{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NIPLM2UDFEJZZJH35AAEC432RV","short_pith_number":"pith:NIPLM2UD","schema_version":"1.0","canonical_sha256":"6a1eb66a8329139ca4fbe80041737a8d66855ec4f343adb3ba9079be8cc95b28","source":{"kind":"arxiv","id":"2402.12376","version":4},"attestation_state":"computed","paper":{"title":"FiT: Flexible Vision Transformer for Diffusion Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengyue Wu, Di Huang, Lei Bai, Wanli Ouyang, Xihui Liu, Zeyu Lu, Zidong Wang","submitted_at":"2024-02-19T18:59:07Z","abstract_excerpt":"Nature is infinitely resolution-free. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To overcome this limitation, we present the Flexible Vision Transformer (FiT), a transformer architecture specifically designed for generating images with unrestricted resolutions and aspect ratios. Unlike traditional methods that perceive images as static-resolution grids, FiT conceptualizes images as sequences of dynamically-sized tokens. This perspective enables a flexible tra"},"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":"2402.12376","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-19T18:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"c301abcc2914487a0d3a54b414f85457f479436c4fb4ebaf0fb5fefea1f8913d","abstract_canon_sha256":"ad490332f9d44215c9b62138842451eafc034e98aec2b86256d7721db558ab7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:22.645267Z","signature_b64":"haBnKHcwzXw1W+Ek6iFCF77Jbc+SRTlyYC8/gVWqi4bY1NzgB45Y3vj5eC2QSN7NGsPr2RBfmmhNCKpB7D+wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a1eb66a8329139ca4fbe80041737a8d66855ec4f343adb3ba9079be8cc95b28","last_reissued_at":"2026-07-05T09:20:22.644684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:22.644684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FiT: Flexible Vision Transformer for Diffusion Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengyue Wu, Di Huang, Lei Bai, Wanli Ouyang, Xihui Liu, Zeyu Lu, Zidong Wang","submitted_at":"2024-02-19T18:59:07Z","abstract_excerpt":"Nature is infinitely resolution-free. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To overcome this limitation, we present the Flexible Vision Transformer (FiT), a transformer architecture specifically designed for generating images with unrestricted resolutions and aspect ratios. Unlike traditional methods that perceive images as static-resolution grids, FiT conceptualizes images as sequences of dynamically-sized tokens. This perspective enables a flexible tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12376","kind":"arxiv","version":4},"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/2402.12376/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":"2402.12376","created_at":"2026-07-05T09:20:22.644755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12376v4","created_at":"2026-07-05T09:20:22.644755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12376","created_at":"2026-07-05T09:20:22.644755+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIPLM2UDFEJZ","created_at":"2026-07-05T09:20:22.644755+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIPLM2UDFEJZZJH3","created_at":"2026-07-05T09:20:22.644755+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIPLM2UD","created_at":"2026-07-05T09:20:22.644755+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.00131","citing_title":"Open-Sora Plan: Open-Source Large Video Generation Model","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22668","citing_title":"SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15908","citing_title":"RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12491","citing_title":"Elastic Attention Cores for Scalable Vision Transformers","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09151","citing_title":"MultiMedVision: Multi-Modal Medical Vision Framework","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24885","citing_title":"VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05331","citing_title":"ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2412.20404","citing_title":"Open-Sora: Democratizing Efficient Video Production for All","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00103","citing_title":"LTX-Video: Realtime Video Latent Diffusion","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NIPLM2UDFEJZZJH35AAEC432RV","json":"https://pith.science/pith/NIPLM2UDFEJZZJH35AAEC432RV.json","graph_json":"https://pith.science/api/pith-number/NIPLM2UDFEJZZJH35AAEC432RV/graph.json","events_json":"https://pith.science/api/pith-number/NIPLM2UDFEJZZJH35AAEC432RV/events.json","paper":"https://pith.science/paper/NIPLM2UD"},"agent_actions":{"view_html":"https://pith.science/pith/NIPLM2UDFEJZZJH35AAEC432RV","download_json":"https://pith.science/pith/NIPLM2UDFEJZZJH35AAEC432RV.json","view_paper":"https://pith.science/paper/NIPLM2UD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12376&json=true","fetch_graph":"https://pith.science/api/pith-number/NIPLM2UDFEJZZJH35AAEC432RV/graph.json","fetch_events":"https://pith.science/api/pith-number/NIPLM2UDFEJZZJH35AAEC432RV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIPLM2UDFEJZZJH35AAEC432RV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIPLM2UDFEJZZJH35AAEC432RV/action/storage_attestation","attest_author":"https://pith.science/pith/NIPLM2UDFEJZZJH35AAEC432RV/action/author_attestation","sign_citation":"https://pith.science/pith/NIPLM2UDFEJZZJH35AAEC432RV/action/citation_signature","submit_replication":"https://pith.science/pith/NIPLM2UDFEJZZJH35AAEC432RV/action/replication_record"}},"created_at":"2026-07-05T09:20:22.644755+00:00","updated_at":"2026-07-05T09:20:22.644755+00:00"}