{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VB75755X7QCCZ67VW4TYBHUSKR","short_pith_number":"pith:VB75755X","schema_version":"1.0","canonical_sha256":"a87fdff7b7fc042cfbf5b727809e92544f05053a2658da00ef6e380cfcae936c","source":{"kind":"arxiv","id":"2312.04557","version":2},"attestation_state":"computed","paper":{"title":"GenTron: Diffusion Transformers for Image and Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Animesh Sinha, Jiawei Ren, Juan-Manuel Perez-Rua, Mengmeng Xu, Ping Luo, Sen He, Shoufa Chen, Tao Xiang, Yanping Xie, Yuren Cong","submitted_at":"2023-12-07T18:59:30Z","abstract_excerpt":"In this study, we explore Transformer-based diffusion models for image and video generation. Despite the dominance of Transformer architectures in various fields due to their flexibility and scalability, the visual generative domain primarily utilizes CNN-based U-Net architectures, particularly in diffusion-based models. We introduce GenTron, a family of Generative models employing Transformer-based diffusion, to address this gap. Our initial step was to adapt Diffusion Transformers (DiTs) from class to text conditioning, a process involving thorough empirical exploration of the conditioning m"},"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":"2312.04557","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-07T18:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"0fcb54d8359746fd4158dde5535363aec0891015a43fd861e4b655bc9c9a6235","abstract_canon_sha256":"e75bbf44aa1e593e7aab7278cd162325c98f0e3cf51a55a6796a668385299284"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:16.430652Z","signature_b64":"u0NfYSCLqvwAdKRRZrENRf3FJynlEkRkW1eExffFnaips+A3Ol4Tnh6DfJvmzoZZv/uBrBwOB+3N6F9tzNL5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a87fdff7b7fc042cfbf5b727809e92544f05053a2658da00ef6e380cfcae936c","last_reissued_at":"2026-07-05T08:26:16.430181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:16.430181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenTron: Diffusion Transformers for Image and Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Animesh Sinha, Jiawei Ren, Juan-Manuel Perez-Rua, Mengmeng Xu, Ping Luo, Sen He, Shoufa Chen, Tao Xiang, Yanping Xie, Yuren Cong","submitted_at":"2023-12-07T18:59:30Z","abstract_excerpt":"In this study, we explore Transformer-based diffusion models for image and video generation. Despite the dominance of Transformer architectures in various fields due to their flexibility and scalability, the visual generative domain primarily utilizes CNN-based U-Net architectures, particularly in diffusion-based models. We introduce GenTron, a family of Generative models employing Transformer-based diffusion, to address this gap. Our initial step was to adapt Diffusion Transformers (DiTs) from class to text conditioning, a process involving thorough empirical exploration of the conditioning m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04557","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/2312.04557/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":"2312.04557","created_at":"2026-07-05T08:26:16.430237+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04557v2","created_at":"2026-07-05T08:26:16.430237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04557","created_at":"2026-07-05T08:26:16.430237+00:00"},{"alias_kind":"pith_short_12","alias_value":"VB75755X7QCC","created_at":"2026-07-05T08:26:16.430237+00:00"},{"alias_kind":"pith_short_16","alias_value":"VB75755X7QCCZ67V","created_at":"2026-07-05T08:26:16.430237+00:00"},{"alias_kind":"pith_short_8","alias_value":"VB75755X","created_at":"2026-07-05T08:26:16.430237+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24888","citing_title":"DiffusionBench: On Holistic Evaluation of Diffusion Transformers","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":229,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR","json":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR.json","graph_json":"https://pith.science/api/pith-number/VB75755X7QCCZ67VW4TYBHUSKR/graph.json","events_json":"https://pith.science/api/pith-number/VB75755X7QCCZ67VW4TYBHUSKR/events.json","paper":"https://pith.science/paper/VB75755X"},"agent_actions":{"view_html":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR","download_json":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR.json","view_paper":"https://pith.science/paper/VB75755X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04557&json=true","fetch_graph":"https://pith.science/api/pith-number/VB75755X7QCCZ67VW4TYBHUSKR/graph.json","fetch_events":"https://pith.science/api/pith-number/VB75755X7QCCZ67VW4TYBHUSKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR/action/storage_attestation","attest_author":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR/action/author_attestation","sign_citation":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR/action/citation_signature","submit_replication":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR/action/replication_record"}},"created_at":"2026-07-05T08:26:16.430237+00:00","updated_at":"2026-07-05T08:26:16.430237+00:00"}