{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X6FFZMGWIQV3WM3E42M77HOMBO","short_pith_number":"pith:X6FFZMGW","schema_version":"1.0","canonical_sha256":"bf8a5cb0d6442bbb3364e699ff9dcc0b983d245aabc310fd8dcc8b2dffc23f82","source":{"kind":"arxiv","id":"2408.15332","version":2},"attestation_state":"computed","paper":{"title":"What makes math problems hard for reinforcement learning: a case study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.CO","math.GR","math.GT"],"primary_cat":"cs.LG","authors_text":"Ali Shehper, Angus Gruen, Anibal M. Medina-Mardones, Bart{\\l}omiej Lewandowski, Lucas Fagan, Piotr Kucharski, Sergei Gukov, Yang Qiu, Zhenghan Wang","submitted_at":"2024-08-27T18:00:06Z","abstract_excerpt":"Using a long-standing conjecture from combinatorial group theory, we explore, from multiple perspectives, the challenges of finding rare instances carrying disproportionately high rewards. Based on lessons learned in the context defined by the Andrews-Curtis conjecture, we propose algorithmic enhancements and a topological hardness measure with implications for a broad class of search problems. As part of our study, we also address several open mathematical questions. Notably, we demonstrate the length reducibility of all but two presentations in the Akbulut-Kirby series (1981), and resolve va"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2408.15332","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T18:00:06Z","cross_cats_sorted":["cs.AI","math.CO","math.GR","math.GT"],"title_canon_sha256":"41d64381ec17a87316196eed70ca2bb223436db2daad2dceb7a9b82d037c6044","abstract_canon_sha256":"b6a1188c2c98e5f8576aa34765be5324afc6de679c2865afef23c9adaab369e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:48.646690Z","signature_b64":"ZPENYclp5xm7P4gdlYVdkw7/yJY/4E7hK7Y9K88i7fdyt3cVGF8SsvT8ZEPPsce8TxdAlaKFMQ87JABFAJ/dAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf8a5cb0d6442bbb3364e699ff9dcc0b983d245aabc310fd8dcc8b2dffc23f82","last_reissued_at":"2026-07-05T10:12:48.646150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:48.646150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What makes math problems hard for reinforcement learning: a case study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.CO","math.GR","math.GT"],"primary_cat":"cs.LG","authors_text":"Ali Shehper, Angus Gruen, Anibal M. Medina-Mardones, Bart{\\l}omiej Lewandowski, Lucas Fagan, Piotr Kucharski, Sergei Gukov, Yang Qiu, Zhenghan Wang","submitted_at":"2024-08-27T18:00:06Z","abstract_excerpt":"Using a long-standing conjecture from combinatorial group theory, we explore, from multiple perspectives, the challenges of finding rare instances carrying disproportionately high rewards. Based on lessons learned in the context defined by the Andrews-Curtis conjecture, we propose algorithmic enhancements and a topological hardness measure with implications for a broad class of search problems. As part of our study, we also address several open mathematical questions. Notably, we demonstrate the length reducibility of all but two presentations in the Akbulut-Kirby series (1981), and resolve va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15332","kind":"arxiv","version":2},"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/2408.15332/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2408.15332","created_at":"2026-07-05T10:12:48.646215+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15332v2","created_at":"2026-07-05T10:12:48.646215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15332","created_at":"2026-07-05T10:12:48.646215+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6FFZMGWIQV3","created_at":"2026-07-05T10:12:48.646215+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6FFZMGWIQV3WM3E","created_at":"2026-07-05T10:12:48.646215+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6FFZMGW","created_at":"2026-07-05T10:12:48.646215+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30220","citing_title":"TriSearch: Learning to Optimize Triangulations via Bistellar Flips","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6FFZMGWIQV3WM3E42M77HOMBO","json":"https://pith.science/pith/X6FFZMGWIQV3WM3E42M77HOMBO.json","graph_json":"https://pith.science/api/pith-number/X6FFZMGWIQV3WM3E42M77HOMBO/graph.json","events_json":"https://pith.science/api/pith-number/X6FFZMGWIQV3WM3E42M77HOMBO/events.json","paper":"https://pith.science/paper/X6FFZMGW"},"agent_actions":{"view_html":"https://pith.science/pith/X6FFZMGWIQV3WM3E42M77HOMBO","download_json":"https://pith.science/pith/X6FFZMGWIQV3WM3E42M77HOMBO.json","view_paper":"https://pith.science/paper/X6FFZMGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15332&json=true","fetch_graph":"https://pith.science/api/pith-number/X6FFZMGWIQV3WM3E42M77HOMBO/graph.json","fetch_events":"https://pith.science/api/pith-number/X6FFZMGWIQV3WM3E42M77HOMBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6FFZMGWIQV3WM3E42M77HOMBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6FFZMGWIQV3WM3E42M77HOMBO/action/storage_attestation","attest_author":"https://pith.science/pith/X6FFZMGWIQV3WM3E42M77HOMBO/action/author_attestation","sign_citation":"https://pith.science/pith/X6FFZMGWIQV3WM3E42M77HOMBO/action/citation_signature","submit_replication":"https://pith.science/pith/X6FFZMGWIQV3WM3E42M77HOMBO/action/replication_record"}},"created_at":"2026-07-05T10:12:48.646215+00:00","updated_at":"2026-07-05T10:12:48.646215+00:00"}