{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JGYN2DVP7IXCQ66REEHAEOVOPQ","short_pith_number":"pith:JGYN2DVP","schema_version":"1.0","canonical_sha256":"49b0dd0eaffa2e287bd1210e023aae7c10e2f1628504ea950359de67b0d0a643","source":{"kind":"arxiv","id":"2410.01912","version":1},"attestation_state":"computed","paper":{"title":"A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Baobao Chang, Haozhe Zhao, Jinze Bai, Junyang Lin, Liang Chen, Sinan Tan, Tianyu Liu, Weichu Xie, Yichi Zhang, Zefan Cai","submitted_at":"2024-10-02T18:10:05Z","abstract_excerpt":"This work tackles the information loss bottleneck of vector-quantization (VQ) autoregressive image generation by introducing a novel model architecture called the 2-Dimensional Autoregression (DnD) Transformer. The DnD-Transformer predicts more codes for an image by introducing a new autoregression direction, \\textit{model depth}, along with the sequence length direction. Compared to traditional 1D autoregression and previous work utilizing similar 2D image decomposition such as RQ-Transformer, the DnD-Transformer is an end-to-end model that can generate higher quality images with the same bac"},"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":"2410.01912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T18:10:05Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e37e98335e3a1cc3ef7e3d041b8b0fe8d67560df837c71fbdada84837234b960","abstract_canon_sha256":"6444526ffdefba1796d54b0f0e3aff05d28b911e4bd216343e468ff131093b90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:57.594038Z","signature_b64":"m0ErLbKTp5k4earOgUi4gWa8NA7qRfL179AtyrSwORV9yJYHCJQv8ZvSvotQZtNbNage0o46j7PHuqrfB6vGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49b0dd0eaffa2e287bd1210e023aae7c10e2f1628504ea950359de67b0d0a643","last_reissued_at":"2026-07-05T09:14:57.593625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:57.593625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Baobao Chang, Haozhe Zhao, Jinze Bai, Junyang Lin, Liang Chen, Sinan Tan, Tianyu Liu, Weichu Xie, Yichi Zhang, Zefan Cai","submitted_at":"2024-10-02T18:10:05Z","abstract_excerpt":"This work tackles the information loss bottleneck of vector-quantization (VQ) autoregressive image generation by introducing a novel model architecture called the 2-Dimensional Autoregression (DnD) Transformer. The DnD-Transformer predicts more codes for an image by introducing a new autoregression direction, \\textit{model depth}, along with the sequence length direction. Compared to traditional 1D autoregression and previous work utilizing similar 2D image decomposition such as RQ-Transformer, the DnD-Transformer is an end-to-end model that can generate higher quality images with the same bac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01912","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/2410.01912/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":"2410.01912","created_at":"2026-07-05T09:14:57.593685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01912v1","created_at":"2026-07-05T09:14:57.593685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01912","created_at":"2026-07-05T09:14:57.593685+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGYN2DVP7IXC","created_at":"2026-07-05T09:14:57.593685+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGYN2DVP7IXCQ66R","created_at":"2026-07-05T09:14:57.593685+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGYN2DVP","created_at":"2026-07-05T09:14:57.593685+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/JGYN2DVP7IXCQ66REEHAEOVOPQ","json":"https://pith.science/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ.json","graph_json":"https://pith.science/api/pith-number/JGYN2DVP7IXCQ66REEHAEOVOPQ/graph.json","events_json":"https://pith.science/api/pith-number/JGYN2DVP7IXCQ66REEHAEOVOPQ/events.json","paper":"https://pith.science/paper/JGYN2DVP"},"agent_actions":{"view_html":"https://pith.science/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ","download_json":"https://pith.science/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ.json","view_paper":"https://pith.science/paper/JGYN2DVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01912&json=true","fetch_graph":"https://pith.science/api/pith-number/JGYN2DVP7IXCQ66REEHAEOVOPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JGYN2DVP7IXCQ66REEHAEOVOPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ/action/storage_attestation","attest_author":"https://pith.science/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ/action/author_attestation","sign_citation":"https://pith.science/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ/action/citation_signature","submit_replication":"https://pith.science/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ/action/replication_record"}},"created_at":"2026-07-05T09:14:57.593685+00:00","updated_at":"2026-07-05T09:14:57.593685+00:00"}