{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4UONZEG6VDY6OO3DCJ5IMSNGPB","short_pith_number":"pith:4UONZEG6","canonical_record":{"source":{"id":"2502.04847","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T11:36:36Z","cross_cats_sorted":[],"title_canon_sha256":"a872184bf32d08e105c98a720ed93036d23ce4c7e818a08a0003692f13618a56","abstract_canon_sha256":"68eca88dcc3bad3ff0e1176e2bf159aa8f09b894259d23a2f7a01d81c948368b"},"schema_version":"1.0"},"canonical_sha256":"e51cdc90dea8f1e73b63127a8649a678469601edfcc227c80f2f4214fe7174b1","source":{"kind":"arxiv","id":"2502.04847","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04847","created_at":"2026-07-05T11:48:00Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04847v5","created_at":"2026-07-05T11:48:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04847","created_at":"2026-07-05T11:48:00Z"},{"alias_kind":"pith_short_12","alias_value":"4UONZEG6VDY6","created_at":"2026-07-05T11:48:00Z"},{"alias_kind":"pith_short_16","alias_value":"4UONZEG6VDY6OO3D","created_at":"2026-07-05T11:48:00Z"},{"alias_kind":"pith_short_8","alias_value":"4UONZEG6","created_at":"2026-07-05T11:48:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4UONZEG6VDY6OO3DCJ5IMSNGPB","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04847","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T11:36:36Z","cross_cats_sorted":[],"title_canon_sha256":"a872184bf32d08e105c98a720ed93036d23ce4c7e818a08a0003692f13618a56","abstract_canon_sha256":"68eca88dcc3bad3ff0e1176e2bf159aa8f09b894259d23a2f7a01d81c948368b"},"schema_version":"1.0"},"canonical_sha256":"e51cdc90dea8f1e73b63127a8649a678469601edfcc227c80f2f4214fe7174b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:00.524684Z","signature_b64":"Z6LUCJ3wBXJ8YXiqBhTJeVyPdo2QWKwex5jGBLDVNh49YZsItm/Qfba2N7BJRzTCVnYd1EIlyYGkaTwtm6gzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e51cdc90dea8f1e73b63127a8649a678469601edfcc227c80f2f4214fe7174b1","last_reissued_at":"2026-07-05T11:48:00.524100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:00.524100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04847","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:48:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YJENcHSo0fabI+Xx47J7s6xrKRVlQdCWlMmj78EBvSXo8qW36ehzJD6G0YlybD8MGNFV5gTmNuu3tjOEfIVeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:03:12.130343Z"},"content_sha256":"a2dce408335723028085c37362591de293287767488ccb259daeda1abe6eaa79","schema_version":"1.0","event_id":"sha256:a2dce408335723028085c37362591de293287767488ccb259daeda1abe6eaa79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4UONZEG6VDY6OO3DCJ5IMSNGPB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyue Peng, Chen Zhang, Jianke Zhu, Pan Xie, Qijun Gan, Xiang Yin, Yi Ren, Zehuan Yuan, Zhenhui Ye","submitted_at":"2025-02-07T11:36:36Z","abstract_excerpt":"Human motion video generation has advanced significantly, while existing methods still struggle with accurately rendering detailed body parts like hands and faces, especially in long sequences and intricate motions. Current approaches also rely on fixed resolution and struggle to maintain visual consistency. To address these limitations, we propose HumanDiT, a pose-guided Diffusion Transformer (DiT)-based framework trained on a large and wild dataset containing 14,000 hours of high-quality video to produce high-fidelity videos with fine-grained body rendering. Specifically, (i) HumanDiT, built"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04847","kind":"arxiv","version":5},"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/2502.04847/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":"2026-07-05T11:48:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aQTeZqSvoI/AAFgtY0MEKeCn124scycA7vDL7MeeaSNN1GkL4uH3v2+AR7aueoxz7SgksTM12sJ8GZPeYfLDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:03:12.130814Z"},"content_sha256":"597f230fade5bb82b3bd4cd69f1feb89a15e023896e03c980277eb968ad80613","schema_version":"1.0","event_id":"sha256:597f230fade5bb82b3bd4cd69f1feb89a15e023896e03c980277eb968ad80613"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4UONZEG6VDY6OO3DCJ5IMSNGPB/bundle.json","state_url":"https://pith.science/pith/4UONZEG6VDY6OO3DCJ5IMSNGPB