{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3RCP2TUZCKWDJD7K22KMWF4ID3","short_pith_number":"pith:3RCP2TUZ","schema_version":"1.0","canonical_sha256":"dc44fd4e9912ac348fead694cb17881ef19845b22febcaf611bf2cb3d648b8e3","source":{"kind":"arxiv","id":"2406.04342","version":1},"attestation_state":"computed","paper":{"title":"Learning 1D Causal Visual Representation with De-focus Attention Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changyao Tian, Chenxin Tao, Gao Huang, Hongsheng Li, Jie Zhou, Jifeng Dai, Lewei Lu, Shiqian Su, Xizhou Zhu, Xuan Luo, Yu Qiao","submitted_at":"2024-06-06T17:59:56Z","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"},"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":"2406.04342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"fcf04a55df19946fd975c83c198f944b5259db4b482cf1f39805b64cf465b600","abstract_canon_sha256":"8fc6a6b861d318eaceacd3b0a481611e98def5271b1737ab46e21834abb14b44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:29.668725Z","signature_b64":"MW8EeuskP7pjLqTrC38wy2u3eaA2YA5FcShxIyvfqSLpJuDwQ1RWLHAyNr/n1g+qW4NR4Jdk/5O6DB1QmXyRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc44fd4e9912ac348fead694cb17881ef19845b22febcaf611bf2cb3d648b8e3","last_reissued_at":"2026-07-05T08:28:29.668269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:29.668269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning 1D Causal Visual Representation with De-focus Attention Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changyao Tian, Chenxin Tao, Gao Huang, Hongsheng Li, Jie Zhou, Jifeng Dai, Lewei Lu, Shiqian Su, Xizhou Zhu, Xuan Luo, Yu Qiao","submitted_at":"2024-06-06T17:59:56Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04342","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/2406.04342/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":"2406.04342","created_at":"2026-07-05T08:28:29.668327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04342v1","created_at":"2026-07-05T08:28:29.668327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04342","created_at":"2026-07-05T08:28:29.668327+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RCP2TUZCKWD","created_at":"2026-07-05T08:28:29.668327+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RCP2TUZCKWDJD7K","created_at":"2026-07-05T08:28:29.668327+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RCP2TUZ","created_at":"2026-07-05T08:28:29.668327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16158","citing_title":"HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding","ref_index":104,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3RCP2TUZCKWDJD7K22KMWF4ID3","json":"https://pith.science/pith/3RCP2TUZCKWDJD7K22KMWF4ID3.json","graph_json":"https://pith.science/api/pith-number/3RCP2TUZCKWDJD7K22KMWF4ID3/graph.json","events_json":"https://pith.science/api/pith-number/3RCP2TUZCKWDJD7K22KMWF4ID3/events.json","paper":"https://pith.science/paper/3RCP2TUZ"},"agent_actions":{"view_html":"https://pith.science/pith/3RCP2TUZCKWDJD7K22KMWF4ID3","download_json":"https://pith.science/pith/3RCP2TUZCKWDJD7K22KMWF4ID3.json","view_paper":"https://pith.science/paper/3RCP2TUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04342&json=true","fetch_graph":"https://pith.science/api/pith-number/3RCP2TUZCKWDJD7K22KMWF4ID3/graph.json","fetch_events":"https://pith.science/api/pith-number/3RCP2TUZCKWDJD7K22KMWF4ID3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RCP2TUZCKWDJD7K22KMWF4ID3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RCP2TUZCKWDJD7K22KMWF4ID3/action/storage_attestation","attest_author":"https://pith.science/pith/3RCP2TUZCKWDJD7K22KMWF4ID3/action/author_attestation","sign_citation":"https://pith.science/pith/3RCP2TUZCKWDJD7K22KMWF4ID3/action/citation_signature","submit_replication":"https://pith.science/pith/3RCP2TUZCKWDJD7K22KMWF4ID3/action/replication_record"}},"created_at":"2026-07-05T08:28:29.668327+00:00","updated_at":"2026-07-05T08:28:29.668327+00:00"}