{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:UH2VNZXYCWY6BH2OEB3BSEGMSE","short_pith_number":"pith:UH2VNZXY","canonical_record":{"source":{"id":"1705.07057","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T15:42:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9150b769f7030f4620c951eac4e5371c9cef9c726671a8c6c75f27b58cebcfe5","abstract_canon_sha256":"84ad9a4e032be3b5c3645bca189ce2a24583732b49fb2e9eb1360d4001faa1ec"},"schema_version":"1.0"},"canonical_sha256":"a1f556e6f815b1e09f4e20761910cc913c5e518fbf7f318ed6510d484db5b3dd","source":{"kind":"arxiv","id":"1705.07057","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07057","created_at":"2026-05-18T00:13:19Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07057v4","created_at":"2026-05-18T00:13:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07057","created_at":"2026-05-18T00:13:19Z"},{"alias_kind":"pith_short_12","alias_value":"UH2VNZXYCWY6","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UH2VNZXYCWY6BH2O","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UH2VNZXY","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:UH2VNZXYCWY6BH2OEB3BSEGMSE","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07057","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T15:42:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9150b769f7030f4620c951eac4e5371c9cef9c726671a8c6c75f27b58cebcfe5","abstract_canon_sha256":"84ad9a4e032be3b5c3645bca189ce2a24583732b49fb2e9eb1360d4001faa1ec"},"schema_version":"1.0"},"canonical_sha256":"a1f556e6f815b1e09f4e20761910cc913c5e518fbf7f318ed6510d484db5b3dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:19.648847Z","signature_b64":"erGM96hVsyMxY3ncoAXyXk1vIBin/k6hp0UNTHwpMLxq090qkNY/8bNI16fJ27tPgyTO4S7ULN8X7orA468BAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1f556e6f815b1e09f4e20761910cc913c5e518fbf7f318ed6510d484db5b3dd","last_reissued_at":"2026-05-18T00:13:19.648281Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:19.648281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07057","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":"2026-05-18T00:13:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lXtLyf42tU9G5s5qUUtj8iOordlZlWaKYQYNoDFzOD/yt62HqECeiZplp5jGTJkdhTuhdEgBj8VIsyvLxnvMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:24:05.677646Z"},"content_sha256":"6ed85a2ede8c53caef6248457f613f2f5f2c6304bc1196bea9f697c807690014","schema_version":"1.0","event_id":"sha256:6ed85a2ede8c53caef6248457f613f2f5f2c6304bc1196bea9f697c807690014"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:UH2VNZXYCWY6BH2OEB3BSEGMSE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Masked Autoregressive Flow for Density Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"George Papamakarios, Iain Murray, Theo Pavlakou","submitted_at":"2017-05-19T15:42:54Z","abstract_excerpt":"Autoregressive models are among the best performing neural density estimators. We describe an approach for increasing the flexibility of an autoregressive model, based on modelling the random numbers that the model uses internally when generating data. By constructing a stack of autoregressive models, each modelling the random numbers of the next model in the stack, we obtain a type of normalizing flow suitable for density estimation, which we call Masked Autoregressive Flow. This type of flow is closely related to Inverse Autoregressive Flow and is a generalization of Real NVP. Masked Autoreg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07057","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":"2026-05-18T00:13:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dIk4Wz/Zy6FWUZDez1IoFZv4/5Op4ovjFPKozHlE23Krga5K4fkZwHpM6LrEH9tgVW/YAPDiwV0m5zKsFt19AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:24:05.678451Z"},"content_sha256":"00da55c265996c5a3053e3335c7bf8db9a62d809fbd6c7c6f2d7b5a64bd1a6b1","schema_version":"1.0","event_id":"sha256:00da55c265996c5a3053e3335c7bf8db9a62d809fbd6c7c6f2d7b5a64bd1a6b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UH2VNZXYCWY6BH2OEB3BSEGMSE/bundle.json","state_url":"https://pith.science/pith/UH