{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IRIPJL66M5GEYBBDQ7GN6KYRFO","short_pith_number":"pith:IRIPJL66","canonical_record":{"source":{"id":"2507.07451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T05:58:55Z","cross_cats_sorted":[],"title_canon_sha256":"6e940d0f99b315f7f13da3fcef0f3f41da94f264a9def7689ae5734cc39d768b","abstract_canon_sha256":"69abf5140e9a5657daa7d2b3fee2aec8f3a1292dab5b71fb107c28e6321bdd56"},"schema_version":"1.0"},"canonical_sha256":"4450f4afde674c4c042387ccdf2b112b9369b198c442afa0dca2ac47442ef213","source":{"kind":"arxiv","id":"2507.07451","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07451","created_at":"2026-07-05T11:34:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07451v1","created_at":"2026-07-05T11:34:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07451","created_at":"2026-07-05T11:34:58Z"},{"alias_kind":"pith_short_12","alias_value":"IRIPJL66M5GE","created_at":"2026-07-05T11:34:58Z"},{"alias_kind":"pith_short_16","alias_value":"IRIPJL66M5GEYBBD","created_at":"2026-07-05T11:34:58Z"},{"alias_kind":"pith_short_8","alias_value":"IRIPJL66","created_at":"2026-07-05T11:34:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IRIPJL66M5GEYBBDQ7GN6KYRFO","target":"record","payload":{"canonical_record":{"source":{"id":"2507.07451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T05:58:55Z","cross_cats_sorted":[],"title_canon_sha256":"6e940d0f99b315f7f13da3fcef0f3f41da94f264a9def7689ae5734cc39d768b","abstract_canon_sha256":"69abf5140e9a5657daa7d2b3fee2aec8f3a1292dab5b71fb107c28e6321bdd56"},"schema_version":"1.0"},"canonical_sha256":"4450f4afde674c4c042387ccdf2b112b9369b198c442afa0dca2ac47442ef213","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:58.442965Z","signature_b64":"ChrphzzlKj8Q8Lx8GcW5N5ZAlwQM5q1oRhw2C1/UKPczvf8Lb4EW9je2tS19gbaLkyw8B+boZJmkYNZdd3JHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4450f4afde674c4c042387ccdf2b112b9369b198c442afa0dca2ac47442ef213","last_reissued_at":"2026-07-05T11:34:58.442516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:58.442516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.07451","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":"2026-07-05T11:34:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sJ7Cgb1opF8ieXYXE4yVHhs6BCoZEXRevIsvxqrQ4braHmtm+7pBfsQj9onwSmro41Rt1WZiKfGN+SjACRkeCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:20:03.457824Z"},"content_sha256":"bdbff55815ba6f7e22ff07a24d2e572928cd22b564a04535e364e65f35e8d3e0","schema_version":"1.0","event_id":"sha256:bdbff55815ba6f7e22ff07a24d2e572928cd22b564a04535e364e65f35e8d3e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IRIPJL66M5GEYBBDQ7GN6KYRFO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RLEP: Reinforcement Learning with Experience Replay for LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fuzheng Zhang, Guorui Zhou, Hongzhi Zhang, Jia Fu, Jingyuan Zhang, Kai Fu, Qi Wang","submitted_at":"2025-07-10T05:58:55Z","abstract_excerpt":"Reinforcement learning (RL) for large language models is an energy-intensive endeavor: training can be unstable, and the policy may gradually drift away from its pretrained weights. We present \\emph{RLEP}\\, -- \\,Reinforcement Learning with Experience rePlay\\, -- \\,a two-phase framework that first collects verified trajectories and then replays them during subsequent training. At every update step, the policy is optimized on mini-batches that blend newly generated rollouts with these replayed successes. By replaying high-quality examples, RLEP steers the model away from fruitless exploration, f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07451","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/2507.07451/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":"2026-07-05T11:34:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ix0RRF7sJ9ZONX7gwemC3+sUZz10svyixPS1V+mmWkZDo1WdBEOrQSlzU6IZYZBjTq7DE1UIQT/kRBnCMxdJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:20:03.458111Z"},"content_sha256":"90eabbe4fb6f2081074460ec22afe81463b13b776715fedbc93737285f5e90c8","schema_version":"1.0","event_id":"sha256:90eabbe4fb6f2081074460ec22afe81463b13b776715fedbc93737285f5e90c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IRIPJL66M5GEYBBDQ7GN6KYRFO/bundle.json","state_url":