{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MK66URCID7NDH42NA2ZXCOUHQM","short_pith_number":"pith:MK66URCI","canonical_record":{"source":{"id":"1804.03782","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T02:10:55Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"93844cfcfa86e33aac84134876048b0e9e893c64a5104499548ac60edfcb124a","abstract_canon_sha256":"2fab9154a1ab4a599c7e49eb59a2f2f4bbeb485b7999e7a31bcc218926c7b8b1"},"schema_version":"1.0"},"canonical_sha256":"62bdea44481fda33f34d06b3713a87831a19dff2a64e9a6384415eca8186073f","source":{"kind":"arxiv","id":"1804.03782","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.03782","created_at":"2026-05-17T23:46:30Z"},{"alias_kind":"arxiv_version","alias_value":"1804.03782v3","created_at":"2026-05-17T23:46:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.03782","created_at":"2026-05-17T23:46:30Z"},{"alias_kind":"pith_short_12","alias_value":"MK66URCID7ND","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MK66URCID7NDH42N","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MK66URCI","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MK66URCID7NDH42NA2ZXCOUHQM","target":"record","payload":{"canonical_record":{"source":{"id":"1804.03782","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T02:10:55Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"93844cfcfa86e33aac84134876048b0e9e893c64a5104499548ac60edfcb124a","abstract_canon_sha256":"2fab9154a1ab4a599c7e49eb59a2f2f4bbeb485b7999e7a31bcc218926c7b8b1"},"schema_version":"1.0"},"canonical_sha256":"62bdea44481fda33f34d06b3713a87831a19dff2a64e9a6384415eca8186073f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:30.683246Z","signature_b64":"//ScaxGWUlltdEhvn6rk0z7opgo21aD5dd2LraXlydCElglcQcAkIVkLvee8qTWDn18woC00hU6hBDmvdAfqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62bdea44481fda33f34d06b3713a87831a19dff2a64e9a6384415eca8186073f","last_reissued_at":"2026-05-17T23:46:30.682377Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:30.682377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.03782","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/fz6lF1dkmMPwQGyKbOTkbBBayIBcvy7PVHP3Uf/XZ51iZZ4/MpGH7j+qk5Zf+YOyYdqriPyUPsvXeCgaElYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:42:13.940011Z"},"content_sha256":"fd4068005882dc2cf539efca9d50c4f8240b75427c5a38d8130501693fafb96d","schema_version":"1.0","event_id":"sha256:fd4068005882dc2cf539efca9d50c4f8240b75427c5a38d8130501693fafb96d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MK66URCID7NDH42NA2ZXCOUHQM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoT: Cooperative Training for Generative Modeling of Discrete Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lantao Yu, Sidi Lu, Siyuan Feng, Weinan Zhang, Yaoming Zhu, Yong Yu","submitted_at":"2018-04-11T02:10:55Z","abstract_excerpt":"In this paper, we study the generative models of sequential discrete data. To tackle the exposure bias problem inherent in maximum likelihood estimation (MLE), generative adversarial networks (GANs) are introduced to penalize the unrealistic generated samples. To exploit the supervision signal from the discriminator, most previous models leverage REINFORCE to address the non-differentiable problem of sequential discrete data. However, because of the unstable property of the training signal during the dynamic process of adversarial training, the effectiveness of REINFORCE, in this case, is hard"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.03782","kind":"arxiv","version":3},"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":"2026-05-17T23:46:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fuNSnz/vN9eZfeNFeWVvwiMTxSxIRJFlcivhJa+fyhIOrQC8pTvsidgl12fgZxl/IvXSWYYl9Q+9nJeDKiJhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:42:13.940724Z"},"content_sha256":"e9da68e06dd23aed037d9a87eba9c2092dd459e3bff04829da3c7c57875e9c71","schema_version":"1.0","event_id":"sha256:e9da68e06dd23aed037d9a87eba9c2092dd459e3bff04829da3c7c57875e9c71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MK66URCID7NDH42NA2ZXCOUHQM/bundle.json","state_url":"https://pith.science/pith/MK66URCID7NDH42NA2ZXCOUHQM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MK66URCID7NDH42NA2ZXCOUHQM/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":"2026-05-26T01:42:13Z","links":{"resolver":"https://pith.science/pith/MK66URCID7NDH42NA2ZXCOUHQM","bundle":"https://pith.science/pith/MK66URCID7NDH42NA2ZXCOUHQM/bundle.json","state":"https://pith.science/pith/MK66URCID7NDH42NA2ZXCOUHQM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MK66URCID7NDH42NA2ZXCOUHQM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MK66URCID7NDH42NA2ZXCOUHQM","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":"2fab9154a1ab4a599c7e49eb59a2f2f4bbeb485b7999e7a31bcc218926c7b8b1","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T02:10:55Z","title_canon_sha256":"93844cfcfa86e33aac84134876048b0e9e893c64a5104499548ac60edfcb124a"},"schema_version":"1.0","source":{"id":"1804.03782","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.03782","created_at":"2026-05-17T23:46:30Z"},{"alias_kind":"arxiv_version","alias_value":"1804.03782v3","created_at":"2026-05-17T23:46:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.03782","created_at":"2026-05-17T23:46:30Z"},{"alias_kind":"pith_short_12","alias_value":"MK66URCID7ND","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MK66URCID7NDH42N","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MK66URCI","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:e9da68e06dd23aed037d9a87eba9c2092dd459e3bff04829da3c7c57875e9c71","target":"graph","created_at":"2026-05-17T23:46:30Z","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":"In this paper, we study the generative models of sequential discrete data. To tackle the exposure bias problem inherent in maximum likelihood estimation (MLE), generative adversarial networks (GANs) are introduced to penalize the unrealistic generated samples. To exploit the supervision signal from the discriminator, most previous models leverage REINFORCE to address the non-differentiable problem of sequential discrete data. However, because of the unstable property of the training signal during the dynamic process of adversarial training, the effectiveness of REINFORCE, in this case, is hard","authors_text":"Lantao Yu, Sidi Lu, Siyuan Feng, Weinan Zhang, Yaoming Zhu, Yong Yu","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T02:10:55Z","title":"CoT: Cooperative Training for Generative Modeling of Discrete Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.03782","kind":"arxiv","version":3},"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:fd4068005882dc2cf539efca9d50c4f8240b75427c5a38d8130501693fafb96d","target":"record","created_at":"2026-05-17T23:46:30Z","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":"2fab9154a1ab4a599c7e49eb59a2f2f4bbeb485b7999e7a31bcc218926c7b8b1","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T02:10:55Z","title_canon_sha256":"93844cfcfa86e33aac84134876048b0e9e893c64a5104499548ac60edfcb124a"},"schema_version":"1.0","source":{"id":"1804.03782","kind":"arxiv","version":3}},"canonical_sha256":"62bdea44481fda33f34d06b3713a87831a19dff2a64e9a6384415eca8186073f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62bdea44481fda33f34d06b3713a87831a19dff2a64e9a6384415eca8186073f","first_computed_at":"2026-05-17T23:46:30.682377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:30.682377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"//ScaxGWUlltdEhvn6rk0z7opgo21aD5dd2LraXlydCElglcQcAkIVkLvee8qTWDn18woC00hU6hBDmvdAfqCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:30.683246Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.03782","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd4068005882dc2cf539efca9d50c4f8240b75427c5a38d8130501693fafb96d","sha256:e9da68e06dd23aed037d9a87eba9c2092dd459e3bff04829da3c7c57875e9c71"],"state_sha256":"6be667c9f650018d2bea171f8cf4ac9f2f21873e91a0c6386c116af576d07636"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6dVQTQ6u13/RLEIIYxfGuhEegfauLTof5wzMYxYVv1k+0PXjFpKYVGZduwUViq26uFwCETLuu8Kqafe9NVjoBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T01:42:13.944411Z","bundle_sha256":"f81c5f23bb01069144aa227e15adfbc8e44a6f9b6bbe83ebe3d798f09593683b"}}