{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QUZWYNORLJIQMM7OGIXDYZ67A3","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":"a6d3601289ae3f0b6587df18435cb3f3dad96e3287272c3df668d29e550e4877","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:48:28Z","title_canon_sha256":"ccdfd49330a259b2cb7e89646ae4180f90aa3dc7415ce5454b7ad25eb282e153"},"schema_version":"1.0","source":{"id":"2606.03800","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03800","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03800v1","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03800","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"pith_short_12","alias_value":"QUZWYNORLJIQ","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"pith_short_16","alias_value":"QUZWYNORLJIQMM7O","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"pith_short_8","alias_value":"QUZWYNOR","created_at":"2026-06-03T02:06:02Z"}],"graph_snapshots":[{"event_id":"sha256:9efd595924d48b6291e116dbeaeb27987ff08016d20f418ff7877c410bed8571","target":"graph","created_at":"2026-06-03T02:06:02Z","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/2606.03800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The supply of high-quality training tasks is a central bottleneck for reinforcement learning from verifiable rewards (RLVR) on agentic language models. Each task requires a sandboxed setup, a prompt, and a hand-authored reward function, and only tasks that pass a quality bar produce useful training signal. Hand-curation at this quality bar does not scale economically to the task counts effective RL training requires, and the substitution rate between automatically generated task variants and human-authored ones is not yet established. We investigate using pre-specified, gate-filtered augmentat","authors_text":"Akshansh <last>, Leonardo Rosa Rodrigues, Mark E. Whiting, Michael Korostelev, Youssef Hassan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:48:28Z","title":"Trading Human Curation for Synthetic Augmentation in RLVR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03800","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":"sha256:4d991d2e3c0b02259f0f7b2aa437a951050810439ac877174bc5a59a74c9cbe3","target":"record","created_at":"2026-06-03T02:06:02Z","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":"a6d3601289ae3f0b6587df18435cb3f3dad96e3287272c3df668d29e550e4877","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:48:28Z","title_canon_sha256":"ccdfd49330a259b2cb7e89646ae4180f90aa3dc7415ce5454b7ad25eb282e153"},"schema_version":"1.0","source":{"id":"2606.03800","kind":"arxiv","version":1}},"canonical_sha256":"85336c35d15a510633ee322e3c67df06d730c451340228941d4f390d32bf8796","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85336c35d15a510633ee322e3c67df06d730c451340228941d4f390d32bf8796","first_computed_at":"2026-06-03T02:06:02.781635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:06:02.781635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"749sW3vkdblVMcUn+dJ8dVU0kak7YgYNvLP6CplMSA9WWuUOC06ABocMlbwlR0DOkNCq6t5QtonUj3F9N9BMAw==","signature_status":"signed_v1","signed_at":"2026-06-03T02:06:02.782086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03800","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d991d2e3c0b02259f0f7b2aa437a951050810439ac877174bc5a59a74c9cbe3","sha256:9efd595924d48b6291e116dbeaeb27987ff08016d20f418ff7877c410bed8571"],"state_sha256":"9f9f63ab719f065dee3885d4ce15d7151d174891eb5ad9b2ba5ddf0b626ae43a"}