{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DV2QDU4HQIZO3UTTGIIOTT6VK2","short_pith_number":"pith:DV2QDU4H","schema_version":"1.0","canonical_sha256":"1d7501d3878232edd2733210e9cfd556b337028a1294d66b582e4bad28842d9b","source":{"kind":"arxiv","id":"2601.22211","version":2},"attestation_state":"computed","paper":{"title":"Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akseli Kangaslahti, Anagha Satish, Andrew Ma, Hezi Jiang, Lily Xu, Lingkai Kong, Milind Tambe, Mingxiao Song, Wenbo Chen","submitted_at":"2026-01-29T18:49:07Z","abstract_excerpt":"Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical. Existing approaches embed task-specific value functions into constrained optimization programs or learn deterministic structured policies, sacrificing generality and policy expressiveness. We propose a solver-induced \\emph{latent spherical flow policy} that brings the expressiveness of modern generative policies to combinatorial RL while guaranteeing feasibility b"},"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":"2601.22211","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T18:49:07Z","cross_cats_sorted":[],"title_canon_sha256":"5d2860218ffaf9c3189bf188f089b41a649624f311bc03155bc64486c28b1102","abstract_canon_sha256":"a87338b2b5423a028233c915b241615641fd37168d980b233bc52953abd18d9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:13.491326Z","signature_b64":"95prlTCH80HroSR9ga6Oc9ZUfev2+QA9Chw3+IVEmZRxcM0y/9NGkijLX8fIT8SNtNhGnjiARu3eqGQolQJQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d7501d3878232edd2733210e9cfd556b337028a1294d66b582e4bad28842d9b","last_reissued_at":"2026-06-09T01:05:13.490775Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:13.490775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akseli Kangaslahti, Anagha Satish, Andrew Ma, Hezi Jiang, Lily Xu, Lingkai Kong, Milind Tambe, Mingxiao Song, Wenbo Chen","submitted_at":"2026-01-29T18:49:07Z","abstract_excerpt":"Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical. Existing approaches embed task-specific value functions into constrained optimization programs or learn deterministic structured policies, sacrificing generality and policy expressiveness. We propose a solver-induced \\emph{latent spherical flow policy} that brings the expressiveness of modern generative policies to combinatorial RL while guaranteeing feasibility b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22211","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/2601.22211/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":"2601.22211","created_at":"2026-06-09T01:05:13.490841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.22211v2","created_at":"2026-06-09T01:05:13.490841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22211","created_at":"2026-06-09T01:05:13.490841+00:00"},{"alias_kind":"pith_short_12","alias_value":"DV2QDU4HQIZO","created_at":"2026-06-09T01:05:13.490841+00:00"},{"alias_kind":"pith_short_16","alias_value":"DV2QDU4HQIZO3UTT","created_at":"2026-06-09T01:05:13.490841+00:00"},{"alias_kind":"pith_short_8","alias_value":"DV2QDU4H","created_at":"2026-06-09T01:05:13.490841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DV2QDU4HQIZO3UTTGIIOTT6VK2","json":"https://pith.science/pith/DV2QDU4HQIZO3UTTGIIOTT6VK2.json","graph_json":"https://pith.science/api/pith-number/DV2QDU4HQIZO3UTTGIIOTT6VK2/graph.json","events_json":"https://pith.science/api/pith-number/DV2QDU4HQIZO3UTTGIIOTT6VK2/events.json","paper":"https://pith.science/paper/DV2QDU4H"},"agent_actions":{"view_html":"https://pith.science/pith/DV2QDU4HQIZO3UTTGIIOTT6VK2","download_json":"https://pith.science/pith/DV2QDU4HQIZO3UTTGIIOTT6VK2.json","view_paper":"https://pith.science/paper/DV2QDU4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.22211&json=true","fetch_graph":"https://pith.science/api/pith-number/DV2QDU4HQIZO3UTTGIIOTT6VK2/graph.json","fetch_events":"https://pith.science/api/pith-number/DV2QDU4HQIZO3UTTGIIOTT6VK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DV2QDU4HQIZO3UTTGIIOTT6VK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DV2QDU4HQIZO3UTTGIIOTT6VK2/action/storage_attestation","attest_author":"https://pith.science/pith/DV2QDU4HQIZO3UTTGIIOTT6VK2/action/author_attestation","sign_citation":"https://pith.science/pith/DV2QDU4HQIZO3UTTGIIOTT6VK2/action/citation_signature","submit_replication":"https://pith.science/pith/DV2QDU4HQIZO3UTTGIIOTT6VK2/action/replication_record"}},"created_at":"2026-06-09T01:05:13.490841+00:00","updated_at":"2026-06-09T01:05:13.490841+00:00"}