{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7GUQWSX6CS2342MKR33JESM5ZR","short_pith_number":"pith:7GUQWSX6","schema_version":"1.0","canonical_sha256":"f9a90b4afe14b5be698a8ef692499dcc71bde8587499279979d27cde8f3b1ebc","source":{"kind":"arxiv","id":"2506.04421","version":1},"attestation_state":"computed","paper":{"title":"HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Christopher R\\'e, Daniel Y. Fu, David W. Romero, Hermann Kumbong, Ming-Yu Liu, Tsung-Yi Lin, Xian Liu, Xihui Liu, Ziwei Liu","submitted_at":"2025-06-04T20:08:07Z","abstract_excerpt":"Visual Auto-Regressive modeling (VAR) has shown promise in bridging the speed and quality gap between autoregressive image models and diffusion models. VAR reformulates autoregressive modeling by decomposing an image into successive resolution scales. During inference, an image is generated by predicting all the tokens in the next (higher-resolution) scale, conditioned on all tokens in all previous (lower-resolution) scales. However, this formulation suffers from reduced image quality due to the parallel generation of all tokens in a resolution scale; has sequence lengths scaling superlinearly"},"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":"2506.04421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T20:08:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"467066d8e4183b03e0e64c72f36d40029ef96ad313459d8808ed1ae5ac632396","abstract_canon_sha256":"c27c594173bc9864865d636e8e9abe29cb1ccf3152d87982830faae48e0d0c7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:14.068282Z","signature_b64":"n3QI7DAFJLopVH/4FxR29oH/razC70yRZ8KZT9eW7MwwSdFVMrwnqDOCcAcxMp/L/+WDvkQwDg+Loke/3ENnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9a90b4afe14b5be698a8ef692499dcc71bde8587499279979d27cde8f3b1ebc","last_reissued_at":"2026-07-05T11:16:14.067756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:14.067756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Christopher R\\'e, Daniel Y. Fu, David W. Romero, Hermann Kumbong, Ming-Yu Liu, Tsung-Yi Lin, Xian Liu, Xihui Liu, Ziwei Liu","submitted_at":"2025-06-04T20:08:07Z","abstract_excerpt":"Visual Auto-Regressive modeling (VAR) has shown promise in bridging the speed and quality gap between autoregressive image models and diffusion models. VAR reformulates autoregressive modeling by decomposing an image into successive resolution scales. During inference, an image is generated by predicting all the tokens in the next (higher-resolution) scale, conditioned on all tokens in all previous (lower-resolution) scales. However, this formulation suffers from reduced image quality due to the parallel generation of all tokens in a resolution scale; has sequence lengths scaling superlinearly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04421","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/2506.04421/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":"2506.04421","created_at":"2026-07-05T11:16:14.067812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04421v1","created_at":"2026-07-05T11:16:14.067812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04421","created_at":"2026-07-05T11:16:14.067812+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GUQWSX6CS23","created_at":"2026-07-05T11:16:14.067812+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GUQWSX6CS2342MK","created_at":"2026-07-05T11:16:14.067812+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GUQWSX6","created_at":"2026-07-05T11:16:14.067812+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/7GUQWSX6CS2342MKR33JESM5ZR","json":"https://pith.science/pith/7GUQWSX6CS2342MKR33JESM5ZR.json","graph_json":"https://pith.science/api/pith-number/7GUQWSX6CS2342MKR33JESM5ZR/graph.json","events_json":"https://pith.science/api/pith-number/7GUQWSX6CS2342MKR33JESM5ZR/events.json","paper":"https://pith.science/paper/7GUQWSX6"},"agent_actions":{"view_html":"https://pith.science/pith/7GUQWSX6CS2342MKR33JESM5ZR","download_json":"https://pith.science/pith/7GUQWSX6CS2342MKR33JESM5ZR.json","view_paper":"https://pith.science/paper/7GUQWSX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04421&json=true","fetch_graph":"https://pith.science/api/pith-number/7GUQWSX6CS2342MKR33JESM5ZR/graph.json","fetch_events":"https://pith.science/api/pith-number/7GUQWSX6CS2342MKR33JESM5ZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GUQWSX6CS2342MKR33JESM5ZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GUQWSX6CS2342MKR33JESM5ZR/action/storage_attestation","attest_author":"https://pith.science/pith/7GUQWSX6CS2342MKR33JESM5ZR/action/author_attestation","sign_citation":"https://pith.science/pith/7GUQWSX6CS2342MKR33JESM5ZR/action/citation_signature","submit_replication":"https://pith.science/pith/7GUQWSX6CS2342MKR33JESM5ZR/action/replication_record"}},"created_at":"2026-07-05T11:16:14.067812+00:00","updated_at":"2026-07-05T11:16:14.067812+00:00"}