{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VB75755X7QCCZ67VW4TYBHUSKR","short_pith_number":"pith:VB75755X","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"},"canonical_sha256":"a87fdff7b7fc042cfbf5b727809e92544f05053a2658da00ef6e380cfcae936c","source":{"kind":"arxiv","id":"2312.04557","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04557","created_at":"2026-07-05T08:26:16Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04557v2","created_at":"2026-07-05T08:26:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04557","created_at":"2026-07-05T08:26:16Z"},{"alias_kind":"pith_short_12","alias_value":"VB75755X7QCC","created_at":"2026-07-05T08:26:16Z"},{"alias_kind":"pith_short_16","alias_value":"VB75755X7QCCZ67V","created_at":"2026-07-05T08:26:16Z"},{"alias_kind":"pith_short_8","alias_value":"VB75755X","created_at":"2026-07-05T08:26:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VB75755X7QCCZ67VW4TYBHUSKR","target":"record","payload":{"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"},"canonical_sha256":"a87fdff7b7fc042cfbf5b727809e92544f05053a2658da00ef6e380cfcae936c","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"},"source_kind":"arxiv","source_id":"2312.04557","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xk3MKqVxBTo4wrfIcU8B7MaBrCOg3eLEXLhXqd0OzAONks26wTzQdp4oN/Zh9xXtt5RfRasox58Agl5pru8bAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-29T07:07:32.968508Z"},"content_sha256":"17b1d3a6fb8c470bdcf2dc1a156cd60a52b484a17926304a755037afc182c494","schema_version":"1.0","event_id":"sha256:17b1d3a6fb8c470bdcf2dc1a156cd60a52b484a17926304a755037afc182c494"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VB75755X7QCCZ67VW4TYBHUSKR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5IwFnr99jGZPYkrf7bNYZo6TaNWO+X7jpJVT8ukH9noQhLLe0B0pyE8JeqphMZP5cS+kWQtcXBnZSjgrrrlTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-29T07:07:32.969005Z"},"content_sha256":"762c6d85fdc7325aa678b2c46d6cf871357ceaed5b8da4d7d96c0b15cff701e0","schema_version":"1.0","event_id":"sha256:762c6d85fdc7325aa678b2c46d6cf871357ceaed5b8da4d7d96c0b15cff701e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR/bundle.json","state_url":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VB75755X7QCCZ67VW4TYBHUSKR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-29T07:07:32Z","links":{"resolver":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR","bundle":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR/bundle.json","state":"https://pith.science/pith/VB75755X7QCCZ67VW4TYBHUSKR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VB75755X7QCCZ67VW4TYBHUSKR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VB75755X7QCCZ67VW4TYBHUSKR","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":"e75bbf44aa1e593e7aab7278cd162325c98f0e3cf51a55a6796a668385299284","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-07T18:59:30Z","title_canon_sha256":"0fcb54d8359746fd4158dde5535363aec0891015a43fd861e4b655bc9c9a6235"},"schema_version":"1.0","source":{"id":"2312.04557","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04557","created_at":"2026-07-05T08:26:16Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04557v2","created_at":"2026-07-05T08:26:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04557","created_at":"2026-07-05T08:26:16Z"},{"alias_kind":"pith_short_12","alias_value":"VB75755X7QCC","created_at":"2026-07-05T08:26:16Z"},{"alias_kind":"pith_short_16","alias_value":"VB75755X7QCCZ67V","created_at":"2026-07-05T08:26:16Z"},{"alias_kind":"pith_short_8","alias_value":"VB75755X","created_at":"2026-07-05T08:26:16Z"}],"graph_snapshots":[{"event_id":"sha256:762c6d85fdc7325aa678b2c46d6cf871357ceaed5b8da4d7d96c0b15cff701e0","target":"graph","created_at":"2026-07-05T08:26:16Z","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/2312.04557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Animesh Sinha, Jiawei Ren, Juan-Manuel Perez-Rua, Mengmeng Xu, Ping Luo, Sen He, Shoufa Chen, Tao Xiang, Yanping Xie, Yuren Cong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-07T18:59:30Z","title":"GenTron: Diffusion Transformers for Image and Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04557","kind":"arxiv","version":2},"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":"sha256:17b1d3a6fb8c470bdcf2dc1a156cd60a52b484a17926304a755037afc182c494","target":"record","created_at":"2026-07-05T08:26:16Z","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":"e75bbf44aa1e593e7aab7278cd162325c98f0e3cf51a55a6796a668385299284","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-07T18:59:30Z","title_canon_sha256":"0fcb54d8359746fd4158dde5535363aec0891015a43fd861e4b655bc9c9a6235"},"schema_version":"1.0","source":{"id":"2312.04557","kind":"arxiv","version":2}},"canonical_sha256":"a87fdff7b7fc042cfbf5b727809e92544f05053a2658da00ef6e380cfcae936c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a87fdff7b7fc042cfbf5b727809e92544f05053a2658da00ef6e380cfcae936c","first_computed_at":"2026-07-05T08:26:16.430181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:16.430181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u0NfYSCLqvwAdKRRZrENRf3FJynlEkRkW1eExffFnaips+A3Ol4Tnh6DfJvmzoZZv/uBrBwOB+3N6F9tzNL5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:16.430652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.04557","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17b1d3a6fb8c470bdcf2dc1a156cd60a52b484a17926304a755037afc182c494","sha256:762c6d85fdc7325aa678b2c46d6cf871357ceaed5b8da4d7d96c0b15cff701e0"],"state_sha256":"ea3ce7d9f5b0bacdc4c19dce2499c25425701a869c9232b0e0b979a46b05b5fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"97wjlklV2oW7VCm9jUa+0tqPetq3vrGBHp7nuhQ2eYPkUwcpUjOTOrXCZd1j862k2rcWx3Nic36qreoP/qxxDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-29T07:07:32.971379Z","bundle_sha256":"7ffdbe577998bd552cb83e106ea6c16099b7f288345a8a0c530aebd2d4eb390b"}}