{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4JWLZWWXCW7CIVQRLRYRWONX6I","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":"d2abf722253770b89c15d6b64aeec1e5a6db4bc985c0660919b745ed523f878c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T12:28:08Z","title_canon_sha256":"e623552df1af570fdf561262e8567497c51ab242e4e818fdd7c290613f6cbf02"},"schema_version":"1.0","source":{"id":"2605.26934","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26934","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26934v1","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26934","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"4JWLZWWXCW7C","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"4JWLZWWXCW7CIVQR","created_at":"2026-05-27T01:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"4JWLZWWX","created_at":"2026-05-27T01:06:20Z"}],"graph_snapshots":[{"event_id":"sha256:1309584fe8388e0d974db898102552325a618cbee635de1b34aadc6b106d622b","target":"graph","created_at":"2026-05-27T01:06:20Z","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/2605.26934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has become central to post-training reasoning models, yet a key limitation of existing studies is their narrow view of the reasoning space: difficulty is treated as reasoning depth alone, and reward is concentrated on forward deductive state tracking. We instead characterize the reasoning space along two dimensions. Difficulty. Beyond reasoning depth, we study environment complexity, where models must identify the correct path amid distractors and interacting structures. Rewarded reasoning form. We consider four abilities core to real-world","authors_text":"Akiko Aizawa, Fei Cheng, Hidetoshi Shimodaira, Jiaxin Wang, Qianying Liu, Sadao Kurohashi, Yihua Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T12:28:08Z","title":"Reasoning Depth and Environment Complexity: A Controlled Study of RLVR Data Allocation across Logical Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26934","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:a2a3f97b4d7cc070c06e0eda56eb1270d33e2c1c53beb0c18beb388b2549c320","target":"record","created_at":"2026-05-27T01:06:20Z","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":"d2abf722253770b89c15d6b64aeec1e5a6db4bc985c0660919b745ed523f878c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T12:28:08Z","title_canon_sha256":"e623552df1af570fdf561262e8567497c51ab242e4e818fdd7c290613f6cbf02"},"schema_version":"1.0","source":{"id":"2605.26934","kind":"arxiv","version":1}},"canonical_sha256":"e26cbcdad715be2456115c711b39b7f222aff8ebc96b306f49567df5539de599","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e26cbcdad715be2456115c711b39b7f222aff8ebc96b306f49567df5539de599","first_computed_at":"2026-05-27T01:06:20.659366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:06:20.659366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IADy6Xf/FTt/a9l9twO/bHTC/IDUgjO5or3FjI7b7UiljbI7QjQnYeM2x4mpfg9PYnP56R1TX4JbWXiBtBJ8Dw==","signature_status":"signed_v1","signed_at":"2026-05-27T01:06:20.660163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26934","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2a3f97b4d7cc070c06e0eda56eb1270d33e2c1c53beb0c18beb388b2549c320","sha256:1309584fe8388e0d974db898102552325a618cbee635de1b34aadc6b106d622b"],"state_sha256":"5fccd14f325b482e228a51e958b23d9097466b541f498f53fca5abd3aae56aa7"}