{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3RCP2TUZCKWDJD7K22KMWF4ID3","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":"8fc6a6b861d318eaceacd3b0a481611e98def5271b1737ab46e21834abb14b44","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:59:56Z","title_canon_sha256":"fcf04a55df19946fd975c83c198f944b5259db4b482cf1f39805b64cf465b600"},"schema_version":"1.0","source":{"id":"2406.04342","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04342","created_at":"2026-07-05T08:28:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04342v1","created_at":"2026-07-05T08:28:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04342","created_at":"2026-07-05T08:28:29Z"},{"alias_kind":"pith_short_12","alias_value":"3RCP2TUZCKWD","created_at":"2026-07-05T08:28:29Z"},{"alias_kind":"pith_short_16","alias_value":"3RCP2TUZCKWDJD7K","created_at":"2026-07-05T08:28:29Z"},{"alias_kind":"pith_short_8","alias_value":"3RCP2TUZ","created_at":"2026-07-05T08:28:29Z"}],"graph_snapshots":[{"event_id":"sha256:49315b2bac7617582b4d757c3cff15e9df0e85a170383351b192ee6f279b9bf0","target":"graph","created_at":"2026-07-05T08:28:29Z","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/2406.04342/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modality differences have led to the development of heterogeneous architectures for vision and language models. While images typically require 2D non-causal modeling, texts utilize 1D causal modeling. This distinction poses significant challenges in constructing unified multi-modal models. This paper explores the feasibility of representing images using 1D causal modeling. We identify an \"over-focus\" issue in existing 1D causal vision models, where attention overly concentrates on a small proportion of visual tokens. The issue of \"over-focus\" hinders the model's ability to extract diverse visu","authors_text":"Changyao Tian, Chenxin Tao, Gao Huang, Hongsheng Li, Jie Zhou, Jifeng Dai, Lewei Lu, Shiqian Su, Xizhou Zhu, Xuan Luo, Yu Qiao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:59:56Z","title":"Learning 1D Causal Visual Representation with De-focus Attention Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04342","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":"sha256:5ff5155ffc420dff7fab5fa730daeb76667067f968ca8be5c4cf40eb80df4edd","target":"record","created_at":"2026-07-05T08:28:29Z","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":"8fc6a6b861d318eaceacd3b0a481611e98def5271b1737ab46e21834abb14b44","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:59:56Z","title_canon_sha256":"fcf04a55df19946fd975c83c198f944b5259db4b482cf1f39805b64cf465b600"},"schema_version":"1.0","source":{"id":"2406.04342","kind":"arxiv","version":1}},"canonical_sha256":"dc44fd4e9912ac348fead694cb17881ef19845b22febcaf611bf2cb3d648b8e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc44fd4e9912ac348fead694cb17881ef19845b22febcaf611bf2cb3d648b8e3","first_computed_at":"2026-07-05T08:28:29.668269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:29.668269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MW8EeuskP7pjLqTrC38wy2u3eaA2YA5FcShxIyvfqSLpJuDwQ1RWLHAyNr/n1g+qW4NR4Jdk/5O6DB1QmXyRBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:29.668725Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04342","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ff5155ffc420dff7fab5fa730daeb76667067f968ca8be5c4cf40eb80df4edd","sha256:49315b2bac7617582b4d757c3cff15e9df0e85a170383351b192ee6f279b9bf0"],"state_sha256":"779bb8419aeec3d16fd3a5f72fe4a4261deecdb92f79c86511cb687336a3fd78"}