{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:D4B76VN5RW2SVWT6BIUI4I7JNU","short_pith_number":"pith:D4B76VN5","canonical_record":{"source":{"id":"1412.6515","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-19T20:28:41Z","cross_cats_sorted":[],"title_canon_sha256":"c1a065cabf6637a2e9e9cc1065d350586afa54ff5e843954a4f5dc7bfeaa5f91","abstract_canon_sha256":"5d2d552dfe05ab6136b0a685f749e1e1904de3b4ef8830c28de4fb460f147399"},"schema_version":"1.0"},"canonical_sha256":"1f03ff55bd8db52ada7e0a288e23e96d2c22dfae91b91d63da401abfc5f50dc5","source":{"kind":"arxiv","id":"1412.6515","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6515","created_at":"2026-05-18T02:03:55Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6515v4","created_at":"2026-05-18T02:03:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6515","created_at":"2026-05-18T02:03:55Z"},{"alias_kind":"pith_short_12","alias_value":"D4B76VN5RW2S","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"D4B76VN5RW2SVWT6","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"D4B76VN5","created_at":"2026-05-18T12:28:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:D4B76VN5RW2SVWT6BIUI4I7JNU","target":"record","payload":{"canonical_record":{"source":{"id":"1412.6515","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-19T20:28:41Z","cross_cats_sorted":[],"title_canon_sha256":"c1a065cabf6637a2e9e9cc1065d350586afa54ff5e843954a4f5dc7bfeaa5f91","abstract_canon_sha256":"5d2d552dfe05ab6136b0a685f749e1e1904de3b4ef8830c28de4fb460f147399"},"schema_version":"1.0"},"canonical_sha256":"1f03ff55bd8db52ada7e0a288e23e96d2c22dfae91b91d63da401abfc5f50dc5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:03:55.075911Z","signature_b64":"m2Vm8CH6OGg7qaqZRWF042z7GfSwCBNzGO059nV4cDe4norL8mhOCyCR0edZ4N3ztXg474Qm4yKeQg6MkTOiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f03ff55bd8db52ada7e0a288e23e96d2c22dfae91b91d63da401abfc5f50dc5","last_reissued_at":"2026-05-18T02:03:55.075090Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:03:55.075090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.6515","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:03:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p13zjoN1v/XBm9w/Ehn6AseBt+8K6j9sXSRUJQVT2+8YBRa1om1E9yPubSFUaN622XPqLxkEx/1GEkR4B7LYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:03:59.531703Z"},"content_sha256":"aac7c7c2a1c9760e1fef89038c54c679d1585eda4bca1b96e9474801e621fee1","schema_version":"1.0","event_id":"sha256:aac7c7c2a1c9760e1fef89038c54c679d1585eda4bca1b96e9474801e621fee1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:D4B76VN5RW2SVWT6BIUI4I7JNU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On distinguishability criteria for estimating generative models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Ian J. Goodfellow","submitted_at":"2014-12-19T20:28:41Z","abstract_excerpt":"Two recently introduced criteria for estimation of generative models are both based on a reduction to binary classification. Noise-contrastive estimation (NCE) is an estimation procedure in which a generative model is trained to be able to distinguish data samples from noise samples. Generative adversarial networks (GANs) are pairs of generator and discriminator networks, with the generator network learning to generate samples by attempting to fool the discriminator network into believing its samples are real data. Both estimation procedures use the same function to drive learning, which natur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6515","kind":"arxiv","version":4},"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":"2026-05-18T02:03:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9pfplbdEKtScFq7Ab2ySMIDlECY2FsI0Nm84UIfVpTlFF0LkE/Je4hmqmqlkv2U26xsSIozbMkMkd5/BGhNjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:03:59.532397Z"},"content_sha256":"d57858ef7571ae0c73aab88869730afe7c00ee9815c4a5685cfa5000ba52ceb0","schema_version":"1.0","event_id":"sha256:d57858ef7571ae0c73aab88869730afe7c00ee9815c4a5685cfa5000ba52ceb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D4B76VN5RW2SVWT6BIUI4I7JNU/bundle.json","state_url":"https://pith.science/pith/