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4UONZEG6VDY6OO3DCJ5IMSNGPB/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":"2026-08-05T03:03:12Z","links":{"resolver":"https://pith.science/pith/4UONZEG6VDY6OO3DCJ5IMSNGPB","bundle":"https://pith.science/pith/4UONZEG6VDY6OO3DCJ5IMSNGPB/bundle.json","state":"https://pith.science/pith/4UONZEG6VDY6OO3DCJ5IMSNGPB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4UONZEG6VDY6OO3DCJ5IMSNGPB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4UONZEG6VDY6OO3DCJ5IMSNGPB","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":"68eca88dcc3bad3ff0e1176e2bf159aa8f09b894259d23a2f7a01d81c948368b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T11:36:36Z","title_canon_sha256":"a872184bf32d08e105c98a720ed93036d23ce4c7e818a08a0003692f13618a56"},"schema_version":"1.0","source":{"id":"2502.04847","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04847","created_at":"2026-07-05T11:48:00Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04847v5","created_at":"2026-07-05T11:48:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04847","created_at":"2026-07-05T11:48:00Z"},{"alias_kind":"pith_short_12","alias_value":"4UONZEG6VDY6","created_at":"2026-07-05T11:48:00Z"},{"alias_kind":"pith_short_16","alias_value":"4UONZEG6VDY6OO3D","created_at":"2026-07-05T11:48:00Z"},{"alias_kind":"pith_short_8","alias_value":"4UONZEG6","created_at":"2026-07-05T11:48:00Z"}],"graph_snapshots":[{"event_id":"sha256:597f230fade5bb82b3bd4cd69f1feb89a15e023896e03c980277eb968ad80613","target":"graph","created_at":"2026-07-05T11:48:00Z","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/2502.04847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human motion video generation has advanced significantly, while existing methods still struggle with accurately rendering detailed body parts like hands and faces, especially in long sequences and intricate motions. Current approaches also rely on fixed resolution and struggle to maintain visual consistency. To address these limitations, we propose HumanDiT, a pose-guided Diffusion Transformer (DiT)-based framework trained on a large and wild dataset containing 14,000 hours of high-quality video to produce high-fidelity videos with fine-grained body rendering. Specifically, (i) HumanDiT, built","authors_text":"Bingyue Peng, Chen Zhang, Jianke Zhu, Pan Xie, Qijun Gan, Xiang Yin, Yi Ren, Zehuan Yuan, Zhenhui Ye","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T11:36:36Z","title":"HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04847","kind":"arxiv","version":5},"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:a2dce408335723028085c37362591de293287767488ccb259daeda1abe6eaa79","target":"record","created_at":"2026-07-05T11:48:00Z","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":"68eca88dcc3bad3ff0e1176e2bf159aa8f09b894259d23a2f7a01d81c948368b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T11:36:36Z","title_canon_sha256":"a872184bf32d08e105c98a720ed93036d23ce4c7e818a08a0003692f13618a56"},"schema_version":"1.0","source":{"id":"2502.04847","kind":"arxiv","version":5}},"canonical_sha256":"e51cdc90dea8f1e73b63127a8649a678469601edfcc227c80f2f4214fe7174b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e51cdc90dea8f1e73b63127a8649a678469601edfcc227c80f2f4214fe7174b1","first_computed_at":"2026-07-05T11:48:00.524100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:00.524100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z6LUCJ3wBXJ8YXiqBhTJeVyPdo2QWKwex5jGBLDVNh49YZsItm/Qfba2N7BJRzTCVnYd1EIlyYGkaTwtm6gzBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:00.524684Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04847","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2dce408335723028085c37362591de293287767488ccb259daeda1abe6eaa79","sha256:597f230fade5bb82b3bd4cd69f1feb89a15e023896e03c980277eb968ad80613"],"state_sha256":"8434f77478495d6d7bddf8f5616bf24426bfd267ac05c6d49acc4e35a18d2ede"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rRofzeU5t0+tiZGa6cmdQ4d351ll394Jva83hqEAloCQflBIJm1/8Q6jKVzd4+Z7fgYRgIwTeohrUxu3ROteAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:03:12.135073Z","bundle_sha256":"3e8ec2f9bcd03de3dd4cbe57f9b64e8d6413a0aada1f5b8164505144211999c0"}}