{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:AEWCO2USUWXKXSVE4737AKBTIU","short_pith_number":"pith:AEWCO2US","canonical_record":{"source":{"id":"1802.08665","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-23T18:15:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6e9cca946ef7f5e12c2b9a26b11fb15793f0f13d609ba4ea8b8c081aae5f1d7d","abstract_canon_sha256":"067553fe3ba1ab9ddbacb411890079cd97fda7f2283a6120594e2e12a9d16211"},"schema_version":"1.0"},"canonical_sha256":"012c276a92a5aeabcaa4e7f7f0283345270d3e66089159839be8bd6299689328","source":{"kind":"arxiv","id":"1802.08665","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.08665","created_at":"2026-05-18T00:22:40Z"},{"alias_kind":"arxiv_version","alias_value":"1802.08665v1","created_at":"2026-05-18T00:22:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08665","created_at":"2026-05-18T00:22:40Z"},{"alias_kind":"pith_short_12","alias_value":"AEWCO2USUWXK","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AEWCO2USUWXKXSVE","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AEWCO2US","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:AEWCO2USUWXKXSVE4737AKBTIU","target":"record","payload":{"canonical_record":{"source":{"id":"1802.08665","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-23T18:15:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6e9cca946ef7f5e12c2b9a26b11fb15793f0f13d609ba4ea8b8c081aae5f1d7d","abstract_canon_sha256":"067553fe3ba1ab9ddbacb411890079cd97fda7f2283a6120594e2e12a9d16211"},"schema_version":"1.0"},"canonical_sha256":"012c276a92a5aeabcaa4e7f7f0283345270d3e66089159839be8bd6299689328","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:40.855637Z","signature_b64":"qtYU1KEB4hUWiKT82ExU+ceYdftPz2ybrSiwDPyzCi8uIxVuJ+qFPEpZ7+pap1fhRwFoZESh6Rkm48NgOzvzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"012c276a92a5aeabcaa4e7f7f0283345270d3e66089159839be8bd6299689328","last_reissued_at":"2026-05-18T00:22:40.854911Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:40.854911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.08665","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":"2026-05-18T00:22:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sEfsGStZS8BODItkNRDOn4suIRTzKNTIfDnvoeDzPjV4aw9rd7x/Vz7/DwgSNhAUEqfOcSpHSZDyAjoJzRwjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:30:02.794218Z"},"content_sha256":"72828304c310fbe2d17066c3f788de5f85971a74435faed12fda5c1d520b2405","schema_version":"1.0","event_id":"sha256:72828304c310fbe2d17066c3f788de5f85971a74435faed12fda5c1d520b2405"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:AEWCO2USUWXKXSVE4737AKBTIU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Latent Permutations with Gumbel-Sinkhorn Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"David Belanger, Gonzalo Mena, Jasper Snoek, Scott Linderman","submitted_at":"2018-02-23T18:15:13Z","abstract_excerpt":"Permutations and matchings are core building blocks in a variety of latent variable models, as they allow us to align, canonicalize, and sort data. Learning in such models is difficult, however, because exact marginalization over these combinatorial objects is intractable. In response, this paper introduces a collection of new methods for end-to-end learning in such models that approximate discrete maximum-weight matching using the continuous Sinkhorn operator. Sinkhorn iteration is attractive because it functions as a simple, easy-to-implement analog of the softmax operator. With this, we can"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08665","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":"2026-05-18T00:22:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KLkZqIt3tuttW5QAg58Abx7haqZ738O0HoRnDqHqDKoiCkB3n6ShdGPWRZ+C7xad8zTtGYoAlZGwo4PWgV/cCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T18:30:02.794902Z"},"content_sha256":"f24cb394eb98658479f7d48925ec1c469e12d1c9c6c453e7c4bb561e76669d82","schema_version":"1.0","event_id":"sha256:f24cb394eb98658479f7d48925ec1c469e12d1c9c6c453e7c4bb561e76669d82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AEWCO2USUWXKXSVE4737AKBTIU/bundle.json","state_url":"https://pith.science/pith