{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:L5J25VLO3UAG327FSRGGW2UYEG","short_pith_number":"pith:L5J25VLO","canonical_record":{"source":{"id":"1903.04933","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-06T22:13:52Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"55c28cf7dff353db09e844f00c40b257d72733b7409322515547327cff0d90dc","abstract_canon_sha256":"ca3171a05e64f195545edc630d85f193cf08be14b22b86276a0068e9822a606f"},"schema_version":"1.0"},"canonical_sha256":"5f53aed56edd006debe5944c6b6a9821b4dd776d334817aba23eb8b4a4f863ee","source":{"kind":"arxiv","id":"1903.04933","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.04933","created_at":"2026-07-05T00:10:34Z"},{"alias_kind":"arxiv_version","alias_value":"1903.04933v2","created_at":"2026-07-05T00:10:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04933","created_at":"2026-07-05T00:10:34Z"},{"alias_kind":"pith_short_12","alias_value":"L5J25VLO3UAG","created_at":"2026-07-05T00:10:34Z"},{"alias_kind":"pith_short_16","alias_value":"L5J25VLO3UAG327F","created_at":"2026-07-05T00:10:34Z"},{"alias_kind":"pith_short_8","alias_value":"L5J25VLO","created_at":"2026-07-05T00:10:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:L5J25VLO3UAG327FSRGGW2UYEG","target":"record","payload":{"canonical_record":{"source":{"id":"1903.04933","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-06T22:13:52Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"55c28cf7dff353db09e844f00c40b257d72733b7409322515547327cff0d90dc","abstract_canon_sha256":"ca3171a05e64f195545edc630d85f193cf08be14b22b86276a0068e9822a606f"},"schema_version":"1.0"},"canonical_sha256":"5f53aed56edd006debe5944c6b6a9821b4dd776d334817aba23eb8b4a4f863ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:34.390150Z","signature_b64":"UJbt7y63wkNd0SMF1w0GY5NqwQAXartNdV/LRbggaoN7bXLDCNO3bMF9JjSZkuzkd8x2oM8wSZisP/XEVHF4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f53aed56edd006debe5944c6b6a9821b4dd776d334817aba23eb8b4a4f863ee","last_reissued_at":"2026-07-05T00:10:34.389711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:34.389711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.04933","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":"2026-07-05T00:10:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FK9LZu0W1/f+78bNUeANMDxmWUc0Pywm+/m8EkWvUYnjKG3wq1zK6d9bBn1uV5RxPzMtm4cqhijXrepY0cayDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:39:40.678548Z"},"content_sha256":"03a44aa0d4ff5856eb256016ca547b2aaa9e36d146325a0ee40dda7ca6ddf1dd","schema_version":"1.0","event_id":"sha256:03a44aa0d4ff5856eb256016ca547b2aaa9e36d146325a0ee40dda7ca6ddf1dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:L5J25VLO3UAG327FSRGGW2UYEG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Autoregressive Image Models with Auxiliary Decoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jeffrey De Fauw, Karen Simonyan, Sander Dieleman","submitted_at":"2019-03-06T22:13:52Z","abstract_excerpt":"Autoregressive generative models of images tend to be biased towards capturing local structure, and as a result they often produce samples which are lacking in terms of large-scale coherence. To address this, we propose two methods to learn discrete representations of images which abstract away local detail. We show that autoregressive models conditioned on these representations can produce high-fidelity reconstructions of images, and that we can train autoregressive priors on these representations that produce samples with large-scale coherence. We can recursively apply the learning procedure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04933","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1903.04933/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:10:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ICireV2J2mxuSol/m0GM7Sybrawt1+zuKef9Zzr9PbcVG6D6wS8S4l6Yg5C4Yy1bqanHzKtck+A+KaUCFvsZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:39:40.679060Z"},"content_sha256":"f2c9ebdd639e0d5e0fea25b2e6ae1e765b204bc974d850a5cc6c5660050fffbf","schema_version":"1.0","event_id":"sha256:f2c9ebdd639e0d5e0fea25b2e6ae1e765b204bc974d850a5cc6c5660050fffbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L5J25VLO3UAG327FSRGGW2UYEG/bundle.json","state_url":"https://pith.science/pith