"https://pith.science/pith/IRIPJL66M5GEYBBDQ7GN6KYRFO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IRIPJL66M5GEYBBDQ7GN6KYRFO/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":"2026-08-05T17:20:03Z","links":{"resolver":"https://pith.science/pith/IRIPJL66M5GEYBBDQ7GN6KYRFO","bundle":"https://pith.science/pith/IRIPJL66M5GEYBBDQ7GN6KYRFO/bundle.json","state":"https://pith.science/pith/IRIPJL66M5GEYBBDQ7GN6KYRFO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IRIPJL66M5GEYBBDQ7GN6KYRFO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IRIPJL66M5GEYBBDQ7GN6KYRFO","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":"69abf5140e9a5657daa7d2b3fee2aec8f3a1292dab5b71fb107c28e6321bdd56","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T05:58:55Z","title_canon_sha256":"6e940d0f99b315f7f13da3fcef0f3f41da94f264a9def7689ae5734cc39d768b"},"schema_version":"1.0","source":{"id":"2507.07451","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07451","created_at":"2026-07-05T11:34:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07451v1","created_at":"2026-07-05T11:34:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07451","created_at":"2026-07-05T11:34:58Z"},{"alias_kind":"pith_short_12","alias_value":"IRIPJL66M5GE","created_at":"2026-07-05T11:34:58Z"},{"alias_kind":"pith_short_16","alias_value":"IRIPJL66M5GEYBBD","created_at":"2026-07-05T11:34:58Z"},{"alias_kind":"pith_short_8","alias_value":"IRIPJL66","created_at":"2026-07-05T11:34:58Z"}],"graph_snapshots":[{"event_id":"sha256:90eabbe4fb6f2081074460ec22afe81463b13b776715fedbc93737285f5e90c8","target":"graph","created_at":"2026-07-05T11:34:58Z","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/2507.07451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) for large language models is an energy-intensive endeavor: training can be unstable, and the policy may gradually drift away from its pretrained weights. We present \\emph{RLEP}\\, -- \\,Reinforcement Learning with Experience rePlay\\, -- \\,a two-phase framework that first collects verified trajectories and then replays them during subsequent training. At every update step, the policy is optimized on mini-batches that blend newly generated rollouts with these replayed successes. By replaying high-quality examples, RLEP steers the model away from fruitless exploration, f","authors_text":"Fuzheng Zhang, Guorui Zhou, Hongzhi Zhang, Jia Fu, Jingyuan Zhang, Kai Fu, Qi Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T05:58:55Z","title":"RLEP: Reinforcement Learning with Experience Replay for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07451","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:bdbff55815ba6f7e22ff07a24d2e572928cd22b564a04535e364e65f35e8d3e0","target":"record","created_at":"2026-07-05T11:34:58Z","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":"69abf5140e9a5657daa7d2b3fee2aec8f3a1292dab5b71fb107c28e6321bdd56","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T05:58:55Z","title_canon_sha256":"6e940d0f99b315f7f13da3fcef0f3f41da94f264a9def7689ae5734cc39d768b"},"schema_version":"1.0","source":{"id":"2507.07451","kind":"arxiv","version":1}},"canonical_sha256":"4450f4afde674c4c042387ccdf2b112b9369b198c442afa0dca2ac47442ef213","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4450f4afde674c4c042387ccdf2b112b9369b198c442afa0dca2ac47442ef213","first_computed_at":"2026-07-05T11:34:58.442516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:58.442516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ChrphzzlKj8Q8Lx8GcW5N5ZAlwQM5q1oRhw2C1/UKPczvf8Lb4EW9je2tS19gbaLkyw8B+boZJmkYNZdd3JHDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:58.442965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07451","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bdbff55815ba6f7e22ff07a24d2e572928cd22b564a04535e364e65f35e8d3e0","sha256:90eabbe4fb6f2081074460ec22afe81463b13b776715fedbc93737285f5e90c8"],"state_sha256":"875a771c18c742912b8f72d64f38f92a1f21135167929267095c123238f23195"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mn7njvX8gbEuTWvKr3ZvJWutCX1aYtr/fKKgHE4iO3EopjHlhunVzgxqyxPnlEBk1gMAe6ek78Njvl+AqzfTBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:20:03.461077Z","bundle_sha256":"ac1fab42799cfb57fa147b11f131392787388b436c51e3ecf83eb78ff137bb08"}}