2VNZXYCWY6BH2OEB3BSEGMSE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UH2VNZXYCWY6BH2OEB3BSEGMSE/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":"2026-05-29T15:24:05Z","links":{"resolver":"https://pith.science/pith/UH2VNZXYCWY6BH2OEB3BSEGMSE","bundle":"https://pith.science/pith/UH2VNZXYCWY6BH2OEB3BSEGMSE/bundle.json","state":"https://pith.science/pith/UH2VNZXYCWY6BH2OEB3BSEGMSE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UH2VNZXYCWY6BH2OEB3BSEGMSE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UH2VNZXYCWY6BH2OEB3BSEGMSE","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":"84ad9a4e032be3b5c3645bca189ce2a24583732b49fb2e9eb1360d4001faa1ec","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T15:42:54Z","title_canon_sha256":"9150b769f7030f4620c951eac4e5371c9cef9c726671a8c6c75f27b58cebcfe5"},"schema_version":"1.0","source":{"id":"1705.07057","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07057","created_at":"2026-05-18T00:13:19Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07057v4","created_at":"2026-05-18T00:13:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07057","created_at":"2026-05-18T00:13:19Z"},{"alias_kind":"pith_short_12","alias_value":"UH2VNZXYCWY6","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UH2VNZXYCWY6BH2O","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UH2VNZXY","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:00da55c265996c5a3053e3335c7bf8db9a62d809fbd6c7c6f2d7b5a64bd1a6b1","target":"graph","created_at":"2026-05-18T00:13:19Z","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":"Autoregressive models are among the best performing neural density estimators. We describe an approach for increasing the flexibility of an autoregressive model, based on modelling the random numbers that the model uses internally when generating data. By constructing a stack of autoregressive models, each modelling the random numbers of the next model in the stack, we obtain a type of normalizing flow suitable for density estimation, which we call Masked Autoregressive Flow. This type of flow is closely related to Inverse Autoregressive Flow and is a generalization of Real NVP. Masked Autoreg","authors_text":"George Papamakarios, Iain Murray, Theo Pavlakou","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T15:42:54Z","title":"Masked Autoregressive Flow for Density Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07057","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":"sha256:6ed85a2ede8c53caef6248457f613f2f5f2c6304bc1196bea9f697c807690014","target":"record","created_at":"2026-05-18T00:13:19Z","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":"84ad9a4e032be3b5c3645bca189ce2a24583732b49fb2e9eb1360d4001faa1ec","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-19T15:42:54Z","title_canon_sha256":"9150b769f7030f4620c951eac4e5371c9cef9c726671a8c6c75f27b58cebcfe5"},"schema_version":"1.0","source":{"id":"1705.07057","kind":"arxiv","version":4}},"canonical_sha256":"a1f556e6f815b1e09f4e20761910cc913c5e518fbf7f318ed6510d484db5b3dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1f556e6f815b1e09f4e20761910cc913c5e518fbf7f318ed6510d484db5b3dd","first_computed_at":"2026-05-18T00:13:19.648281Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:19.648281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"erGM96hVsyMxY3ncoAXyXk1vIBin/k6hp0UNTHwpMLxq090qkNY/8bNI16fJ27tPgyTO4S7ULN8X7orA468BAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:19.648847Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07057","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ed85a2ede8c53caef6248457f613f2f5f2c6304bc1196bea9f697c807690014","sha256:00da55c265996c5a3053e3335c7bf8db9a62d809fbd6c7c6f2d7b5a64bd1a6b1"],"state_sha256":"e4b96edb6a3546d6ac2350ac89c38cdaf66161191dfe8a79785c311774de5bb5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aj/SxBen+AgOOIO1JjXLyegwYUZuyuO7UU8rPEdBUjKzgsXPyxwU74gekT/OUAVrXNMYme/0uX7/m4mhzzdYAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T15:24:05.681858Z","bundle_sha256":"4c0127c54bc750fe8429b8e6797fa70aa449f31aad4c1e75f2b2a509b7caeab8"}}