{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MB76UZPDHZY5LY35HAM44MNYAW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b46783fc3a4f26e70a7a47ecce9c633a50d494207c1fb48f1bb1727e3fae8138","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T17:55:43Z","title_canon_sha256":"435f966603a9007d3fbaf1b4855baca2a35e4911efa64ef5cd60072527c5e4ad"},"schema_version":"1.0","source":{"id":"2404.09976","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09976","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09976v1","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09976","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"MB76UZPDHZY5","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_16","alias_value":"MB76UZPDHZY5LY35","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_8","alias_value":"MB76UZPD","created_at":"2026-07-05T08:08:13Z"}],"graph_snapshots":[{"event_id":"sha256:05f07f371111db16913e8d4372cda8d136a1c302774f63686fe7f068e4173705","target":"graph","created_at":"2026-07-05T08:08:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.09976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jeya Maria Jose Valanarasu, Nithin Gopalakrishnan Nair, Vishal M. Patel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T17:55:43Z","title":"Diffscaler: Enhancing the Generative Prowess of Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09976","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:36661c527ad797ee5b28ff77c0ed135a3b2491f486a3079ce0a9fe4d3e49dea3","target":"record","created_at":"2026-07-05T08:08:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b46783fc3a4f26e70a7a47ecce9c633a50d494207c1fb48f1bb1727e3fae8138","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T17:55:43Z","title_canon_sha256":"435f966603a9007d3fbaf1b4855baca2a35e4911efa64ef5cd60072527c5e4ad"},"schema_version":"1.0","source":{"id":"2404.09976","kind":"arxiv","version":1}},"canonical_sha256":"607fea65e33e71d5e37d3819ce31b8059518519b02f0bc95ee13db06f58849f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"607fea65e33e71d5e37d3819ce31b8059518519b02f0bc95ee13db06f58849f5","first_computed_at":"2026-07-05T08:08:13.686508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:13.686508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kRub1b9gsl22j1ZwYQVhlqHoRr3Nl7jufzSlKYnN2sgbXiHDo9sSrn6WVV9/uMycyDNaMfiw/b1+wHbu+tmMAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:13.686904Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09976","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36661c527ad797ee5b28ff77c0ed135a3b2491f486a3079ce0a9fe4d3e49dea3","sha256:05f07f371111db16913e8d4372cda8d136a1c302774f63686fe7f068e4173705"],"state_sha256":"3e994395285f63b1ff1072177ae58352cb6cfae647e0ad22c362e057ae2fa59c"}