{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RITKXJV32EEZDCJLQ2JLYBI3NK","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":"61c11cdc41ac6330c2405d93aea12e85fc35e09dd0e9897ede33a711d986b8c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-11T14:30:34Z","title_canon_sha256":"820fdc85182d5c2699e78bdb9752309b4b54955f9c18ff397b0209c865075e78"},"schema_version":"1.0","source":{"id":"2211.06235","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06235","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06235v1","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06235","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"pith_short_12","alias_value":"RITKXJV32EEZ","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"pith_short_16","alias_value":"RITKXJV32EEZDCJL","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"pith_short_8","alias_value":"RITKXJV3","created_at":"2026-07-05T05:15:18Z"}],"graph_snapshots":[{"event_id":"sha256:a8d68623e6a162dd461de919e47060bef8b1e3b1af3a5a768308caf602af94c7","target":"graph","created_at":"2026-07-05T05:15:18Z","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/2211.06235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-driven person image generation is an emerging and challenging task in cross-modality image generation. Controllable person image generation promotes a wide range of applications such as digital human interaction and virtual try-on. However, previous methods mostly employ single-modality information as the prior condition (e.g. pose-guided person image generation), or utilize the preset words for text-driven human synthesis. Introducing a sentence composed of free words with an editable semantic pose map to describe person appearance is a more user-friendly way. In this paper, we propose H","authors_text":"Binghao Zhao, Jianxin Sun, Kaiduo Zhang, Kunbo Zhang, Muyi Sun, Tieniu Tan, Zhenan Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-11T14:30:34Z","title":"HumanDiffusion: a Coarse-to-Fine Alignment Diffusion Framework for Controllable Text-Driven Person Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06235","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":"sha256:92894121a2388274d7cecc62edd45ebacdb5548bfa0cfda3cc76bbc072524853","target":"record","created_at":"2026-07-05T05:15:18Z","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":"61c11cdc41ac6330c2405d93aea12e85fc35e09dd0e9897ede33a711d986b8c0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-11T14:30:34Z","title_canon_sha256":"820fdc85182d5c2699e78bdb9752309b4b54955f9c18ff397b0209c865075e78"},"schema_version":"1.0","source":{"id":"2211.06235","kind":"arxiv","version":1}},"canonical_sha256":"8a26aba6bbd10991892b8692bc051b6aaba9409f5720d3684bc0ba132c216543","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a26aba6bbd10991892b8692bc051b6aaba9409f5720d3684bc0ba132c216543","first_computed_at":"2026-07-05T05:15:18.466078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:18.466078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OnWjDymb1MKrHJY+/+WaWeFEA7Z8hKSpRW0LfOKs2nRiLN4qyQ3Hp6VJG7JMXd7pdKtiHVU6phbfPPtZKuxRCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:18.466480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.06235","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92894121a2388274d7cecc62edd45ebacdb5548bfa0cfda3cc76bbc072524853","sha256:a8d68623e6a162dd461de919e47060bef8b1e3b1af3a5a768308caf602af94c7"],"state_sha256":"e772d30783a708e149edc0f2a3f664d101ae300b91592f66fe498522f4f16a3d"}