{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MCRSEHQTFAULTYE5A6SUBSCCDW","short_pith_number":"pith:MCRSEHQT","canonical_record":{"source":{"id":"2505.12457","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T15:14:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b116ce40a1ce423cfabcd76626a9bc1a9250fa8371b115506d4e0f4138e4094a","abstract_canon_sha256":"970a46942981ece8989aecbd00062169e0dff42baf09611986dffd9f77eb0053"},"schema_version":"1.0"},"canonical_sha256":"60a3221e132828b9e09d07a540c8421d8165291af2a6d22db8d312b34efa84bb","source":{"kind":"arxiv","id":"2505.12457","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12457","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12457v1","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12457","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"MCRSEHQTFAUL","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"MCRSEHQTFAULTYE5","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"MCRSEHQT","created_at":"2026-07-05T11:05:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MCRSEHQTFAULTYE5A6SUBSCCDW","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12457","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T15:14:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b116ce40a1ce423cfabcd76626a9bc1a9250fa8371b115506d4e0f4138e4094a","abstract_canon_sha256":"970a46942981ece8989aecbd00062169e0dff42baf09611986dffd9f77eb0053"},"schema_version":"1.0"},"canonical_sha256":"60a3221e132828b9e09d07a540c8421d8165291af2a6d22db8d312b34efa84bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:04.688767Z","signature_b64":"ByDksUevDC7OVbupVmMKLmFtv/F1XjRfUVsgaB+UJSsy9hCK4BKehRC7ZGhpgkjFqbd4SAKRbMxbVpcXBnUQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60a3221e132828b9e09d07a540c8421d8165291af2a6d22db8d312b34efa84bb","last_reissued_at":"2026-07-05T11:05:04.688217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:04.688217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12457","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":"2026-07-05T11:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jdEiyiG8Q+WSy2h+75BW1cOLgP4YHbCPUlNKPepk+q5yan1+KZGPNKIRpmPNXP0iA9w0qlcVqZx+aq76VWlXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:44:19.148869Z"},"content_sha256":"ff1e9a353d20ac2f43cb93a801abd18913832aaadefbcc301c3bafb98e403483","schema_version":"1.0","event_id":"sha256:ff1e9a353d20ac2f43cb93a801abd18913832aaadefbcc301c3bafb98e403483"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MCRSEHQTFAULTYE5A6SUBSCCDW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bing Qin, Bin Liu, Dong Hu, Jiannan Guan, Kai Xiong, Li Du, Ting Liu, Wenbin Zhang, Xiao Ding, YangouOuyang, Yang Zhao, Zhouhao Sun","submitted_at":"2025-05-18T15:14:58Z","abstract_excerpt":"Scaling RL for LLMs is computationally expensive, largely due to multi-sampling for policy optimization and evaluation, making efficient data selection crucial. Inspired by the Zone of Proximal Development (ZPD) theory, we hypothesize LLMs learn best from data within their potential comprehension zone. Addressing the limitation of conventional, computationally intensive multi-sampling methods for data assessment, we introduce UFO-RL. This novel framework uses a computationally efficient single-pass uncertainty estimation to identify informative data instances, achieving up to 185x faster data "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12457","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/2505.12457/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":"2026-07-05T11:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cbjCGrwYbh4N0lc858+vY+CIRvWb7QR/7p3gzSyCFK/sxHwiyyUnaPBSAAIq+RNaOhWpLEEngAX1m28+56mpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:44:19.149177Z"},"content_sha256":"f4dd046a5556bab7ca903d53b0564fe601db983ea058d3b8dbc34373253043e8","schema_version":"1.0","event_id":"sha256:f4dd046a5556bab7ca903d53b0564fe601db983ea058d3b8dbc34373253043e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MCRSEHQTFAULTYE5A6SUBSCCDW/bundle.json","state_url":"https://pith.science/pith/MCRSEHQTFAULTYE5A6SUBSCCDW