/L5J25VLO3UAG327FSRGGW2UYEG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L5J25VLO3UAG327FSRGGW2UYEG/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":"2026-08-03T17:39:40Z","links":{"resolver":"https://pith.science/pith/L5J25VLO3UAG327FSRGGW2UYEG","bundle":"https://pith.science/pith/L5J25VLO3UAG327FSRGGW2UYEG/bundle.json","state":"https://pith.science/pith/L5J25VLO3UAG327FSRGGW2UYEG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L5J25VLO3UAG327FSRGGW2UYEG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:L5J25VLO3UAG327FSRGGW2UYEG","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":"ca3171a05e64f195545edc630d85f193cf08be14b22b86276a0068e9822a606f","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-06T22:13:52Z","title_canon_sha256":"55c28cf7dff353db09e844f00c40b257d72733b7409322515547327cff0d90dc"},"schema_version":"1.0","source":{"id":"1903.04933","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.04933","created_at":"2026-07-05T00:10:34Z"},{"alias_kind":"arxiv_version","alias_value":"1903.04933v2","created_at":"2026-07-05T00:10:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04933","created_at":"2026-07-05T00:10:34Z"},{"alias_kind":"pith_short_12","alias_value":"L5J25VLO3UAG","created_at":"2026-07-05T00:10:34Z"},{"alias_kind":"pith_short_16","alias_value":"L5J25VLO3UAG327F","created_at":"2026-07-05T00:10:34Z"},{"alias_kind":"pith_short_8","alias_value":"L5J25VLO","created_at":"2026-07-05T00:10:34Z"}],"graph_snapshots":[{"event_id":"sha256:f2c9ebdd639e0d5e0fea25b2e6ae1e765b204bc974d850a5cc6c5660050fffbf","target":"graph","created_at":"2026-07-05T00:10:34Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1903.04933/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive generative models of images tend to be biased towards capturing local structure, and as a result they often produce samples which are lacking in terms of large-scale coherence. To address this, we propose two methods to learn discrete representations of images which abstract away local detail. We show that autoregressive models conditioned on these representations can produce high-fidelity reconstructions of images, and that we can train autoregressive priors on these representations that produce samples with large-scale coherence. We can recursively apply the learning procedure","authors_text":"Jeffrey De Fauw, Karen Simonyan, Sander Dieleman","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-06T22:13:52Z","title":"Hierarchical Autoregressive Image Models with Auxiliary Decoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04933","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":"sha256:03a44aa0d4ff5856eb256016ca547b2aaa9e36d146325a0ee40dda7ca6ddf1dd","target":"record","created_at":"2026-07-05T00:10:34Z","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":"ca3171a05e64f195545edc630d85f193cf08be14b22b86276a0068e9822a606f","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-06T22:13:52Z","title_canon_sha256":"55c28cf7dff353db09e844f00c40b257d72733b7409322515547327cff0d90dc"},"schema_version":"1.0","source":{"id":"1903.04933","kind":"arxiv","version":2}},"canonical_sha256":"5f53aed56edd006debe5944c6b6a9821b4dd776d334817aba23eb8b4a4f863ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f53aed56edd006debe5944c6b6a9821b4dd776d334817aba23eb8b4a4f863ee","first_computed_at":"2026-07-05T00:10:34.389711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:10:34.389711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UJbt7y63wkNd0SMF1w0GY5NqwQAXartNdV/LRbggaoN7bXLDCNO3bMF9JjSZkuzkd8x2oM8wSZisP/XEVHF4Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:10:34.390150Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.04933","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03a44aa0d4ff5856eb256016ca547b2aaa9e36d146325a0ee40dda7ca6ddf1dd","sha256:f2c9ebdd639e0d5e0fea25b2e6ae1e765b204bc974d850a5cc6c5660050fffbf"],"state_sha256":"cc38b0018fccce282e82ea49ec2f746d9ab962ede9c7ec8ccaef5d7523dcde12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ng3/DvOtoDOJZq908q9qsbtbsYZNkKzWTCxM9iid8YIwXY+7gITlpsH5K0a+/Fol8nIEit7okrlhnQEVh5YvAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:39:40.683957Z","bundle_sha256":"bdf57619c09e5921c11d006863951642bdad89ff983ffa7af08b551b76d78bab"}}