{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GPXYNRQA7EDMSXIMFKZOGAGCIN","short_pith_number":"pith:GPXYNRQA","schema_version":"1.0","canonical_sha256":"33ef86c600f906c95d0c2ab2e300c24349c22aa4f71e48fcd2d3d5205f6e37a7","source":{"kind":"arxiv","id":"2504.06232","version":2},"attestation_state":"computed","paper":{"title":"HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaqi Wang, Jiazi Bu, Pan Zhang, Pengyang Ling, Tong Wu, Xiaoyi Dong, Yuhang Cao, Yuhang Zang, Yujie Zhou","submitted_at":"2025-04-08T17:30:40Z","abstract_excerpt":"Text-to-image (T2I) diffusion/flow models have drawn considerable attention recently due to their remarkable ability to deliver flexible visual creations. Still, high-resolution image synthesis presents formidable challenges due to the scarcity and complexity of high-resolution content. Recent approaches have investigated training-free strategies to enable high-resolution image synthesis with pre-trained models. However, these techniques often struggle with generating high-quality visuals and tend to exhibit artifacts or low-fidelity details, as they typically rely solely on the endpoint of th"},"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":"2504.06232","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-08T17:30:40Z","cross_cats_sorted":[],"title_canon_sha256":"d274349fa881e73b066841576652867361a206d7b04212f642f6aba405e72466","abstract_canon_sha256":"9e262c249cbb075b9bc19785e8d97dfd5cef5708aadd80f92ad97b8a2748c9bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:59.077432Z","signature_b64":"CgtBme9jbtDiTbQQQOtS/cQ8Q9+v1uSztmPp4/oFbidrOY4Qn0DkhX8h2tw6TvJa5xPWJ+snXRdKHdAZA/8FAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33ef86c600f906c95d0c2ab2e300c24349c22aa4f71e48fcd2d3d5205f6e37a7","last_reissued_at":"2026-07-05T11:03:59.076940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:59.076940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaqi Wang, Jiazi Bu, Pan Zhang, Pengyang Ling, Tong Wu, Xiaoyi Dong, Yuhang Cao, Yuhang Zang, Yujie Zhou","submitted_at":"2025-04-08T17:30:40Z","abstract_excerpt":"Text-to-image (T2I) diffusion/flow models have drawn considerable attention recently due to their remarkable ability to deliver flexible visual creations. Still, high-resolution image synthesis presents formidable challenges due to the scarcity and complexity of high-resolution content. Recent approaches have investigated training-free strategies to enable high-resolution image synthesis with pre-trained models. However, these techniques often struggle with generating high-quality visuals and tend to exhibit artifacts or low-fidelity details, as they typically rely solely on the endpoint of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06232","kind":"arxiv","version":2},"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/2504.06232/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":"2504.06232","created_at":"2026-07-05T11:03:59.076996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.06232v2","created_at":"2026-07-05T11:03:59.076996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06232","created_at":"2026-07-05T11:03:59.076996+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPXYNRQA7EDM","created_at":"2026-07-05T11:03:59.076996+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPXYNRQA7EDMSXIM","created_at":"2026-07-05T11:03:59.076996+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPXYNRQA","created_at":"2026-07-05T11:03:59.076996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06828","citing_title":"AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01636","citing_title":"Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22668","citing_title":"SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15908","citing_title":"RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20147","citing_title":"PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Dataset","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12013","citing_title":"L2P: Unlocking Latent Potential for Pixel Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10045","citing_title":"ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPXYNRQA7EDMSXIMFKZOGAGCIN","json":"https://pith.science/pith/GPXYNRQA7EDMSXIMFKZOGAGCIN.json","graph_json":"https://pith.science/api/pith-number/GPXYNRQA7EDMSXIMFKZOGAGCIN/graph.json","events_json":"https://pith.science/api/pith-number/GPXYNRQA7EDMSXIMFKZOGAGCIN/events.json","paper":"https://pith.science/paper/GPXYNRQA"},"agent_actions":{"view_html":"https://pith.science/pith/GPXYNRQA7EDMSXIMFKZOGAGCIN","download_json":"https://pith.science/pith/GPXYNRQA7EDMSXIMFKZOGAGCIN.json","view_paper":"https://pith.science/paper/GPXYNRQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.06232&json=true","fetch_graph":"https://pith.science/api/pith-number/GPXYNRQA7EDMSXIMFKZOGAGCIN/graph.json","fetch_events":"https://pith.science/api/pith-number/GPXYNRQA7EDMSXIMFKZOGAGCIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPXYNRQA7EDMSXIMFKZOGAGCIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPXYNRQA7EDMSXIMFKZOGAGCIN/action/storage_attestation","attest_author":"https://pith.science/pith/GPXYNRQA7EDMSXIMFKZOGAGCIN/action/author_attestation","sign_citation":"https://pith.science/pith/GPXYNRQA7EDMSXIMFKZOGAGCIN/action/citation_signature","submit_replication":"https://pith.science/pith/GPXYNRQA7EDMSXIMFKZOGAGCIN/action/replication_record"}},"created_at":"2026-07-05T11:03:59.076996+00:00","updated_at":"2026-07-05T11:03:59.076996+00:00"}