{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MB76UZPDHZY5LY35HAM44MNYAW","short_pith_number":"pith:MB76UZPD","schema_version":"1.0","canonical_sha256":"607fea65e33e71d5e37d3819ce31b8059518519b02f0bc95ee13db06f58849f5","source":{"kind":"arxiv","id":"2404.09976","version":1},"attestation_state":"computed","paper":{"title":"Diffscaler: Enhancing the Generative Prowess of Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeya Maria Jose Valanarasu, Nithin Gopalakrishnan Nair, Vishal M. Patel","submitted_at":"2024-04-15T17:55:43Z","abstract_excerpt":"Recently, diffusion transformers have gained wide attention with its excellent performance in text-to-image and text-to-vidoe models, emphasizing the need for transformers as backbone for diffusion models. Transformer-based models have shown better generalization capability compared to CNN-based models for general vision tasks. However, much less has been explored in the existing literature regarding the capabilities of transformer-based diffusion backbones and expanding their generative prowess to other datasets. This paper focuses on enabling a single pre-trained diffusion transformer model "},"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":"2404.09976","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T17:55:43Z","cross_cats_sorted":[],"title_canon_sha256":"435f966603a9007d3fbaf1b4855baca2a35e4911efa64ef5cd60072527c5e4ad","abstract_canon_sha256":"b46783fc3a4f26e70a7a47ecce9c633a50d494207c1fb48f1bb1727e3fae8138"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:13.686904Z","signature_b64":"kRub1b9gsl22j1ZwYQVhlqHoRr3Nl7jufzSlKYnN2sgbXiHDo9sSrn6WVV9/uMycyDNaMfiw/b1+wHbu+tmMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"607fea65e33e71d5e37d3819ce31b8059518519b02f0bc95ee13db06f58849f5","last_reissued_at":"2026-07-05T08:08:13.686508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:13.686508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffscaler: Enhancing the Generative Prowess of Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeya Maria Jose Valanarasu, Nithin Gopalakrishnan Nair, Vishal M. Patel","submitted_at":"2024-04-15T17:55:43Z","abstract_excerpt":"Recently, diffusion transformers have gained wide attention with its excellent performance in text-to-image and text-to-vidoe models, emphasizing the need for transformers as backbone for diffusion models. Transformer-based models have shown better generalization capability compared to CNN-based models for general vision tasks. However, much less has been explored in the existing literature regarding the capabilities of transformer-based diffusion backbones and expanding their generative prowess to other datasets. This paper focuses on enabling a single pre-trained diffusion transformer model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09976","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/2404.09976/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":"2404.09976","created_at":"2026-07-05T08:08:13.686571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09976v1","created_at":"2026-07-05T08:08:13.686571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09976","created_at":"2026-07-05T08:08:13.686571+00:00"},{"alias_kind":"pith_short_12","alias_value":"MB76UZPDHZY5","created_at":"2026-07-05T08:08:13.686571+00:00"},{"alias_kind":"pith_short_16","alias_value":"MB76UZPDHZY5LY35","created_at":"2026-07-05T08:08:13.686571+00:00"},{"alias_kind":"pith_short_8","alias_value":"MB76UZPD","created_at":"2026-07-05T08:08:13.686571+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02713","citing_title":"UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MB76UZPDHZY5LY35HAM44MNYAW","json":"https://pith.science/pith/MB76UZPDHZY5LY35HAM44MNYAW.json","graph_json":"https://pith.science/api/pith-number/MB76UZPDHZY5LY35HAM44MNYAW/graph.json","events_json":"https://pith.science/api/pith-number/MB76UZPDHZY5LY35HAM44MNYAW/events.json","paper":"https://pith.science/paper/MB76UZPD"},"agent_actions":{"view_html":"https://pith.science/pith/MB76UZPDHZY5LY35HAM44MNYAW","download_json":"https://pith.science/pith/MB76UZPDHZY5LY35HAM44MNYAW.json","view_paper":"https://pith.science/paper/MB76UZPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09976&json=true","fetch_graph":"https://pith.science/api/pith-number/MB76UZPDHZY5LY35HAM44MNYAW/graph.json","fetch_events":"https://pith.science/api/pith-number/MB76UZPDHZY5LY35HAM44MNYAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MB76UZPDHZY5LY35HAM44MNYAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MB76UZPDHZY5LY35HAM44MNYAW/action/storage_attestation","attest_author":"https://pith.science/pith/MB76UZPDHZY5LY35HAM44MNYAW/action/author_attestation","sign_citation":"https://pith.science/pith/MB76UZPDHZY5LY35HAM44MNYAW/action/citation_signature","submit_replication":"https://pith.science/pith/MB76UZPDHZY5LY35HAM44MNYAW/action/replication_record"}},"created_at":"2026-07-05T08:08:13.686571+00:00","updated_at":"2026-07-05T08:08:13.686571+00:00"}