{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WMFXDLCFVSB2K2XBDJUZ5ZOSUO","short_pith_number":"pith:WMFXDLCF","schema_version":"1.0","canonical_sha256":"b30b71ac45ac83a56ae11a699ee5d2a38fac6268a9f18faf1af926526f4ea3f1","source":{"kind":"arxiv","id":"1805.07010","version":1},"attestation_state":"computed","paper":{"title":"Learning Permutations with Sinkhorn Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Patrick Emami, Sanjay Ranka","submitted_at":"2018-05-18T01:10:09Z","abstract_excerpt":"Many problems at the intersection of combinatorics and computer science require solving for a permutation that optimally matches, ranks, or sorts some data. These problems usually have a task-specific, often non-differentiable objective function that data-driven algorithms can use as a learning signal. In this paper, we propose the Sinkhorn Policy Gradient (SPG) algorithm for learning policies on permutation matrices. The actor-critic neural network architecture we introduce for SPG uniquely decouples representation learning of the state space from the highly-structured action space of permuta"},"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":"1805.07010","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-18T01:10:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f4429516583b2fc2b8a69906fffd15e4f3727470a8cbc10d34e94fdf8c71e9ea","abstract_canon_sha256":"b154c71e39f3e3fa7f0a839669339312d14c1c971bff05fab91e09a0b7066283"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:41.360790Z","signature_b64":"SXz1IfY70erWej6EsGn3gowI/GNSDYwCAt3Js8JNZecw1J5Tj7rlaKuKlbvt0iRoFmvVGFSAyo4D+JtymUa+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b30b71ac45ac83a56ae11a699ee5d2a38fac6268a9f18faf1af926526f4ea3f1","last_reissued_at":"2026-05-18T00:15:41.360223Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:41.360223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Permutations with Sinkhorn Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Patrick Emami, Sanjay Ranka","submitted_at":"2018-05-18T01:10:09Z","abstract_excerpt":"Many problems at the intersection of combinatorics and computer science require solving for a permutation that optimally matches, ranks, or sorts some data. These problems usually have a task-specific, often non-differentiable objective function that data-driven algorithms can use as a learning signal. In this paper, we propose the Sinkhorn Policy Gradient (SPG) algorithm for learning policies on permutation matrices. The actor-critic neural network architecture we introduce for SPG uniquely decouples representation learning of the state space from the highly-structured action space of permuta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07010","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1805.07010","created_at":"2026-05-18T00:15:41.360336+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.07010v1","created_at":"2026-05-18T00:15:41.360336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07010","created_at":"2026-05-18T00:15:41.360336+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMFXDLCFVSB2","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMFXDLCFVSB2K2XB","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMFXDLCF","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16755","citing_title":"Learning Unbiased Permutations via Flow Matching","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08758","citing_title":"Omni-scale Learning-based Sequential Decision Framework for Order Fulfillment of Tote-handling Robotic Systems","ref_index":97,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO","json":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO.json","graph_json":"https://pith.science/api/pith-number/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/graph.json","events_json":"https://pith.science/api/pith-number/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/events.json","paper":"https://pith.science/paper/WMFXDLCF"},"agent_actions":{"view_html":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO","download_json":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO.json","view_paper":"https://pith.science/paper/WMFXDLCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.07010&json=true","fetch_graph":"https://pith.science/api/pith-number/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/graph.json","fetch_events":"https://pith.science/api/pith-number/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/action/storage_attestation","attest_author":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/action/author_attestation","sign_citation":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/action/citation_signature","submit_replication":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/action/replication_record"}},"created_at":"2026-05-18T00:15:41.360336+00:00","updated_at":"2026-05-18T00:15:41.360336+00:00"}