{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PLWW3LKEUEOSX6K6ZUZVFLBOZC","short_pith_number":"pith:PLWW3LKE","canonical_record":{"source":{"id":"2411.11505","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T12:05:27Z","cross_cats_sorted":[],"title_canon_sha256":"5eb05f8f7a8ecfb8c2b76c3635a3b201694abe54856bb0f23ea018961af38811","abstract_canon_sha256":"b580d78dc3865bf73f83a9e6cc8f7d0691ae2c993de3150373fd444677b0d73d"},"schema_version":"1.0"},"canonical_sha256":"7aed6dad44a11d2bf95ecd3352ac2ec882454aac028d0abb18e46bb98a9c771d","source":{"kind":"arxiv","id":"2411.11505","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11505","created_at":"2026-07-05T10:25:13Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11505v4","created_at":"2026-07-05T10:25:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11505","created_at":"2026-07-05T10:25:13Z"},{"alias_kind":"pith_short_12","alias_value":"PLWW3LKEUEOS","created_at":"2026-07-05T10:25:13Z"},{"alias_kind":"pith_short_16","alias_value":"PLWW3LKEUEOSX6K6","created_at":"2026-07-05T10:25:13Z"},{"alias_kind":"pith_short_8","alias_value":"PLWW3LKE","created_at":"2026-07-05T10:25:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PLWW3LKEUEOSX6K6ZUZVFLBOZC","target":"record","payload":{"canonical_record":{"source":{"id":"2411.11505","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T12:05:27Z","cross_cats_sorted":[],"title_canon_sha256":"5eb05f8f7a8ecfb8c2b76c3635a3b201694abe54856bb0f23ea018961af38811","abstract_canon_sha256":"b580d78dc3865bf73f83a9e6cc8f7d0691ae2c993de3150373fd444677b0d73d"},"schema_version":"1.0"},"canonical_sha256":"7aed6dad44a11d2bf95ecd3352ac2ec882454aac028d0abb18e46bb98a9c771d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:13.921998Z","signature_b64":"xuRoXd43ZMuYZaVxmS4Oy2sGQRHfxnoEdlEYd0elLiKLtsD4nVnMI9iFxvbyX2LKyH5EW2doeZZusVi9qBasAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7aed6dad44a11d2bf95ecd3352ac2ec882454aac028d0abb18e46bb98a9c771d","last_reissued_at":"2026-07-05T10:25:13.921102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:13.921102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.11505","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:25:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0gdftOtSTCIZ/RECZJYKmGnNp1NhhcqxDnvcJ0Q+FKiMrLScGtpzFptMUINQmh6BzDxY1uVsZK/ADl+RJX5uCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:19:31.921817Z"},"content_sha256":"8170619123dfcd772261a516470af6d363875f649f0e11a4af15ada964d24d84","schema_version":"1.0","event_id":"sha256:8170619123dfcd772261a516470af6d363875f649f0e11a4af15ada964d24d84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PLWW3LKEUEOSX6K6ZUZVFLBOZC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LaVin-DiT: Large Vision Diffusion Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changhu Wang, Dongdong Yu, Mingming Gong, Runnan Chen, Tongliang Liu, Xiaobo Xia, Zhaoqing Wang","submitted_at":"2024-11-18T12:05:27Z","abstract_excerpt":"This paper presents the Large Vision Diffusion Transformer (LaVin-DiT), a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework. Unlike existing large vision models directly adapted from natural language processing architectures, which rely on less efficient autoregressive techniques and disrupt spatial relationships essential for vision data, LaVin-DiT introduces key innovations to optimize generative performance for vision tasks. First, to address the high dimensionality of visual data, we incorporate a spatial-temporal variational a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11505","kind":"arxiv","version":4},"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/2411.11505/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":"2026-07-05T10:25:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"16tk6ebFCzoaXix2evpPqEBL+cedS28cD0imsvW6IoDf4QZc1n1/eLJLOxJJiXVV1UxxLmabGho0yMkEdnMdCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:19:31.922186Z"},"content_sha256":"ca202788da1fc04a95bc9a0c6ac90c65cd26510dce14af73645658c7a709d32a","schema_version":"1.0","event_id":"sha256:ca202788da1fc04a95bc9a0c6ac90c65cd26510dce14af73645658c7a709d32a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PLWW3LKEUEOSX6K6ZUZVFLBOZC/bundle.json","state_url":"https://pith.science/pith/PLWW3LKEUEOSX6K6ZUZVFLBOZC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PLWW3LKEUEOSX6K6ZUZVFLBOZC/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":"2026-07-07T12:19:31Z","links":{"resolver":"https://pith.science/pith/PLWW3LKEUEOSX6K6ZUZVFLBOZC","bundle":"https://pith.science/pith/PLWW3LKEUEOSX6K6ZUZVFLBOZC/bundle.json","state":"https://pith.science/pith/PLWW3LKEUEOSX6K6ZUZVFLBOZC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PLWW3LKEUEOSX6K6ZUZVFLBOZC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PLWW3LKEUEOSX6K6ZUZVFLBOZC","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":"b580d78dc3865bf73f83a9e6cc8f7d0691ae2c993de3150373fd444677b0d73d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T12:05:27Z","title_canon_sha256":"5eb05f8f7a8ecfb8c2b76c3635a3b201694abe54856bb0f23ea018961af38811"},"schema_version":"1.0","source":{"id":"2411.11505","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11505","created_at":"2026-07-05T10:25:13Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11505v4","created_at":"2026-07-05T10:25:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11505","created_at":"2026-07-05T10:25:13Z"},{"alias_kind":"pith_short_12","alias_value":"PLWW3LKEUEOS","created_at":"2026-07-05T10:25:13Z"},{"alias_kind":"pith_short_16","alias_value":"PLWW3LKEUEOSX6K6","created_at":"2026-07-05T10:25:13Z"},{"alias_kind":"pith_short_8","alias_value":"PLWW3LKE","created_at":"2026-07-05T10:25:13Z"}],"graph_snapshots":[{"event_id":"sha256:ca202788da1fc04a95bc9a0c6ac90c65cd26510dce14af73645658c7a709d32a","target":"graph","created_at":"2026-07-05T10:25:13Z","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/2411.11505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents the Large Vision Diffusion Transformer (LaVin-DiT), a scalable and unified foundation model designed to tackle over 20 computer vision tasks in a generative framework. Unlike existing large vision models directly adapted from natural language processing architectures, which rely on less efficient autoregressive techniques and disrupt spatial relationships essential for vision data, LaVin-DiT introduces key innovations to optimize generative performance for vision tasks. First, to address the high dimensionality of visual data, we incorporate a spatial-temporal variational a","authors_text":"Changhu Wang, Dongdong Yu, Mingming Gong, Runnan Chen, Tongliang Liu, Xiaobo Xia, Zhaoqing Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T12:05:27Z","title":"LaVin-DiT: Large Vision Diffusion Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11505","kind":"arxiv","version":4},"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":"sha256:8170619123dfcd772261a516470af6d363875f649f0e11a4af15ada964d24d84","target":"record","created_at":"2026-07-05T10:25:13Z","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":"b580d78dc3865bf73f83a9e6cc8f7d0691ae2c993de3150373fd444677b0d73d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T12:05:27Z","title_canon_sha256":"5eb05f8f7a8ecfb8c2b76c3635a3b201694abe54856bb0f23ea018961af38811"},"schema_version":"1.0","source":{"id":"2411.11505","kind":"arxiv","version":4}},"canonical_sha256":"7aed6dad44a11d2bf95ecd3352ac2ec882454aac028d0abb18e46bb98a9c771d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7aed6dad44a11d2bf95ecd3352ac2ec882454aac028d0abb18e46bb98a9c771d","first_computed_at":"2026-07-05T10:25:13.921102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:13.921102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xuRoXd43ZMuYZaVxmS4Oy2sGQRHfxnoEdlEYd0elLiKLtsD4nVnMI9iFxvbyX2LKyH5EW2doeZZusVi9qBasAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:13.921998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.11505","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8170619123dfcd772261a516470af6d363875f649f0e11a4af15ada964d24d84","sha256:ca202788da1fc04a95bc9a0c6ac90c65cd26510dce14af73645658c7a709d32a"],"state_sha256":"025c7250cbae91eb16cbcc5b8296eead037fc01732f879e6579a9def0945d43a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ychy9Uf3Qab6bB5KepsRpEiTe+v5BHWJbFfRl/yjoJLFSUetvs135pnRC9vbZgqWlMFcm+xfHw7jiAe0KqoYDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:19:31.924057Z","bundle_sha256":"5f50cf50d1440bb3872a8749f87bed821b0c0e33aa88a76f278b3135de6ba16d"}}