{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3HGPULRI2KMWO6G77HUHZHMW5E","short_pith_number":"pith:3HGPULRI","schema_version":"1.0","canonical_sha256":"d9ccfa2e28d2996778dff9e87c9d96e939030633ead2bccbaaec6090f597a4ad","source":{"kind":"arxiv","id":"2502.18663","version":3},"attestation_state":"computed","paper":{"title":"CayleyPy RL: Pathfinding and Reinforcement Learning on Cayley Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DM","cs.SI","math.CO","math.GR"],"primary_cat":"cs.LG","authors_text":"A. Chervov, A. Dolgorukova, A. Eliseev, A. Korolkova, A. Lukyanenko, A. Ogurtsov, A. Romanov, A. Rozanov, A. Soibelman, A. Sychev, D. Gorodkov, D. Mamayeva, F. Petrov, G. Antiufeev, G. Verbii, I. Kiselev, I. Koltsov, K. Khoruzhii, L. Cheldieva, L. Grunvald, L. Shishina, M. Evseev, M. Obozov, N. Narynbaev, N. Rokotyan, R. Turtayev, S. Ermilov, S. Fironov, S. Kovalev, S. Krymskii, S. Lytkin, S. Nikolenko, V. Nelin, V. Zamkovoy","submitted_at":"2025-02-25T21:53:41Z","abstract_excerpt":"This paper is the second in a series of studies on developing efficient artificial intelligence-based approaches to pathfinding on extremely large graphs (e.g. $10^{70}$ nodes) with a focus on Cayley graphs and mathematical applications. The open-source CayleyPy project is a central component of our research. The present paper proposes a novel combination of a reinforcement learning approach with a more direct diffusion distance approach from the first paper. Our analysis includes benchmarking various choices for the key building blocks of the approach: architectures of the neural network, gen"},"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":"2502.18663","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T21:53:41Z","cross_cats_sorted":["cs.DM","cs.SI","math.CO","math.GR"],"title_canon_sha256":"1986f180822dff062c825a24166514ec26cc19e77a16fa262492279e5520d650","abstract_canon_sha256":"37596810213480a5047bd5ac44bc33b40de3c4c7f18c02e804fd50d9211ff4c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:04.100407Z","signature_b64":"ohdx8NAxKZhZd9vX0HSg8BTUoZ1jbumSz275pF/yUh+SQ8OJ1PRqis0ppH8Jfezkai/WcYz2ACYbT/MpCE8jDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9ccfa2e28d2996778dff9e87c9d96e939030633ead2bccbaaec6090f597a4ad","last_reissued_at":"2026-05-20T00:02:04.099539Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:04.099539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CayleyPy RL: Pathfinding and Reinforcement Learning on Cayley Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DM","cs.SI","math.CO","math.GR"],"primary_cat":"cs.LG","authors_text":"A. Chervov, A. Dolgorukova, A. Eliseev, A. Korolkova, A. Lukyanenko, A. Ogurtsov, A. Romanov, A. Rozanov, A. Soibelman, A. Sychev, D. Gorodkov, D. Mamayeva, F. Petrov, G. Antiufeev, G. Verbii, I. Kiselev, I. Koltsov, K. Khoruzhii, L. Cheldieva, L. Grunvald, L. Shishina, M. Evseev, M. Obozov, N. Narynbaev, N. Rokotyan, R. Turtayev, S. Ermilov, S. Fironov, S. Kovalev, S. Krymskii, S. Lytkin, S. Nikolenko, V. Nelin, V. Zamkovoy","submitted_at":"2025-02-25T21:53:41Z","abstract_excerpt":"This paper is the second in a series of studies on developing efficient artificial intelligence-based approaches to pathfinding on extremely large graphs (e.g. $10^{70}$ nodes) with a focus on Cayley graphs and mathematical applications. The open-source CayleyPy project is a central component of our research. The present paper proposes a novel combination of a reinforcement learning approach with a more direct diffusion distance approach from the first paper. Our analysis includes benchmarking various choices for the key building blocks of the approach: architectures of the neural network, gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18663","kind":"arxiv","version":3},"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/2502.18663/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":"2502.18663","created_at":"2026-05-20T00:02:04.099687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18663v3","created_at":"2026-05-20T00:02:04.099687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18663","created_at":"2026-05-20T00:02:04.099687+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HGPULRI2KMW","created_at":"2026-05-20T00:02:04.099687+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HGPULRI2KMWO6G7","created_at":"2026-05-20T00:02:04.099687+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HGPULRI","created_at":"2026-05-20T00:02:04.099687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2601.13209","citing_title":"AI for Mathematics: Progress, Challenges, and Prospects","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HGPULRI2KMWO6G77HUHZHMW5E","json":"https://pith.science/pith/3HGPULRI2KMWO6G77HUHZHMW5E.json","graph_json":"https://pith.science/api/pith-number/3HGPULRI2KMWO6G77HUHZHMW5E/graph.json","events_json":"https://pith.science/api/pith-number/3HGPULRI2KMWO6G77HUHZHMW5E/events.json","paper":"https://pith.science/paper/3HGPULRI"},"agent_actions":{"view_html":"https://pith.science/pith/3HGPULRI2KMWO6G77HUHZHMW5E","download_json":"https://pith.science/pith/3HGPULRI2KMWO6G77HUHZHMW5E.json","view_paper":"https://pith.science/paper/3HGPULRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18663&json=true","fetch_graph":"https://pith.science/api/pith-number/3HGPULRI2KMWO6G77HUHZHMW5E/graph.json","fetch_events":"https://pith.science/api/pith-number/3HGPULRI2KMWO6G77HUHZHMW5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HGPULRI2KMWO6G77HUHZHMW5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HGPULRI2KMWO6G77HUHZHMW5E/action/storage_attestation","attest_author":"https://pith.science/pith/3HGPULRI2KMWO6G77HUHZHMW5E/action/author_attestation","sign_citation":"https://pith.science/pith/3HGPULRI2KMWO6G77HUHZHMW5E/action/citation_signature","submit_replication":"https://pith.science/pith/3HGPULRI2KMWO6G77HUHZHMW5E/action/replication_record"}},"created_at":"2026-05-20T00:02:04.099687+00:00","updated_at":"2026-05-20T00:02:04.099687+00:00"}