{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SP52SAE7ZO2S2KFJ4ZAZIAQIOG","short_pith_number":"pith:SP52SAE7","schema_version":"1.0","canonical_sha256":"93fba9009fcbb52d28a9e64194020871bff1c64062bc73f06700b348779f6571","source":{"kind":"arxiv","id":"2412.09626","version":2},"attestation_state":"computed","paper":{"title":"FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hangjie Yuan, Haonan Qiu, Ruihang Chu, Shiwei Zhang, Xiang Wang, Yingya Zhang, Yujie Wei, Ziwei Liu","submitted_at":"2024-12-12T18:59:59Z","abstract_excerpt":"Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resources, hampering their ability to generate high-fidelity images or videos at higher resolutions. Recent efforts have explored tuning-free strategies to exhibit the untapped potential higher-resolution visual generation of pre-trained models. However, these methods are still prone to producing low-quality visual content with repetitive patterns. The key obstacle lies in the inevitable increase in high-frequency informa"},"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":"2412.09626","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"4e0019d54214c29a65bbf6f14564bfe90e3e16f793b0b7c9a13cb1634fcb731c","abstract_canon_sha256":"638122a28f0343696a7ee20c5cb389250e5a2cd618165712eda8d143d102e5c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:31.150077Z","signature_b64":"kG8LcVp2Yrd93+oh/606KQ3tSIwO4g4En61OPxbZpI+RvkjwWlYMvnHG5a2QI2bPalV24OLdcQcXqotpAkg4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93fba9009fcbb52d28a9e64194020871bff1c64062bc73f06700b348779f6571","last_reissued_at":"2026-07-05T11:35:31.149612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:31.149612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hangjie Yuan, Haonan Qiu, Ruihang Chu, Shiwei Zhang, Xiang Wang, Yingya Zhang, Yujie Wei, Ziwei Liu","submitted_at":"2024-12-12T18:59:59Z","abstract_excerpt":"Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resources, hampering their ability to generate high-fidelity images or videos at higher resolutions. Recent efforts have explored tuning-free strategies to exhibit the untapped potential higher-resolution visual generation of pre-trained models. However, these methods are still prone to producing low-quality visual content with repetitive patterns. The key obstacle lies in the inevitable increase in high-frequency informa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09626","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/2412.09626/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":"2412.09626","created_at":"2026-07-05T11:35:31.149662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09626v2","created_at":"2026-07-05T11:35:31.149662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09626","created_at":"2026-07-05T11:35:31.149662+00:00"},{"alias_kind":"pith_short_12","alias_value":"SP52SAE7ZO2S","created_at":"2026-07-05T11:35:31.149662+00:00"},{"alias_kind":"pith_short_16","alias_value":"SP52SAE7ZO2S2KFJ","created_at":"2026-07-05T11:35:31.149662+00:00"},{"alias_kind":"pith_short_8","alias_value":"SP52SAE7","created_at":"2026-07-05T11:35:31.149662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.02307","citing_title":"NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generation","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SP52SAE7ZO2S2KFJ4ZAZIAQIOG","json":"https://pith.science/pith/SP52SAE7ZO2S2KFJ4ZAZIAQIOG.json","graph_json":"https://pith.science/api/pith-number/SP52SAE7ZO2S2KFJ4ZAZIAQIOG/graph.json","events_json":"https://pith.science/api/pith-number/SP52SAE7ZO2S2KFJ4ZAZIAQIOG/events.json","paper":"https://pith.science/paper/SP52SAE7"},"agent_actions":{"view_html":"https://pith.science/pith/SP52SAE7ZO2S2KFJ4ZAZIAQIOG","download_json":"https://pith.science/pith/SP52SAE7ZO2S2KFJ4ZAZIAQIOG.json","view_paper":"https://pith.science/paper/SP52SAE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09626&json=true","fetch_graph":"https://pith.science/api/pith-number/SP52SAE7ZO2S2KFJ4ZAZIAQIOG/graph.json","fetch_events":"https://pith.science/api/pith-number/SP52SAE7ZO2S2KFJ4ZAZIAQIOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SP52SAE7ZO2S2KFJ4ZAZIAQIOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SP52SAE7ZO2S2KFJ4ZAZIAQIOG/action/storage_attestation","attest_author":"https://pith.science/pith/SP52SAE7ZO2S2KFJ4ZAZIAQIOG/action/author_attestation","sign_citation":"https://pith.science/pith/SP52SAE7ZO2S2KFJ4ZAZIAQIOG/action/citation_signature","submit_replication":"https://pith.science/pith/SP52SAE7ZO2S2KFJ4ZAZIAQIOG/action/replication_record"}},"created_at":"2026-07-05T11:35:31.149662+00:00","updated_at":"2026-07-05T11:35:31.149662+00:00"}