{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JGYN2DVP7IXCQ66REEHAEOVOPQ","short_pith_number":"pith:JGYN2DVP","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"},"canonical_sha256":"49b0dd0eaffa2e287bd1210e023aae7c10e2f1628504ea950359de67b0d0a643","source":{"kind":"arxiv","id":"2410.01912","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01912","created_at":"2026-07-05T09:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01912v1","created_at":"2026-07-05T09:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01912","created_at":"2026-07-05T09:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"JGYN2DVP7IXC","created_at":"2026-07-05T09:14:57Z"},{"alias_kind":"pith_short_16","alias_value":"JGYN2DVP7IXCQ66R","created_at":"2026-07-05T09:14:57Z"},{"alias_kind":"pith_short_8","alias_value":"JGYN2DVP","created_at":"2026-07-05T09:14:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JGYN2DVP7IXCQ66REEHAEOVOPQ","target":"record","payload":{"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"},"canonical_sha256":"49b0dd0eaffa2e287bd1210e023aae7c10e2f1628504ea950359de67b0d0a643","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"},"source_kind":"arxiv","source_id":"2410.01912","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:14:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VDxPFFgXCLOdCddu4rmqH+vl7c4TVlZyG/t0s72ZVmQaNpF3NYmU4izbCq5kJKLanJzjK3/LishCGnajshACDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:59:53.768191Z"},"content_sha256":"8c686303250571304b837ec559595dfdf7f7823422a855000467585c697fe668","schema_version":"1.0","event_id":"sha256:8c686303250571304b837ec559595dfdf7f7823422a855000467585c697fe668"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JGYN2DVP7IXCQ66REEHAEOVOPQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:14:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OUPq93mHwcR6FESTLHTnUpuLidTgLu18fVzVBXI9E4tCe3eL8xWPFAkmPJwhtiiEvwGRQzGjEJqbiFaarx2mAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:59:53.768896Z"},"content_sha256":"1ee3d45c7a14f81da26b8a93f22700286b0cd8a0e3ba423e9f5aba57b4ca7280","schema_version":"1.0","event_id":"sha256:1ee3d45c7a14f81da26b8a93f22700286b0cd8a0e3ba423e9f5aba57b4ca7280"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ/bundle.json","state_url":"https://pith.science/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T13:59:53Z","links":{"resolver":"https://pith.science/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ","bundle":"https://pith.science/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ/bundle.json","state":"https://pith.science/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JGYN2DVP7IXCQ66REEHAEOVOPQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JGYN2DVP7IXCQ66REEHAEOVOPQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6444526ffdefba1796d54b0f0e3aff05d28b911e4bd216343e468ff131093b90","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T18:10:05Z","title_canon_sha256":"e37e98335e3a1cc3ef7e3d041b8b0fe8d67560df837c71fbdada84837234b960"},"schema_version":"1.0","source":{"id":"2410.01912","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01912","created_at":"2026-07-05T09:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01912v1","created_at":"2026-07-05T09:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01912","created_at":"2026-07-05T09:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"JGYN2DVP7IXC","created_at":"2026-07-05T09:14:57Z"},{"alias_kind":"pith_short_16","alias_value":"JGYN2DVP7IXCQ66R","created_at":"2026-07-05T09:14:57Z"},{"alias_kind":"pith_short_8","alias_value":"JGYN2DVP","created_at":"2026-07-05T09:14:57Z"}],"graph_snapshots":[{"event_id":"sha256:1ee3d45c7a14f81da26b8a93f22700286b0cd8a0e3ba423e9f5aba57b4ca7280","target":"graph","created_at":"2026-07-05T09:14:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.01912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Baobao Chang, Haozhe Zhao, Jinze Bai, Junyang Lin, Liang Chen, Sinan Tan, Tianyu Liu, Weichu Xie, Yichi Zhang, Zefan Cai","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T18:10:05Z","title":"A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01912","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8c686303250571304b837ec559595dfdf7f7823422a855000467585c697fe668","target":"record","created_at":"2026-07-05T09:14:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6444526ffdefba1796d54b0f0e3aff05d28b911e4bd216343e468ff131093b90","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T18:10:05Z","title_canon_sha256":"e37e98335e3a1cc3ef7e3d041b8b0fe8d67560df837c71fbdada84837234b960"},"schema_version":"1.0","source":{"id":"2410.01912","kind":"arxiv","version":1}},"canonical_sha256":"49b0dd0eaffa2e287bd1210e023aae7c10e2f1628504ea950359de67b0d0a643","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49b0dd0eaffa2e287bd1210e023aae7c10e2f1628504ea950359de67b0d0a643","first_computed_at":"2026-07-05T09:14:57.593625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:57.593625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m0ErLbKTp5k4earOgUi4gWa8NA7qRfL179AtyrSwORV9yJYHCJQv8ZvSvotQZtNbNage0o46j7PHuqrfB6vGBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:57.594038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01912","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c686303250571304b837ec559595dfdf7f7823422a855000467585c697fe668","sha256:1ee3d45c7a14f81da26b8a93f22700286b0cd8a0e3ba423e9f5aba57b4ca7280"],"state_sha256":"00bfea5b69f89b9b5ea919dea954666662df1a0588c31602001f694ed296ee74"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mVd6i4PoJ8K4OiL98jyx527umcnPcoM+NBORIhAQAbtYlt5RCVMFG8A3KJy2cdQUOrWv6xqXYk/+tA5UzhwlCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:59:53.792211Z","bundle_sha256":"fe2612b0adc21eb4e54b34fc073f3cf727cc0413878f725542dfe564eaddef8f"}}