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MCRSEHQTFAULTYE5A6SUBSCCDW/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":"2026-08-18T05:44:19Z","links":{"resolver":"https://pith.science/pith/MCRSEHQTFAULTYE5A6SUBSCCDW","bundle":"https://pith.science/pith/MCRSEHQTFAULTYE5A6SUBSCCDW/bundle.json","state":"https://pith.science/pith/MCRSEHQTFAULTYE5A6SUBSCCDW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MCRSEHQTFAULTYE5A6SUBSCCDW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MCRSEHQTFAULTYE5A6SUBSCCDW","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":"970a46942981ece8989aecbd00062169e0dff42baf09611986dffd9f77eb0053","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T15:14:58Z","title_canon_sha256":"b116ce40a1ce423cfabcd76626a9bc1a9250fa8371b115506d4e0f4138e4094a"},"schema_version":"1.0","source":{"id":"2505.12457","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12457","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12457v1","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12457","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"MCRSEHQTFAUL","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"MCRSEHQTFAULTYE5","created_at":"2026-07-05T11:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"MCRSEHQT","created_at":"2026-07-05T11:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:f4dd046a5556bab7ca903d53b0564fe601db983ea058d3b8dbc34373253043e8","target":"graph","created_at":"2026-07-05T11:05:04Z","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/2505.12457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling RL for LLMs is computationally expensive, largely due to multi-sampling for policy optimization and evaluation, making efficient data selection crucial. Inspired by the Zone of Proximal Development (ZPD) theory, we hypothesize LLMs learn best from data within their potential comprehension zone. Addressing the limitation of conventional, computationally intensive multi-sampling methods for data assessment, we introduce UFO-RL. This novel framework uses a computationally efficient single-pass uncertainty estimation to identify informative data instances, achieving up to 185x faster data ","authors_text":"Bing Qin, Bin Liu, Dong Hu, Jiannan Guan, Kai Xiong, Li Du, Ting Liu, Wenbin Zhang, Xiao Ding, YangouOuyang, Yang Zhao, Zhouhao Sun","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T15:14:58Z","title":"UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12457","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:ff1e9a353d20ac2f43cb93a801abd18913832aaadefbcc301c3bafb98e403483","target":"record","created_at":"2026-07-05T11:05:04Z","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":"970a46942981ece8989aecbd00062169e0dff42baf09611986dffd9f77eb0053","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T15:14:58Z","title_canon_sha256":"b116ce40a1ce423cfabcd76626a9bc1a9250fa8371b115506d4e0f4138e4094a"},"schema_version":"1.0","source":{"id":"2505.12457","kind":"arxiv","version":1}},"canonical_sha256":"60a3221e132828b9e09d07a540c8421d8165291af2a6d22db8d312b34efa84bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60a3221e132828b9e09d07a540c8421d8165291af2a6d22db8d312b34efa84bb","first_computed_at":"2026-07-05T11:05:04.688217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:04.688217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ByDksUevDC7OVbupVmMKLmFtv/F1XjRfUVsgaB+UJSsy9hCK4BKehRC7ZGhpgkjFqbd4SAKRbMxbVpcXBnUQDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:04.688767Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12457","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff1e9a353d20ac2f43cb93a801abd18913832aaadefbcc301c3bafb98e403483","sha256:f4dd046a5556bab7ca903d53b0564fe601db983ea058d3b8dbc34373253043e8"],"state_sha256":"05bc9083df22890ea54fc35f5e2fdc687080e8bd630a54b37c8887fe77b4b34c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zIzwttGtuITDLJ1yRGARlkHZIcnZ9ecMI3qYBq1Gp/yT2qqxJ2ydTRl2qnt+MhV3+bq7JufnTb4RbPBlGzT8Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T05:44:19.153445Z","bundle_sha256":"504a45048d0273762ac19bcc8dabd808a42e1df32427ce4296797c1951bea9b3"}}