{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZZHS6EFREHFRH4R3HSLH2N7LFX","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":"25d451caac25505aba206317438cb05b3ed1598055c10505323ec952178da5e0","cross_cats_sorted":["cs.AI","math.GR","math.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T17:14:47Z","title_canon_sha256":"d1569faa7d518cd3c7ed838f30fe8fd35fd318098a1648b5a5ecd1393a46a96c"},"schema_version":"1.0","source":{"id":"2606.21611","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21611","created_at":"2026-06-23T01:13:16Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21611v1","created_at":"2026-06-23T01:13:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21611","created_at":"2026-06-23T01:13:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZZHS6EFREHFR","created_at":"2026-06-23T01:13:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZZHS6EFREHFRH4R3","created_at":"2026-06-23T01:13:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZZHS6EFR","created_at":"2026-06-23T01:13:16Z"}],"graph_snapshots":[{"event_id":"sha256:e21769f836afc3897f32e6ad893a5edb73cb72985a74168d65db5c30baa62029","target":"graph","created_at":"2026-06-23T01:13:16Z","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/2606.21611/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mathematical search problems present a unique challenge for Reinforcement Learning (RL) due to vast search spaces and sparse rewards. In previous works, the Andrews-Curtis (AC) conjecture was established as an illustrative example of such problems. In this work, we identify a critical structural barrier in the AC landscape: a \"Two-Hump\" distribution, where problem instances are either trivially solvable or effectively impossible, with a scarcity of intermediate \"hard-but-solvable\" instances required for effective learning. We tackle this challenge through two primary avenues: novel data genera","authors_text":"Ali Shehper, Angus Gruen, Coco Huang, Davide Passaro, Giorgi Butbaia, Lucas Fagan, Maksymilian Manko, Michele Tarquini, Sergei Gukov","cross_cats":["cs.AI","math.GR","math.GT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T17:14:47Z","title":"The Two-Hump Problem: Bridging the Difficulty Gap in Mathematical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21611","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":"sha256:2e4f45a6146e5f9d68c780960df2e78ca5533d85929b96d273567c574763feec","target":"record","created_at":"2026-06-23T01:13:16Z","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":"25d451caac25505aba206317438cb05b3ed1598055c10505323ec952178da5e0","cross_cats_sorted":["cs.AI","math.GR","math.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-19T17:14:47Z","title_canon_sha256":"d1569faa7d518cd3c7ed838f30fe8fd35fd318098a1648b5a5ecd1393a46a96c"},"schema_version":"1.0","source":{"id":"2606.21611","kind":"arxiv","version":1}},"canonical_sha256":"ce4f2f10b121cb13f23b3c967d37eb2df7df675cfa71a7615d4b00b659d15421","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce4f2f10b121cb13f23b3c967d37eb2df7df675cfa71a7615d4b00b659d15421","first_computed_at":"2026-06-23T01:13:16.268456Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:13:16.268456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RCoUxAi1BW+k/mITAib8+NkM3c7PPpjovreAkAY1cWYkDTkFX7OXDHKKL68i3gEvVGkV/+t8zWLsv9TPKheECA==","signature_status":"signed_v1","signed_at":"2026-06-23T01:13:16.268946Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21611","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e4f45a6146e5f9d68c780960df2e78ca5533d85929b96d273567c574763feec","sha256:e21769f836afc3897f32e6ad893a5edb73cb72985a74168d65db5c30baa62029"],"state_sha256":"e18e1f2223c5decb1061a88a50f0099baaede924edf7028d1acc831484189d55"}