/AEWCO2USUWXKXSVE4737AKBTIU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AEWCO2USUWXKXSVE4737AKBTIU/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":"2026-05-30T18:30:02Z","links":{"resolver":"https://pith.science/pith/AEWCO2USUWXKXSVE4737AKBTIU","bundle":"https://pith.science/pith/AEWCO2USUWXKXSVE4737AKBTIU/bundle.json","state":"https://pith.science/pith/AEWCO2USUWXKXSVE4737AKBTIU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AEWCO2USUWXKXSVE4737AKBTIU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:AEWCO2USUWXKXSVE4737AKBTIU","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":"067553fe3ba1ab9ddbacb411890079cd97fda7f2283a6120594e2e12a9d16211","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-23T18:15:13Z","title_canon_sha256":"6e9cca946ef7f5e12c2b9a26b11fb15793f0f13d609ba4ea8b8c081aae5f1d7d"},"schema_version":"1.0","source":{"id":"1802.08665","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.08665","created_at":"2026-05-18T00:22:40Z"},{"alias_kind":"arxiv_version","alias_value":"1802.08665v1","created_at":"2026-05-18T00:22:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08665","created_at":"2026-05-18T00:22:40Z"},{"alias_kind":"pith_short_12","alias_value":"AEWCO2USUWXK","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AEWCO2USUWXKXSVE","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AEWCO2US","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:f24cb394eb98658479f7d48925ec1c469e12d1c9c6c453e7c4bb561e76669d82","target":"graph","created_at":"2026-05-18T00:22:40Z","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":"Permutations and matchings are core building blocks in a variety of latent variable models, as they allow us to align, canonicalize, and sort data. Learning in such models is difficult, however, because exact marginalization over these combinatorial objects is intractable. In response, this paper introduces a collection of new methods for end-to-end learning in such models that approximate discrete maximum-weight matching using the continuous Sinkhorn operator. Sinkhorn iteration is attractive because it functions as a simple, easy-to-implement analog of the softmax operator. With this, we can","authors_text":"David Belanger, Gonzalo Mena, Jasper Snoek, Scott Linderman","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-23T18:15:13Z","title":"Learning Latent Permutations with Gumbel-Sinkhorn Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08665","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":"sha256:72828304c310fbe2d17066c3f788de5f85971a74435faed12fda5c1d520b2405","target":"record","created_at":"2026-05-18T00:22:40Z","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":"067553fe3ba1ab9ddbacb411890079cd97fda7f2283a6120594e2e12a9d16211","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-23T18:15:13Z","title_canon_sha256":"6e9cca946ef7f5e12c2b9a26b11fb15793f0f13d609ba4ea8b8c081aae5f1d7d"},"schema_version":"1.0","source":{"id":"1802.08665","kind":"arxiv","version":1}},"canonical_sha256":"012c276a92a5aeabcaa4e7f7f0283345270d3e66089159839be8bd6299689328","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"012c276a92a5aeabcaa4e7f7f0283345270d3e66089159839be8bd6299689328","first_computed_at":"2026-05-18T00:22:40.854911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:40.854911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qtYU1KEB4hUWiKT82ExU+ceYdftPz2ybrSiwDPyzCi8uIxVuJ+qFPEpZ7+pap1fhRwFoZESh6Rkm48NgOzvzCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:40.855637Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.08665","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72828304c310fbe2d17066c3f788de5f85971a74435faed12fda5c1d520b2405","sha256:f24cb394eb98658479f7d48925ec1c469e12d1c9c6c453e7c4bb561e76669d82"],"state_sha256":"9937b142139634948532b5031759d7b38df365cc95cbd65278deb6141a3354d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDv4RAJGxHbjV0MKbajvQmx5tdJLGOUhNPOwIM23NVSIFTTHrxdQdlCAGVKK+jXIYd+DpZP4gSy5BGp1RV7dAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T18:30:02.800280Z","bundle_sha256":"220c23c8dedf4fd4fd6c9d75752423cc776df45661269a71d3d3872066b073a6"}}