{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CQSRZDPWSEZM75UU5WZA3POOI3","short_pith_number":"pith:CQSRZDPW","schema_version":"1.0","canonical_sha256":"14251c8df69132cff694edb20dbdce46c21e061bf98c5394b921788b6c9deed9","source":{"kind":"arxiv","id":"1802.01817","version":1},"attestation_state":"computed","paper":{"title":"Byte-Level Recursive Convolutional Auto-Encoder for Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Xiang Zhang, Yann LeCun","submitted_at":"2018-02-06T06:47:09Z","abstract_excerpt":"This article proposes to auto-encode text at byte-level using convolutional networks with a recursive architecture. The motivation is to explore whether it is possible to have scalable and homogeneous text generation at byte-level in a non-sequential fashion through the simple task of auto-encoding. We show that non-sequential text generation from a fixed-length representation is not only possible, but also achieved much better auto-encoding results than recurrent networks. The proposed model is a multi-stage deep convolutional encoder-decoder framework using residual connections, containing u"},"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":"1802.01817","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-06T06:47:09Z","cross_cats_sorted":[],"title_canon_sha256":"03a0de01346d81ebec104f417654ab8aae8aa899fd619264af02470e5b30251d","abstract_canon_sha256":"9c85638c15ecf2b5abb2562cf4ae431217e64f4389df1213201dea5156f162a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:21.199695Z","signature_b64":"+gS/TKQ5ZbNaVFQ3AB4C7avRVixk9kSRC6kcVvu+MgDaSsgg0R/c5WB8/LtnZ2tv5M7JlE1Nl4DJuSjxtIkxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14251c8df69132cff694edb20dbdce46c21e061bf98c5394b921788b6c9deed9","last_reissued_at":"2026-05-18T00:24:21.199211Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:21.199211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Byte-Level Recursive Convolutional Auto-Encoder for Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Xiang Zhang, Yann LeCun","submitted_at":"2018-02-06T06:47:09Z","abstract_excerpt":"This article proposes to auto-encode text at byte-level using convolutional networks with a recursive architecture. The motivation is to explore whether it is possible to have scalable and homogeneous text generation at byte-level in a non-sequential fashion through the simple task of auto-encoding. We show that non-sequential text generation from a fixed-length representation is not only possible, but also achieved much better auto-encoding results than recurrent networks. The proposed model is a multi-stage deep convolutional encoder-decoder framework using residual connections, containing u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.01817","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":"1802.01817","created_at":"2026-05-18T00:24:21.199286+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.01817v1","created_at":"2026-05-18T00:24:21.199286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.01817","created_at":"2026-05-18T00:24:21.199286+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQSRZDPWSEZM","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQSRZDPWSEZM75UU","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQSRZDPW","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQSRZDPWSEZM75UU5WZA3POOI3","json":"https://pith.science/pith/CQSRZDPWSEZM75UU5WZA3POOI3.json","graph_json":"https://pith.science/api/pith-number/CQSRZDPWSEZM75UU5WZA3POOI3/graph.json","events_json":"https://pith.science/api/pith-number/CQSRZDPWSEZM75UU5WZA3POOI3/events.json","paper":"https://pith.science/paper/CQSRZDPW"},"agent_actions":{"view_html":"https://pith.science/pith/CQSRZDPWSEZM75UU5WZA3POOI3","download_json":"https://pith.science/pith/CQSRZDPWSEZM75UU5WZA3POOI3.json","view_paper":"https://pith.science/paper/CQSRZDPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.01817&json=true","fetch_graph":"https://pith.science/api/pith-number/CQSRZDPWSEZM75UU5WZA3POOI3/graph.json","fetch_events":"https://pith.science/api/pith-number/CQSRZDPWSEZM75UU5WZA3POOI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQSRZDPWSEZM75UU5WZA3POOI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQSRZDPWSEZM75UU5WZA3POOI3/action/storage_attestation","attest_author":"https://pith.science/pith/CQSRZDPWSEZM75UU5WZA3POOI3/action/author_attestation","sign_citation":"https://pith.science/pith/CQSRZDPWSEZM75UU5WZA3POOI3/action/citation_signature","submit_replication":"https://pith.science/pith/CQSRZDPWSEZM75UU5WZA3POOI3/action/replication_record"}},"created_at":"2026-05-18T00:24:21.199286+00:00","updated_at":"2026-05-18T00:24:21.199286+00:00"}