{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4WBTSAZUSJHS5PO7MDHEKA35XV","short_pith_number":"pith:4WBTSAZU","schema_version":"1.0","canonical_sha256":"e583390334924f2ebddf60ce45037dbd7c243c985672f86cce3ed4040243d266","source":{"kind":"arxiv","id":"2503.02883","version":1},"attestation_state":"computed","paper":{"title":"ARINAR: Bi-Level Autoregressive Feature-by-Feature Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liang Zheng, Qinyu Zhao, Stephen Gould","submitted_at":"2025-03-04T18:59:56Z","abstract_excerpt":"Existing autoregressive (AR) image generative models use a token-by-token generation schema. That is, they predict a per-token probability distribution and sample the next token from that distribution. The main challenge is how to model the complex distribution of high-dimensional tokens. Previous methods either are too simplistic to fit the distribution or result in slow generation speed. Instead of fitting the distribution of the whole tokens, we explore using a AR model to generate each token in a feature-by-feature way, i.e., taking the generated features as input and generating the next f"},"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":"2503.02883","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T18:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"d70bb4781ca8e976a9d77de4cd863fbfe22aa179afa28ec54741c3a30ca85621","abstract_canon_sha256":"ac7060bb51b35f336556b91c785075ed8c87d7e55ee7e8e8a0e79064af8f7223"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:16.153987Z","signature_b64":"HQnY6FX/fk5Rd7ZP+WeH2Ez08MQzj3PPHneC0hFvzK6rxKA6nTn2KysxBnDwBtWWd8FbFPAIycVXUfBGfsWjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e583390334924f2ebddf60ce45037dbd7c243c985672f86cce3ed4040243d266","last_reissued_at":"2026-07-05T10:24:16.153339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:16.153339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ARINAR: Bi-Level Autoregressive Feature-by-Feature Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liang Zheng, Qinyu Zhao, Stephen Gould","submitted_at":"2025-03-04T18:59:56Z","abstract_excerpt":"Existing autoregressive (AR) image generative models use a token-by-token generation schema. That is, they predict a per-token probability distribution and sample the next token from that distribution. The main challenge is how to model the complex distribution of high-dimensional tokens. Previous methods either are too simplistic to fit the distribution or result in slow generation speed. Instead of fitting the distribution of the whole tokens, we explore using a AR model to generate each token in a feature-by-feature way, i.e., taking the generated features as input and generating the next f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02883","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.02883/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.02883","created_at":"2026-07-05T10:24:16.153432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02883v1","created_at":"2026-07-05T10:24:16.153432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02883","created_at":"2026-07-05T10:24:16.153432+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WBTSAZUSJHS","created_at":"2026-07-05T10:24:16.153432+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WBTSAZUSJHS5PO7","created_at":"2026-07-05T10:24:16.153432+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WBTSAZU","created_at":"2026-07-05T10:24:16.153432+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/4WBTSAZUSJHS5PO7MDHEKA35XV","json":"https://pith.science/pith/4WBTSAZUSJHS5PO7MDHEKA35XV.json","graph_json":"https://pith.science/api/pith-number/4WBTSAZUSJHS5PO7MDHEKA35XV/graph.json","events_json":"https://pith.science/api/pith-number/4WBTSAZUSJHS5PO7MDHEKA35XV/events.json","paper":"https://pith.science/paper/4WBTSAZU"},"agent_actions":{"view_html":"https://pith.science/pith/4WBTSAZUSJHS5PO7MDHEKA35XV","download_json":"https://pith.science/pith/4WBTSAZUSJHS5PO7MDHEKA35XV.json","view_paper":"https://pith.science/paper/4WBTSAZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02883&json=true","fetch_graph":"https://pith.science/api/pith-number/4WBTSAZUSJHS5PO7MDHEKA35XV/graph.json","fetch_events":"https://pith.science/api/pith-number/4WBTSAZUSJHS5PO7MDHEKA35XV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WBTSAZUSJHS5PO7MDHEKA35XV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WBTSAZUSJHS5PO7MDHEKA35XV/action/storage_attestation","attest_author":"https://pith.science/pith/4WBTSAZUSJHS5PO7MDHEKA35XV/action/author_attestation","sign_citation":"https://pith.science/pith/4WBTSAZUSJHS5PO7MDHEKA35XV/action/citation_signature","submit_replication":"https://pith.science/pith/4WBTSAZUSJHS5PO7MDHEKA35XV/action/replication_record"}},"created_at":"2026-07-05T10:24:16.153432+00:00","updated_at":"2026-07-05T10:24:16.153432+00:00"}