{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WMFXDLCFVSB2K2XBDJUZ5ZOSUO","short_pith_number":"pith:WMFXDLCF","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"},"canonical_sha256":"b30b71ac45ac83a56ae11a699ee5d2a38fac6268a9f18faf1af926526f4ea3f1","source":{"kind":"arxiv","id":"1805.07010","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07010","created_at":"2026-05-18T00:15:41Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07010v1","created_at":"2026-05-18T00:15:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07010","created_at":"2026-05-18T00:15:41Z"},{"alias_kind":"pith_short_12","alias_value":"WMFXDLCFVSB2","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WMFXDLCFVSB2K2XB","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WMFXDLCF","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WMFXDLCFVSB2K2XBDJUZ5ZOSUO","target":"record","payload":{"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"},"canonical_sha256":"b30b71ac45ac83a56ae11a699ee5d2a38fac6268a9f18faf1af926526f4ea3f1","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"},"source_kind":"arxiv","source_id":"1805.07010","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Yn7RhP4RvGDiQ2K7OPfoWQwFT07lMUZVCBimi38CBzkWDnNxoLhOLlFuw2BMheQiA/W5maPyD/aZERBYbxTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T15:49:23.585620Z"},"content_sha256":"d11abc8af963c306647b3c4d8af929f39edc888e5a9f46d694cd39fe9132d242","schema_version":"1.0","event_id":"sha256:d11abc8af963c306647b3c4d8af929f39edc888e5a9f46d694cd39fe9132d242"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WMFXDLCFVSB2K2XBDJUZ5ZOSUO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Czpq9ds31DFpoCNujmjW4P+7c8fhVdd3VQP7NKlukflKmD6qiQ4Jij1D+JvGs3tiFnjt5XrtafxtXU7uuIuIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T15:49:23.586284Z"},"content_sha256":"386ba1ba66293b243540936cccd2fc80456d77704f9e50dd24d810653e664dc6","schema_version":"1.0","event_id":"sha256:386ba1ba66293b243540936cccd2fc80456d77704f9e50dd24d810653e664dc6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/bundle.json","state_url":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-24T15:49:23Z","links":{"resolver":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO","bundle":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/bundle.json","state":"https://pith.science/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WMFXDLCFVSB2K2XBDJUZ5ZOSUO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WMFXDLCFVSB2K2XBDJUZ5ZOSUO","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":"b154c71e39f3e3fa7f0a839669339312d14c1c971bff05fab91e09a0b7066283","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-18T01:10:09Z","title_canon_sha256":"f4429516583b2fc2b8a69906fffd15e4f3727470a8cbc10d34e94fdf8c71e9ea"},"schema_version":"1.0","source":{"id":"1805.07010","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07010","created_at":"2026-05-18T00:15:41Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07010v1","created_at":"2026-05-18T00:15:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07010","created_at":"2026-05-18T00:15:41Z"},{"alias_kind":"pith_short_12","alias_value":"WMFXDLCFVSB2","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WMFXDLCFVSB2K2XB","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WMFXDLCF","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:386ba1ba66293b243540936cccd2fc80456d77704f9e50dd24d810653e664dc6","target":"graph","created_at":"2026-05-18T00:15:41Z","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"},"paper":{"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","authors_text":"Patrick Emami, Sanjay Ranka","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-18T01:10:09Z","title":"Learning Permutations with Sinkhorn Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07010","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:d11abc8af963c306647b3c4d8af929f39edc888e5a9f46d694cd39fe9132d242","target":"record","created_at":"2026-05-18T00:15:41Z","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":"b154c71e39f3e3fa7f0a839669339312d14c1c971bff05fab91e09a0b7066283","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-18T01:10:09Z","title_canon_sha256":"f4429516583b2fc2b8a69906fffd15e4f3727470a8cbc10d34e94fdf8c71e9ea"},"schema_version":"1.0","source":{"id":"1805.07010","kind":"arxiv","version":1}},"canonical_sha256":"b30b71ac45ac83a56ae11a699ee5d2a38fac6268a9f18faf1af926526f4ea3f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b30b71ac45ac83a56ae11a699ee5d2a38fac6268a9f18faf1af926526f4ea3f1","first_computed_at":"2026-05-18T00:15:41.360223Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:41.360223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SXz1IfY70erWej6EsGn3gowI/GNSDYwCAt3Js8JNZecw1J5Tj7rlaKuKlbvt0iRoFmvVGFSAyo4D+JtymUa+CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:41.360790Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07010","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d11abc8af963c306647b3c4d8af929f39edc888e5a9f46d694cd39fe9132d242","sha256:386ba1ba66293b243540936cccd2fc80456d77704f9e50dd24d810653e664dc6"],"state_sha256":"f6877ca6a788f01ed54a5caaa935f774bfb85e373108ddf25ba7ce322873867e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OW8MCG0RTEiasvMr6Lg/gfVZAAq7CUcn9TuL8/nVV5cUGnBGdZ29hzmnOtOjMtb07h3epThCsC6ip0wfMi3wAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T15:49:23.589224Z","bundle_sha256":"af16074c387404dfb62672a6bd76c0f8dd62db56cdefccb1129554d5079951ea"}}