven Exploration (CDE), a framework that leverages the model's own intrinsic sense of curiosity to guide exploration. We formalize curiosity with signals from both the actor and the critic: for the actor, we use perplexity over its generated response, and for the critic, we use the variance of value"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09675","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/2509.09675/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":"2026-07-05T12:09:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f5HKBYGT34m5DXEloog3BFSbl8rHPge7QqhlVmLXKIKLiKice1+k13JEG0PHqrB4zNld9K/QRe5mYaG+EnoGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:25:31.359988Z"},"content_sha256":"06bd5093d4801faf91c34fb88af6883843c94f0f98be9f4d75c972130561332c","schema_version":"1.0","event_id":"sha256:06bd5093d4801faf91c34fb88af6883843c94f0f98be9f4d75c972130561332c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJI3Y26BO5QAUFML4PODRBGVS7/bundle.json","state_url":"https://pith.science/pith/RJI3Y26BO5QAUFML4PODRBGVS7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJI3Y26BO5QAUFML4PODRBGVS7/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":"2026-08-05T01:25:31Z","links":{"resolver":"https://pith.science/pith/RJI3Y26BO5QAUFML4PODRBGVS7","bundle":"https://pith.science/pith/RJI3Y26BO5QAUFML4PODRBGVS7/bundle.json","state":"https://pith.science/pith/RJI3Y26BO5QAUFML4PODRBGVS7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJI3Y26BO5QAUFML4PODRBGVS7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RJI3Y26BO5QAUFML4PODRBGVS7","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":"3ecb76f0b22d37b88bbf44feb06f33607a2d423cf3145a5eaac095b52a413e96","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T17:59:17Z","title_canon_sha256":"3b6e46bc8dedb7d95d09e44192df8b049c555ff3f4db6039d0774ad39370f176"},"schema_version":"1.0","source":{"id":"2509.09675","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09675","created_at":"2026-07-05T12:09:40Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09675v1","created_at":"2026-07-05T12:09:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09675","created_at":"2026-07-05T12:09:40Z"},{"alias_kind":"pith_short_12","alias_value":"RJI3Y26BO5QA","created_at":"2026-07-05T12:09:40Z"},{"alias_kind":"pith_short_16","alias_value":"RJI3Y26BO5QAUFML","created_at":"2026-07-05T12:09:40Z"},{"alias_kind":"pith_short_8","alias_value":"RJI3Y26B","created_at":"2026-07-05T12:09:40Z"}],"graph_snapshots":[{"event_id":"sha256:06bd5093d4801faf91c34fb88af6883843c94f0f98be9f4d75c972130561332c","target":"graph","created_at":"2026-07-05T12:09:40Z","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/2509.09675/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for enhancing the reasoning ability of Large Language Models (LLMs). Yet current RLVR methods often explore poorly, leading to premature convergence and entropy collapse. To address this challenge, we introduce Curiosity-Driven Exploration (CDE), a framework that leverages the model's own intrinsic sense of curiosity to guide exploration. We formalize curiosity with signals from both the actor and the critic: for the actor, we use perplexity over its generated response, and for the critic, we use the variance of value","authors_text":"Dian Yu, Dong Yu, Haitao Mi, Haolin Liu, Hongtu Zhu, Linfeng Song, Rui Liu, Runpeng Dai, Tong Zheng, Zhaopeng Tu, Zhenwen Liang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T17:59:17Z","title":"CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09675","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:c7700b5587391c1b062a378dcf48089ea585d0f1c1e87bce3323ff941a15bd5a","target":"record","created_at":"2026-07-05T12:09:40Z","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":"3ecb76f0b22d37b88bbf44feb06f33607a2d423cf3145a5eaac095b52a413e96","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T17:59:17Z","title_canon_sha256":"3b6e46bc8dedb7d95d09e44192df8b049c555ff3f4db6039d0774ad39370f176"},"schema_version":"1.0","source":{"id":"2509.09675","kind":"arxiv","version":1}},"canonical_sha256":"8a51bc6bc177600a158be3dc3884d597c65b5fedf992d39836596ed7d2ecf0fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a51bc6bc177600a158be3dc3884d597c65b5fedf992d39836596ed7d2ecf0fe","first_computed_at":"2026-07-05T12:09:40.695061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:40.695061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zU1VhdJX/8AKC9gj9wM/ZjEIqZ0pSzANC1V497C6xIrsJVadBpkmxi7Ynasjen52pUcImwi9eL1f40rgD0u+DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:40.695608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09675","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7700b5587391c1b062a378dcf48089ea585d0f1c1e87bce3323ff941a15bd5a","sha256:06bd5093d4801faf91c34fb88af6883843c94f0f98be9f4d75c972130561332c"],"state_sha256":"b756194c668c5e462810e609f1066cab5c7e32f3a5554f00b4d3ba548dc54b5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xQRas292wDZPjfYCon2Ug+heXyHqn8LTJDO2AK47E8Gi2tfpuNMVjmiSz+dsC79cLwJLcCLpgK2/AGytpUHZCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:25:31.366209Z","bundle_sha256":"f59d9c8a9b2e7bdd2e410551c2ea67f26cb3862a1ea3d4900ced40fae1603dcd"}}