D4B76VN5RW2SVWT6BIUI4I7JNU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D4B76VN5RW2SVWT6BIUI4I7JNU/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":"2026-05-25T21:03:59Z","links":{"resolver":"https://pith.science/pith/D4B76VN5RW2SVWT6BIUI4I7JNU","bundle":"https://pith.science/pith/D4B76VN5RW2SVWT6BIUI4I7JNU/bundle.json","state":"https://pith.science/pith/D4B76VN5RW2SVWT6BIUI4I7JNU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D4B76VN5RW2SVWT6BIUI4I7JNU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:D4B76VN5RW2SVWT6BIUI4I7JNU","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":"5d2d552dfe05ab6136b0a685f749e1e1904de3b4ef8830c28de4fb460f147399","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-19T20:28:41Z","title_canon_sha256":"c1a065cabf6637a2e9e9cc1065d350586afa54ff5e843954a4f5dc7bfeaa5f91"},"schema_version":"1.0","source":{"id":"1412.6515","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6515","created_at":"2026-05-18T02:03:55Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6515v4","created_at":"2026-05-18T02:03:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6515","created_at":"2026-05-18T02:03:55Z"},{"alias_kind":"pith_short_12","alias_value":"D4B76VN5RW2S","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"D4B76VN5RW2SVWT6","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"D4B76VN5","created_at":"2026-05-18T12:28:25Z"}],"graph_snapshots":[{"event_id":"sha256:d57858ef7571ae0c73aab88869730afe7c00ee9815c4a5685cfa5000ba52ceb0","target":"graph","created_at":"2026-05-18T02:03:55Z","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":"Two recently introduced criteria for estimation of generative models are both based on a reduction to binary classification. Noise-contrastive estimation (NCE) is an estimation procedure in which a generative model is trained to be able to distinguish data samples from noise samples. Generative adversarial networks (GANs) are pairs of generator and discriminator networks, with the generator network learning to generate samples by attempting to fool the discriminator network into believing its samples are real data. Both estimation procedures use the same function to drive learning, which natur","authors_text":"Ian J. Goodfellow","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-19T20:28:41Z","title":"On distinguishability criteria for estimating generative models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6515","kind":"arxiv","version":4},"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:aac7c7c2a1c9760e1fef89038c54c679d1585eda4bca1b96e9474801e621fee1","target":"record","created_at":"2026-05-18T02:03:55Z","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":"5d2d552dfe05ab6136b0a685f749e1e1904de3b4ef8830c28de4fb460f147399","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-12-19T20:28:41Z","title_canon_sha256":"c1a065cabf6637a2e9e9cc1065d350586afa54ff5e843954a4f5dc7bfeaa5f91"},"schema_version":"1.0","source":{"id":"1412.6515","kind":"arxiv","version":4}},"canonical_sha256":"1f03ff55bd8db52ada7e0a288e23e96d2c22dfae91b91d63da401abfc5f50dc5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f03ff55bd8db52ada7e0a288e23e96d2c22dfae91b91d63da401abfc5f50dc5","first_computed_at":"2026-05-18T02:03:55.075090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:03:55.075090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m2Vm8CH6OGg7qaqZRWF042z7GfSwCBNzGO059nV4cDe4norL8mhOCyCR0edZ4N3ztXg474Qm4yKeQg6MkTOiAg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:03:55.075911Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.6515","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aac7c7c2a1c9760e1fef89038c54c679d1585eda4bca1b96e9474801e621fee1","sha256:d57858ef7571ae0c73aab88869730afe7c00ee9815c4a5685cfa5000ba52ceb0"],"state_sha256":"55904d3e4016fc7b6daeba98ef795c44873b9016bb68ccc9da4c492abb5c7fc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XPo5yrg9upnqT+53HPjjjC+MrR40koEbZwG+qV1pO7V1AmosmZkagvRU6CWhlR6CcLALSNcSWLJqrXDlhmuMDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:03:59.535999Z","bundle_sha256":"8e80b60b878a4e01f828120d32b225c29fef35636721242834415069b8f57890"}}