{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RP3H3TNGEZXOGKNCBSE4I7Z6MK","short_pith_number":"pith:RP3H3TNG","canonical_record":{"source":{"id":"1807.01202","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-03T14:26:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a731904e854176b44090889aaece31f86941a6f9d8c90edb196f4ba44d97753b","abstract_canon_sha256":"75a2615df36c5dff53b7aa2f3a2c35db8ef5dc5799da613a3f9a4805f7dbc838"},"schema_version":"1.0"},"canonical_sha256":"8bf67dcda6266ee329a20c89c47f3e629b7cf4b366ba56dafcef7e66dad107be","source":{"kind":"arxiv","id":"1807.01202","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01202","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01202v2","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01202","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"RP3H3TNGEZXO","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RP3H3TNGEZXOGKNC","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RP3H3TNG","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RP3H3TNGEZXOGKNCBSE4I7Z6MK","target":"record","payload":{"canonical_record":{"source":{"id":"1807.01202","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-03T14:26:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a731904e854176b44090889aaece31f86941a6f9d8c90edb196f4ba44d97753b","abstract_canon_sha256":"75a2615df36c5dff53b7aa2f3a2c35db8ef5dc5799da613a3f9a4805f7dbc838"},"schema_version":"1.0"},"canonical_sha256":"8bf67dcda6266ee329a20c89c47f3e629b7cf4b366ba56dafcef7e66dad107be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:29.905432Z","signature_b64":"/xsyhZ76/XB6JpENLeA8yAK4TU/r/Zi+rK6i64FgU5o4uPGFP42BAbuDiXOewWMHThAjpxpWIvILJpwgZ7MEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bf67dcda6266ee329a20c89c47f3e629b7cf4b366ba56dafcef7e66dad107be","last_reissued_at":"2026-05-18T00:11:29.905000Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:29.905000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.01202","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5TQwTcT6HOcBqbCMWc2MANpNlQQnUAujAVh1zpT+6lIRQTXF/xGs3bzg8lRl39I5mblIGOedBqH+0gFOmqECCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T19:12:23.628413Z"},"content_sha256":"d1ea62358d31d5126391928fac798c9a9b27436b741cc2656e7c0b0d07ba8c86","schema_version":"1.0","event_id":"sha256:d1ea62358d31d5126391928fac798c9a9b27436b741cc2656e7c0b0d07ba8c86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RP3H3TNGEZXOGKNCBSE4I7Z6MK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generating Multi-Categorical Samples with Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christian Hammerschmidt, Radu State, Ramiro Camino","submitted_at":"2018-07-03T14:26:57Z","abstract_excerpt":"We propose a method to train generative adversarial networks on mutivariate feature vectors representing multiple categorical values. In contrast to the continuous domain, where GAN-based methods have delivered considerable results, GANs struggle to perform equally well on discrete data. We propose and compare several architectures based on multiple (Gumbel) softmax output layers taking into account the structure of the data. We evaluate the performance of our architecture on datasets with different sparsity, number of features, ranges of categorical values, and dependencies among the features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01202","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":""},"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":"2026-05-18T00:11:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U3MQ01eKBy5w25t6HEDBihT4WsAMmHmMsolGzS1sS79VeeTVmJrLFLEs7wo/95uG6nEtzjzAOFe8a+bjzY3UBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T19:12:23.628767Z"},"content_sha256":"af2535696df394dec93f6fef8175b80d2e4d7bf4841ecc19ce7b5418da52b845","schema_version":"1.0","event_id":"sha256:af2535696df394dec93f6fef8175b80d2e4d7bf4841ecc19ce7b5418da52b845"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RP3H3TNGEZXOGKNCBSE4I7Z6MK/bundle.json","state_url":"https://pith.science/pith/RP3H3TNGEZXOGKNCBSE4I7Z6MK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RP3H3TNGEZXOGKNCBSE4I7Z6MK/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":"2026-06-01T19:12:23Z","links":{"resolver":"https://pith.science/pith/RP3H3TNGEZXOGKNCBSE4I7Z6MK","bundle":"https://pith.science/pith/RP3H3TNGEZXOGKNCBSE4I7Z6MK/bundle.json","state":"https://pith.science/pith/RP3H3TNGEZXOGKNCBSE4I7Z6MK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RP3H3TNGEZXOGKNCBSE4I7Z6MK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RP3H3TNGEZXOGKNCBSE4I7Z6MK","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":"75a2615df36c5dff53b7aa2f3a2c35db8ef5dc5799da613a3f9a4805f7dbc838","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-03T14:26:57Z","title_canon_sha256":"a731904e854176b44090889aaece31f86941a6f9d8c90edb196f4ba44d97753b"},"schema_version":"1.0","source":{"id":"1807.01202","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01202","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01202v2","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01202","created_at":"2026-05-18T00:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"RP3H3TNGEZXO","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RP3H3TNGEZXOGKNC","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RP3H3TNG","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:af2535696df394dec93f6fef8175b80d2e4d7bf4841ecc19ce7b5418da52b845","target":"graph","created_at":"2026-05-18T00:11:29Z","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":"We propose a method to train generative adversarial networks on mutivariate feature vectors representing multiple categorical values. In contrast to the continuous domain, where GAN-based methods have delivered considerable results, GANs struggle to perform equally well on discrete data. We propose and compare several architectures based on multiple (Gumbel) softmax output layers taking into account the structure of the data. We evaluate the performance of our architecture on datasets with different sparsity, number of features, ranges of categorical values, and dependencies among the features","authors_text":"Christian Hammerschmidt, Radu State, Ramiro Camino","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-03T14:26:57Z","title":"Generating Multi-Categorical Samples with Generative Adversarial Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01202","kind":"arxiv","version":2},"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:d1ea62358d31d5126391928fac798c9a9b27436b741cc2656e7c0b0d07ba8c86","target":"record","created_at":"2026-05-18T00:11:29Z","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":"75a2615df36c5dff53b7aa2f3a2c35db8ef5dc5799da613a3f9a4805f7dbc838","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-03T14:26:57Z","title_canon_sha256":"a731904e854176b44090889aaece31f86941a6f9d8c90edb196f4ba44d97753b"},"schema_version":"1.0","source":{"id":"1807.01202","kind":"arxiv","version":2}},"canonical_sha256":"8bf67dcda6266ee329a20c89c47f3e629b7cf4b366ba56dafcef7e66dad107be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bf67dcda6266ee329a20c89c47f3e629b7cf4b366ba56dafcef7e66dad107be","first_computed_at":"2026-05-18T00:11:29.905000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:29.905000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/xsyhZ76/XB6JpENLeA8yAK4TU/r/Zi+rK6i64FgU5o4uPGFP42BAbuDiXOewWMHThAjpxpWIvILJpwgZ7MEDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:29.905432Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01202","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1ea62358d31d5126391928fac798c9a9b27436b741cc2656e7c0b0d07ba8c86","sha256:af2535696df394dec93f6fef8175b80d2e4d7bf4841ecc19ce7b5418da52b845"],"state_sha256":"72dd14e5619295b910028dd36826ee69406d9f2cf86f06498ee520a23b04c3d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/EGfOFqrVAr67i42J5RPSDAHSG/KvkY1YqteB9Dxf3afrcS5L9LHPSbSv3HTFW9eg2dZo8O9zASCwv6uV8uuBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T19:12:23.630784Z","bundle_sha256":"34e6366d87beeb8e8e4f43c3eb1d0566a9dd7b7240edfb027cfabc2e4b41234c"}}