{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:RJBPYNHN5WHTR352G7TKVQNJ3C","short_pith_number":"pith:RJBPYNHN","canonical_record":{"source":{"id":"1601.06759","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-01-25T20:34:24Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"3710a20ec0d0236138a6bf1281059177db5b0bb4ccb0be3958e6d7e17feec4b5","abstract_canon_sha256":"f583fb251866bd43f71cb569cf6dbb2ff97eeaaf3b04dc99dc9bc6126c922305"},"schema_version":"1.0"},"canonical_sha256":"8a42fc34eded8f38efba37e6aac1a9d8b48367751ddc58796b536b9cf33fe744","source":{"kind":"arxiv","id":"1601.06759","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1601.06759","created_at":"2026-05-18T01:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"1601.06759v3","created_at":"2026-05-18T01:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.06759","created_at":"2026-05-18T01:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"RJBPYNHN5WHT","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RJBPYNHN5WHTR352","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RJBPYNHN","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:RJBPYNHN5WHTR352G7TKVQNJ3C","target":"record","payload":{"canonical_record":{"source":{"id":"1601.06759","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-01-25T20:34:24Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"3710a20ec0d0236138a6bf1281059177db5b0bb4ccb0be3958e6d7e17feec4b5","abstract_canon_sha256":"f583fb251866bd43f71cb569cf6dbb2ff97eeaaf3b04dc99dc9bc6126c922305"},"schema_version":"1.0"},"canonical_sha256":"8a42fc34eded8f38efba37e6aac1a9d8b48367751ddc58796b536b9cf33fe744","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:08:28.875846Z","signature_b64":"v7TAXJVCT4B5VOtPIDFeclYxJcFPwXwS4NX1uSM6VP/o7U1ctIFzc2fVJo33DORDcHOlbrhMl4qqOoB+dujuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a42fc34eded8f38efba37e6aac1a9d8b48367751ddc58796b536b9cf33fe744","last_reissued_at":"2026-05-18T01:08:28.875353Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:08:28.875353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1601.06759","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":"2026-05-18T01:08:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TL1PWpXh3O8wB+vK6tJohsE4DUypP5jQPrm9vsSzNSHQwWsEV3ZwEK4JNaA+Vo3m81pDgkxFNW2xFjbv9MrnCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:13:55.828356Z"},"content_sha256":"2e74c1d73c72007e224c957e5a33217c13e09177d9b29feafa3bb2449aaba050","schema_version":"1.0","event_id":"sha256:2e74c1d73c72007e224c957e5a33217c13e09177d9b29feafa3bb2449aaba050"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:RJBPYNHN5WHTR352G7TKVQNJ3C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pixel Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Aaron van den Oord, Koray Kavukcuoglu, Nal Kalchbrenner","submitted_at":"2016-01-25T20:34:24Z","abstract_excerpt":"Modeling the distribution of natural images is a landmark problem in unsupervised learning. This task requires an image model that is at once expressive, tractable and scalable. We present a deep neural network that sequentially predicts the pixels in an image along the two spatial dimensions. Our method models the discrete probability of the raw pixel values and encodes the complete set of dependencies in the image. Architectural novelties include fast two-dimensional recurrent layers and an effective use of residual connections in deep recurrent networks. We achieve log-likelihood scores on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.06759","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":"2026-05-18T01:08:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PIcalw5NgMQROSyPirn8RpaDgEgTF2ikYmjkPaeUjfFPqLFpnVAE/1o86QWZ6SWkq6FAz6FC2zNRH+vyS69hDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:13:55.828797Z"},"content_sha256":"197cd2904c8d9153526409ad59234e4d5a24538ca41e8adfae3a515a8c387750","schema_version":"1.0","event_id":"sha256:197cd2904c8d9153526409ad59234e4d5a24538ca41e8adfae3a515a8c387750"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJBPYNHN5WHTR352G7TKVQNJ3C/bundle.json","state_url":"https://pith.science/pith/RJBPYNHN5WHTR352G7TKVQNJ3C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJBPYNHN5WHTR352G7TKVQNJ3C/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":"2026-05-28T23:13:55Z","links":{"resolver":"https://pith.science/pith/RJBPYNHN5WHTR352G7TKVQNJ3C","bundle":"https://pith.science/pith/RJBPYNHN5WHTR352G7TKVQNJ3C/bundle.json","state":"https://pith.science/pith/RJBPYNHN5WHTR352G7TKVQNJ3C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJBPYNHN5WHTR352G7TKVQNJ3C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:RJBPYNHN5WHTR352G7TKVQNJ3C","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":"f583fb251866bd43f71cb569cf6dbb2ff97eeaaf3b04dc99dc9bc6126c922305","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-01-25T20:34:24Z","title_canon_sha256":"3710a20ec0d0236138a6bf1281059177db5b0bb4ccb0be3958e6d7e17feec4b5"},"schema_version":"1.0","source":{"id":"1601.06759","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1601.06759","created_at":"2026-05-18T01:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"1601.06759v3","created_at":"2026-05-18T01:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.06759","created_at":"2026-05-18T01:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"RJBPYNHN5WHT","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RJBPYNHN5WHTR352","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RJBPYNHN","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:197cd2904c8d9153526409ad59234e4d5a24538ca41e8adfae3a515a8c387750","target":"graph","created_at":"2026-05-18T01:08:28Z","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":"Modeling the distribution of natural images is a landmark problem in unsupervised learning. This task requires an image model that is at once expressive, tractable and scalable. We present a deep neural network that sequentially predicts the pixels in an image along the two spatial dimensions. Our method models the discrete probability of the raw pixel values and encodes the complete set of dependencies in the image. Architectural novelties include fast two-dimensional recurrent layers and an effective use of residual connections in deep recurrent networks. We achieve log-likelihood scores on ","authors_text":"Aaron van den Oord, Koray Kavukcuoglu, Nal Kalchbrenner","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-01-25T20:34:24Z","title":"Pixel Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.06759","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":"sha256:2e74c1d73c72007e224c957e5a33217c13e09177d9b29feafa3bb2449aaba050","target":"record","created_at":"2026-05-18T01:08:28Z","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":"f583fb251866bd43f71cb569cf6dbb2ff97eeaaf3b04dc99dc9bc6126c922305","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-01-25T20:34:24Z","title_canon_sha256":"3710a20ec0d0236138a6bf1281059177db5b0bb4ccb0be3958e6d7e17feec4b5"},"schema_version":"1.0","source":{"id":"1601.06759","kind":"arxiv","version":3}},"canonical_sha256":"8a42fc34eded8f38efba37e6aac1a9d8b48367751ddc58796b536b9cf33fe744","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a42fc34eded8f38efba37e6aac1a9d8b48367751ddc58796b536b9cf33fe744","first_computed_at":"2026-05-18T01:08:28.875353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:08:28.875353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v7TAXJVCT4B5VOtPIDFeclYxJcFPwXwS4NX1uSM6VP/o7U1ctIFzc2fVJo33DORDcHOlbrhMl4qqOoB+dujuBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:08:28.875846Z","signed_message":"canonical_sha256_bytes"},"source_id":"1601.06759","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e74c1d73c72007e224c957e5a33217c13e09177d9b29feafa3bb2449aaba050","sha256:197cd2904c8d9153526409ad59234e4d5a24538ca41e8adfae3a515a8c387750"],"state_sha256":"f68d26f3624033764e2c32ce4f3de6697f47d73b447462e933850c458cc1f078"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AcSruOc9hr6huaV/lmh06A0GgYf7nf7OY3xNmlh+qjTaF0I38f1ZIrI1VESFuYvDSk74DG4dpn5fynkRnX1wBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T23:13:55.832201Z","bundle_sha256":"abcee18e65aea9b4cfde6b8d0f58d1e997215cb9f07e67f5a03e5bbe6d128435"}}