{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HMACJZVDLUT2JKI3WXGHL7XXEK","short_pith_number":"pith:HMACJZVD","schema_version":"1.0","canonical_sha256":"3b0024e6a35d27a4a91bb5cc75fef722a15b1051ad7d290a8e255fe6860d8f30","source":{"kind":"arxiv","id":"1712.09763","version":1},"attestation_state":"computed","paper":{"title":"PixelSNAIL: An Improved Autoregressive Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mostafa Rohaninejad, Nikhil Mishra, Pieter Abbeel, Xi Chen","submitted_at":"2017-12-28T05:54:44Z","abstract_excerpt":"Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio. They pose density estimation as a sequence modeling task, where a recurrent neural network (RNN) models the conditional distribution over the next element conditioned on all previous elements. In this paradigm, the bottleneck is the extent to which the RNN can model long-range dependencies, and the most successful approaches rely on causal convolutions, which offer better access to earlier parts of the sequence than conventional RNNs. Taki"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1712.09763","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-28T05:54:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c2e87ef05f03ade94b38a781eec22f1982242f381e021f163ab4d945177caa21","abstract_canon_sha256":"6fec312b8c26a5cbaa26cdc2987b9af52dfe139dafe1743b968135666f94365b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:05.634502Z","signature_b64":"pCoTHFhkBBd4txAixqKAahM9qwbXx7zqW8StN7TRoqRSV50MbtN9bm71p4gZ2SpXqeeH2JpSfuCKhHJ744Q9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b0024e6a35d27a4a91bb5cc75fef722a15b1051ad7d290a8e255fe6860d8f30","last_reissued_at":"2026-05-18T00:27:05.633800Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:05.633800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PixelSNAIL: An Improved Autoregressive Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mostafa Rohaninejad, Nikhil Mishra, Pieter Abbeel, Xi Chen","submitted_at":"2017-12-28T05:54:44Z","abstract_excerpt":"Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio. They pose density estimation as a sequence modeling task, where a recurrent neural network (RNN) models the conditional distribution over the next element conditioned on all previous elements. In this paradigm, the bottleneck is the extent to which the RNN can model long-range dependencies, and the most successful approaches rely on causal convolutions, which offer better access to earlier parts of the sequence than conventional RNNs. Taki"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09763","kind":"arxiv","version":1},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1712.09763","created_at":"2026-05-18T00:27:05.633908+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09763v1","created_at":"2026-05-18T00:27:05.633908+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09763","created_at":"2026-05-18T00:27:05.633908+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMACJZVDLUT2","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMACJZVDLUT2JKI3","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMACJZVD","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2104.10157","citing_title":"VideoGPT: Video Generation using VQ-VAE and Transformers","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"1904.10509","citing_title":"Generating Long Sequences with Sparse Transformers","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HMACJZVDLUT2JKI3WXGHL7XXEK","json":"https://pith.science/pith/HMACJZVDLUT2JKI3WXGHL7XXEK.json","graph_json":"https://pith.science/api/pith-number/HMACJZVDLUT2JKI3WXGHL7XXEK/graph.json","events_json":"https://pith.science/api/pith-number/HMACJZVDLUT2JKI3WXGHL7XXEK/events.json","paper":"https://pith.science/paper/HMACJZVD"},"agent_actions":{"view_html":"https://pith.science/pith/HMACJZVDLUT2JKI3WXGHL7XXEK","download_json":"https://pith.science/pith/HMACJZVDLUT2JKI3WXGHL7XXEK.json","view_paper":"https://pith.science/paper/HMACJZVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09763&json=true","fetch_graph":"https://pith.science/api/pith-number/HMACJZVDLUT2JKI3WXGHL7XXEK/graph.json","fetch_events":"https://pith.science/api/pith-number/HMACJZVDLUT2JKI3WXGHL7XXEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMACJZVDLUT2JKI3WXGHL7XXEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMACJZVDLUT2JKI3WXGHL7XXEK/action/storage_attestation","attest_author":"https://pith.science/pith/HMACJZVDLUT2JKI3WXGHL7XXEK/action/author_attestation","sign_citation":"https://pith.science/pith/HMACJZVDLUT2JKI3WXGHL7XXEK/action/citation_signature","submit_replication":"https://pith.science/pith/HMACJZVDLUT2JKI3WXGHL7XXEK/action/replication_record"}},"created_at":"2026-05-18T00:27:05.633908+00:00","updated_at":"2026-05-18T00:27:05.633908+00:00"}