{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UOA26XFL5ZAYCP4KSHCRPJEQMR","short_pith_number":"pith:UOA26XFL","schema_version":"1.0","canonical_sha256":"a381af5cabee41813f8a91c517a49064781e90cf0ccfb354387109b5903c11df","source":{"kind":"arxiv","id":"2606.30934","version":1},"attestation_state":"computed","paper":{"title":"Quality-Aware Modulation for Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kevin Cheung, Luke Budny, Yuhong Guo","submitted_at":"2026-06-29T21:38:05Z","abstract_excerpt":"Modern text-to-image diffusion models, such as diffusion transformers (DiT), rely on timestep or prompt embeddings to modulate the strength of the denoising process in each timestep. While this modulation communicates the current noise level, it does not provide any quality-aware information, which can lead to generated images that are unaligned, visually inconsistent, and lacking in fidelity. In this paper, we propose the Quality Representation Module (QRM), a lightweight transformer module that learns a quality-aware representation based on existing model inputs, and produces a set of vector"},"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":"2606.30934","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T21:38:05Z","cross_cats_sorted":[],"title_canon_sha256":"8bb91a95db4729684b854e2366fd44c6d443b72417e729f82787806e26f88266","abstract_canon_sha256":"5b390123e683a96a59adb213ac47b162baf54e147ec7d3e2f813152eee63ea57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:22.033684Z","signature_b64":"/Lv5VSJTNimwE6LxeYDCswz+rBGocOWqP+VkgCSYb/taGYYzLxVTyu8GLNByfIB5Vw5H2W4j+ZnPgvncwgCfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a381af5cabee41813f8a91c517a49064781e90cf0ccfb354387109b5903c11df","last_reissued_at":"2026-07-01T00:17:22.033293Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:22.033293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quality-Aware Modulation for Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kevin Cheung, Luke Budny, Yuhong Guo","submitted_at":"2026-06-29T21:38:05Z","abstract_excerpt":"Modern text-to-image diffusion models, such as diffusion transformers (DiT), rely on timestep or prompt embeddings to modulate the strength of the denoising process in each timestep. While this modulation communicates the current noise level, it does not provide any quality-aware information, which can lead to generated images that are unaligned, visually inconsistent, and lacking in fidelity. In this paper, we propose the Quality Representation Module (QRM), a lightweight transformer module that learns a quality-aware representation based on existing model inputs, and produces a set of vector"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30934","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/2606.30934/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":"2606.30934","created_at":"2026-07-01T00:17:22.033357+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30934v1","created_at":"2026-07-01T00:17:22.033357+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30934","created_at":"2026-07-01T00:17:22.033357+00:00"},{"alias_kind":"pith_short_12","alias_value":"UOA26XFL5ZAY","created_at":"2026-07-01T00:17:22.033357+00:00"},{"alias_kind":"pith_short_16","alias_value":"UOA26XFL5ZAYCP4K","created_at":"2026-07-01T00:17:22.033357+00:00"},{"alias_kind":"pith_short_8","alias_value":"UOA26XFL","created_at":"2026-07-01T00:17:22.033357+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UOA26XFL5ZAYCP4KSHCRPJEQMR","json":"https://pith.science/pith/UOA26XFL5ZAYCP4KSHCRPJEQMR.json","graph_json":"https://pith.science/api/pith-number/UOA26XFL5ZAYCP4KSHCRPJEQMR/graph.json","events_json":"https://pith.science/api/pith-number/UOA26XFL5ZAYCP4KSHCRPJEQMR/events.json","paper":"https://pith.science/paper/UOA26XFL"},"agent_actions":{"view_html":"https://pith.science/pith/UOA26XFL5ZAYCP4KSHCRPJEQMR","download_json":"https://pith.science/pith/UOA26XFL5ZAYCP4KSHCRPJEQMR.json","view_paper":"https://pith.science/paper/UOA26XFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30934&json=true","fetch_graph":"https://pith.science/api/pith-number/UOA26XFL5ZAYCP4KSHCRPJEQMR/graph.json","fetch_events":"https://pith.science/api/pith-number/UOA26XFL5ZAYCP4KSHCRPJEQMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UOA26XFL5ZAYCP4KSHCRPJEQMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UOA26XFL5ZAYCP4KSHCRPJEQMR/action/storage_attestation","attest_author":"https://pith.science/pith/UOA26XFL5ZAYCP4KSHCRPJEQMR/action/author_attestation","sign_citation":"https://pith.science/pith/UOA26XFL5ZAYCP4KSHCRPJEQMR/action/citation_signature","submit_replication":"https://pith.science/pith/UOA26XFL5ZAYCP4KSHCRPJEQMR/action/replication_record"}},"created_at":"2026-07-01T00:17:22.033357+00:00","updated_at":"2026-07-01T00:17:22.033357+00:00"}