{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GZC6EAZPDRDSCBQFTTMDI4WVCO","short_pith_number":"pith:GZC6EAZP","canonical_record":{"source":{"id":"2507.06892","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T14:29:45Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"709bcd98843228718f5f149a7677eaf705385f62e21ed9b7353ad94f2e82f70e","abstract_canon_sha256":"665761fadaaaf49c690dcf290b9fc12b2b11cbf486d34dcf88d6ff9fd3f6b9a6"},"schema_version":"1.0"},"canonical_sha256":"3645e2032f1c472106059cd83472d513b39c695f4f75a2ca9cd2c1b6294c7c30","source":{"kind":"arxiv","id":"2507.06892","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06892","created_at":"2026-07-05T11:35:36Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06892v3","created_at":"2026-07-05T11:35:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06892","created_at":"2026-07-05T11:35:36Z"},{"alias_kind":"pith_short_12","alias_value":"GZC6EAZPDRDS","created_at":"2026-07-05T11:35:36Z"},{"alias_kind":"pith_short_16","alias_value":"GZC6EAZPDRDSCBQF","created_at":"2026-07-05T11:35:36Z"},{"alias_kind":"pith_short_8","alias_value":"GZC6EAZP","created_at":"2026-07-05T11:35:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GZC6EAZPDRDSCBQFTTMDI4WVCO","target":"record","payload":{"canonical_record":{"source":{"id":"2507.06892","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T14:29:45Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"709bcd98843228718f5f149a7677eaf705385f62e21ed9b7353ad94f2e82f70e","abstract_canon_sha256":"665761fadaaaf49c690dcf290b9fc12b2b11cbf486d34dcf88d6ff9fd3f6b9a6"},"schema_version":"1.0"},"canonical_sha256":"3645e2032f1c472106059cd83472d513b39c695f4f75a2ca9cd2c1b6294c7c30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:36.380187Z","signature_b64":"PT5vF+6CMAvFzsSujtWltQ/oBg3PcMHOa1nNZN1lwlIikzjs1euFf0f3MM+uC5wFdgV4swgPa1xx3TmW5eCzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3645e2032f1c472106059cd83472d513b39c695f4f75a2ca9cd2c1b6294c7c30","last_reissued_at":"2026-07-05T11:35:36.379677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:36.379677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.06892","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:35:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LQlcZxTD/6/rTKnjccIJqfbElv79SFhqZVCTsUkjExrvgOLKQ2KIUK803VlO/EGMMn40rsC/QVcRI28was1iAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:17:23.227984Z"},"content_sha256":"5a7ee1b762ee1c11a7187d79c16f24f9bd18b533143f95faba4c5a3d2f2c6876","schema_version":"1.0","event_id":"sha256:5a7ee1b762ee1c11a7187d79c16f24f9bd18b533143f95faba4c5a3d2f2c6876"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GZC6EAZPDRDSCBQFTTMDI4WVCO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hongyao Tang, Jianye Hao, Jing Liang, Jinyi Liu, Lei Bai, Shuyue Hu, Yan Zheng, Yi Ma","submitted_at":"2025-07-09T14:29:45Z","abstract_excerpt":"Reinforcement Learning (RL) has demonstrated its potential to improve the reasoning ability of Large Language Models (LLMs). One major limitation of most existing Reinforcement Finetuning (RFT) methods is that they are on-policy RL in nature, i.e., data generated during the past learning process is not fully utilized. This inevitably comes at a significant cost of compute and time, posing a stringent bottleneck on continuing economic and efficient scaling. To this end, we launch the renaissance of off-policy RL and propose Reincarnating Mix-policy Proximal Policy Gradient (ReMix), a general ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06892","kind":"arxiv","version":3},"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/2507.06892/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":"2026-07-05T11:35:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eO3kjkD9c7X8h28h+Xx8RHE83uJMin8Zmuc7dtxwhl+XE7vom6dM2mECH3mIawkT/gjK3TW9CTDZeGBc3jN/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:17:23.228913Z"},"content_sha256":"d7b9ce494e396f5d39ba5ec34b75f955ccaa7365a004ed6cf011214c97271244","schema_version":"1.0","event_id":"sha256:d7b9ce494e396f5d39ba5ec34b75f955ccaa7365a004ed6cf011214c97271244"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GZC6EAZPDRDSCBQFTTMDI4WVCO/bundle.json","state_url":"https://pith.science/pith/GZC6EAZPDRDSCBQFTTMDI4WVCO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GZC6EAZPDRDSCBQFTTMDI4WVCO/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":"2026-08-03T15:17:23Z","links":{"resolver":"https://pith.science/pith/GZC6EAZPDRDSCBQFTTMDI4WVCO","bundle":"https://pith.science/pith/GZC6EAZPDRDSCBQFTTMDI4WVCO/bundle.json","state":"https://pith.science/pith/GZC6EAZPDRDSCBQFTTMDI4WVCO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GZC6EAZPDRDSCBQFTTMDI4WVCO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GZC6EAZPDRDSCBQFTTMDI4WVCO","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":"665761fadaaaf49c690dcf290b9fc12b2b11cbf486d34dcf88d6ff9fd3f6b9a6","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T14:29:45Z","title_canon_sha256":"709bcd98843228718f5f149a7677eaf705385f62e21ed9b7353ad94f2e82f70e"},"schema_version":"1.0","source":{"id":"2507.06892","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06892","created_at":"2026-07-05T11:35:36Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06892v3","created_at":"2026-07-05T11:35:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06892","created_at":"2026-07-05T11:35:36Z"},{"alias_kind":"pith_short_12","alias_value":"GZC6EAZPDRDS","created_at":"2026-07-05T11:35:36Z"},{"alias_kind":"pith_short_16","alias_value":"GZC6EAZPDRDSCBQF","created_at":"2026-07-05T11:35:36Z"},{"alias_kind":"pith_short_8","alias_value":"GZC6EAZP","created_at":"2026-07-05T11:35:36Z"}],"graph_snapshots":[{"event_id":"sha256:d7b9ce494e396f5d39ba5ec34b75f955ccaa7365a004ed6cf011214c97271244","target":"graph","created_at":"2026-07-05T11:35:36Z","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/2507.06892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has demonstrated its potential to improve the reasoning ability of Large Language Models (LLMs). One major limitation of most existing Reinforcement Finetuning (RFT) methods is that they are on-policy RL in nature, i.e., data generated during the past learning process is not fully utilized. This inevitably comes at a significant cost of compute and time, posing a stringent bottleneck on continuing economic and efficient scaling. To this end, we launch the renaissance of off-policy RL and propose Reincarnating Mix-policy Proximal Policy Gradient (ReMix), a general ap","authors_text":"Hongyao Tang, Jianye Hao, Jing Liang, Jinyi Liu, Lei Bai, Shuyue Hu, Yan Zheng, Yi Ma","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T14:29:45Z","title":"Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06892","kind":"arxiv","version":3},"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":"sha256:5a7ee1b762ee1c11a7187d79c16f24f9bd18b533143f95faba4c5a3d2f2c6876","target":"record","created_at":"2026-07-05T11:35:36Z","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":"665761fadaaaf49c690dcf290b9fc12b2b11cbf486d34dcf88d6ff9fd3f6b9a6","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T14:29:45Z","title_canon_sha256":"709bcd98843228718f5f149a7677eaf705385f62e21ed9b7353ad94f2e82f70e"},"schema_version":"1.0","source":{"id":"2507.06892","kind":"arxiv","version":3}},"canonical_sha256":"3645e2032f1c472106059cd83472d513b39c695f4f75a2ca9cd2c1b6294c7c30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3645e2032f1c472106059cd83472d513b39c695f4f75a2ca9cd2c1b6294c7c30","first_computed_at":"2026-07-05T11:35:36.379677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:36.379677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PT5vF+6CMAvFzsSujtWltQ/oBg3PcMHOa1nNZN1lwlIikzjs1euFf0f3MM+uC5wFdgV4swgPa1xx3TmW5eCzCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:36.380187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06892","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a7ee1b762ee1c11a7187d79c16f24f9bd18b533143f95faba4c5a3d2f2c6876","sha256:d7b9ce494e396f5d39ba5ec34b75f955ccaa7365a004ed6cf011214c97271244"],"state_sha256":"b4f0617a7a4f08597c9ba2e58624cf6f071644dbbf0c332cd4831d62b869b659"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Se8KyLf8HXAb/N+v+z7gobTXlxKiTeFIPdKygTvQVDBmk6MwQQrsG5T0wr9TAJkPqhQTXs6E/MzKslMN4r7lDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:17:23.236369Z","bundle_sha256":"353e380a8e4aeaf0f16d2ea212fa2a0b28744852408e27d4604380f408a86dc7"}}