{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AB5U4DTNRN7QCYHN5UNZWE4PR4","short_pith_number":"pith:AB5U4DTN","canonical_record":{"source":{"id":"2605.28631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T15:38:09Z","cross_cats_sorted":[],"title_canon_sha256":"0dac031a26eea15924f6194a61745982a64346e3eaaea0bd8fa8bcf901ed5296","abstract_canon_sha256":"666cfcdfd3a130edfec5623c21c7e4b29515d3d1bc946c0d6f97b2f0c94c4b5f"},"schema_version":"1.0"},"canonical_sha256":"007b4e0e6d8b7f0160eded1b9b138f8f09f4c84269cf4edd941e7665d7cbccb1","source":{"kind":"arxiv","id":"2605.28631","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28631","created_at":"2026-05-28T02:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28631v1","created_at":"2026-05-28T02:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28631","created_at":"2026-05-28T02:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"AB5U4DTNRN7Q","created_at":"2026-05-28T02:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"AB5U4DTNRN7QCYHN","created_at":"2026-05-28T02:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"AB5U4DTN","created_at":"2026-05-28T02:04:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AB5U4DTNRN7QCYHN5UNZWE4PR4","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T15:38:09Z","cross_cats_sorted":[],"title_canon_sha256":"0dac031a26eea15924f6194a61745982a64346e3eaaea0bd8fa8bcf901ed5296","abstract_canon_sha256":"666cfcdfd3a130edfec5623c21c7e4b29515d3d1bc946c0d6f97b2f0c94c4b5f"},"schema_version":"1.0"},"canonical_sha256":"007b4e0e6d8b7f0160eded1b9b138f8f09f4c84269cf4edd941e7665d7cbccb1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:58.351890Z","signature_b64":"0r9ZpI0yVVP1lmEeXeGJXhD9YhZGOOlRS5NJBkQMmmOeOyl32Btk1CS615g/sZ1s9a6Djy4fIxPNYogc9DU5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"007b4e0e6d8b7f0160eded1b9b138f8f09f4c84269cf4edd941e7665d7cbccb1","last_reissued_at":"2026-05-28T02:04:58.351496Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:58.351496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28631","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":"2026-05-28T02:04:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qNx/mQTUCi39ea8/LR5fozT8B2YcSBZKuB/VlnK/R72QSJSzDixFa1mD23tOc+65HApUdq7dJeVa8yMSQmXdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:16:50.387829Z"},"content_sha256":"e425ab789399d4032d471c5d2f127a6fa4bc5b44cf00fa641e81b67f6b5afa10","schema_version":"1.0","event_id":"sha256:e425ab789399d4032d471c5d2f127a6fa4bc5b44cf00fa641e81b67f6b5afa10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AB5U4DTNRN7QCYHN5UNZWE4PR4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel F. Schmidt, Jianfei Cai, Jianghao Wu, Jin Ye, Weiqiang Wang, Yasmeen George","submitted_at":"2026-05-27T15:38:09Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) can yield large reasoning gains from very few training instances, yet its strong sensitivity to which instances are used makes data selection a central bottleneck. Most existing selection pipelines rely on training-time optimization signals and/or require access to verifiable rewards or ground-truth answers over large candidate pools, which is costly and often infeasible in specialized domains. We study RLVR data selection in a setting where selection must be performed before any RL training and without labels or reward evaluation on the fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28631","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/2605.28631/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":"2026-05-28T02:04:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C1xy7JsaIZF2vQqyUeYnZHblXpHNSqnEzxtbzbIlHfm8j4rfBrd4KFYh6i6ALtUdUQDk6r5M99axXrg/IdeIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:16:50.388209Z"},"content_sha256":"8f4816c62ce095ed65be44a3de1b354c31b242adf771fc4fee629560e29ab417","schema_version":"1.0","event_id":"sha256:8f4816c62ce095ed65be44a3de1b354c31b242adf771fc4fee629560e29ab417"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AB5U4DTNRN7QCYHN5UNZWE4PR4/bundle.json","state_url":"https://pith.science/pith/AB5U4DTNRN7QCYHN5UNZWE4PR4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AB5U4DTNRN7QCYHN5UNZWE4PR4/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":"2026-05-30T11:16:50Z","links":{"resolver":"https://pith.science/pith/AB5U4DTNRN7QCYHN5UNZWE4PR4","bundle":"https://pith.science/pith/AB5U4DTNRN7QCYHN5UNZWE4PR4/bundle.json","state":"https://pith.science/pith/AB5U4DTNRN7QCYHN5UNZWE4PR4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AB5U4DTNRN7QCYHN5UNZWE4PR4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AB5U4DTNRN7QCYHN5UNZWE4PR4","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":"666cfcdfd3a130edfec5623c21c7e4b29515d3d1bc946c0d6f97b2f0c94c4b5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T15:38:09Z","title_canon_sha256":"0dac031a26eea15924f6194a61745982a64346e3eaaea0bd8fa8bcf901ed5296"},"schema_version":"1.0","source":{"id":"2605.28631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28631","created_at":"2026-05-28T02:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28631v1","created_at":"2026-05-28T02:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28631","created_at":"2026-05-28T02:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"AB5U4DTNRN7Q","created_at":"2026-05-28T02:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"AB5U4DTNRN7QCYHN","created_at":"2026-05-28T02:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"AB5U4DTN","created_at":"2026-05-28T02:04:58Z"}],"graph_snapshots":[{"event_id":"sha256:8f4816c62ce095ed65be44a3de1b354c31b242adf771fc4fee629560e29ab417","target":"graph","created_at":"2026-05-28T02:04:58Z","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/2605.28631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) can yield large reasoning gains from very few training instances, yet its strong sensitivity to which instances are used makes data selection a central bottleneck. Most existing selection pipelines rely on training-time optimization signals and/or require access to verifiable rewards or ground-truth answers over large candidate pools, which is costly and often infeasible in specialized domains. We study RLVR data selection in a setting where selection must be performed before any RL training and without labels or reward evaluation on the fu","authors_text":"Daniel F. Schmidt, Jianfei Cai, Jianghao Wu, Jin Ye, Weiqiang Wang, Yasmeen George","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T15:38:09Z","title":"Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28631","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:e425ab789399d4032d471c5d2f127a6fa4bc5b44cf00fa641e81b67f6b5afa10","target":"record","created_at":"2026-05-28T02:04:58Z","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":"666cfcdfd3a130edfec5623c21c7e4b29515d3d1bc946c0d6f97b2f0c94c4b5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T15:38:09Z","title_canon_sha256":"0dac031a26eea15924f6194a61745982a64346e3eaaea0bd8fa8bcf901ed5296"},"schema_version":"1.0","source":{"id":"2605.28631","kind":"arxiv","version":1}},"canonical_sha256":"007b4e0e6d8b7f0160eded1b9b138f8f09f4c84269cf4edd941e7665d7cbccb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"007b4e0e6d8b7f0160eded1b9b138f8f09f4c84269cf4edd941e7665d7cbccb1","first_computed_at":"2026-05-28T02:04:58.351496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:58.351496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0r9ZpI0yVVP1lmEeXeGJXhD9YhZGOOlRS5NJBkQMmmOeOyl32Btk1CS615g/sZ1s9a6Djy4fIxPNYogc9DU5Ag==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:58.351890Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e425ab789399d4032d471c5d2f127a6fa4bc5b44cf00fa641e81b67f6b5afa10","sha256:8f4816c62ce095ed65be44a3de1b354c31b242adf771fc4fee629560e29ab417"],"state_sha256":"39c40ec6d75dc26bfd3a3fb257c68aaf61b470167d37207e25b038b075e098b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iv0VDFW0XY9Jeq5A+PPwjl3gCFpCnKWK3RtOttZ/Ye/buYnDCQ41v+rA41fy1MURrA/1rRxNbw4aGzqb0+gRBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T11:16:50.390470Z","bundle_sha256":"07549a2bef29e4a24f9bc894984d91b297c9bd070ad059568f855c34a6efe1e4"}}