{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:S6XBZFD6V2QMZNSHDS4NIEHMWM","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":"6caafde257cb095ab93cb4cfdc8332dc7eaa5c2cc15b86c52d044c25a4de63aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-03T18:59:47Z","title_canon_sha256":"8befc34e57937ee1b8ad65c34b31a176f90a08ede32336cae2293b66a98b1407"},"schema_version":"1.0","source":{"id":"2303.02153","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02153","created_at":"2026-07-05T05:47:53Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02153v1","created_at":"2026-07-05T05:47:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02153","created_at":"2026-07-05T05:47:53Z"},{"alias_kind":"pith_short_12","alias_value":"S6XBZFD6V2QM","created_at":"2026-07-05T05:47:53Z"},{"alias_kind":"pith_short_16","alias_value":"S6XBZFD6V2QMZNSH","created_at":"2026-07-05T05:47:53Z"},{"alias_kind":"pith_short_8","alias_value":"S6XBZFD6","created_at":"2026-07-05T05:47:53Z"}],"graph_snapshots":[{"event_id":"sha256:a0fcf757539585e21dda156d424fa7b75ff7e11d3c66122686d16952ed223b1d","target":"graph","created_at":"2026-07-05T05:47:53Z","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/2303.02153/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models (DMs) have become the new trend of generative models and have demonstrated a powerful ability of conditional synthesis. Among those, text-to-image diffusion models pre-trained on large-scale image-text pairs are highly controllable by customizable prompts. Unlike the unconditional generative models that focus on low-level attributes and details, text-to-image diffusion models contain more high-level knowledge thanks to the vision-language pre-training. In this paper, we propose VPD (Visual Perception with a pre-trained Diffusion model), a new framework that exploits the semant","authors_text":"Benlin Liu, Jie Zhou, Jiwen Lu, Wenliang Zhao, Yongming Rao, Zuyan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-03T18:59:47Z","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02153","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":"sha256:4739648814d545505ffd42a7de6bb923cb2afc7c646ae4af0ab52abe5f1e5c5b","target":"record","created_at":"2026-07-05T05:47:53Z","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":"6caafde257cb095ab93cb4cfdc8332dc7eaa5c2cc15b86c52d044c25a4de63aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-03T18:59:47Z","title_canon_sha256":"8befc34e57937ee1b8ad65c34b31a176f90a08ede32336cae2293b66a98b1407"},"schema_version":"1.0","source":{"id":"2303.02153","kind":"arxiv","version":1}},"canonical_sha256":"97ae1c947eaea0ccb6471cb8d410ecb3285a056fd2495d70f5e03aaa14defa67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97ae1c947eaea0ccb6471cb8d410ecb3285a056fd2495d70f5e03aaa14defa67","first_computed_at":"2026-07-05T05:47:53.121840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:53.121840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FjD5gFp1r5GaNVFSUUzbBWxdFWOa0zUCWz9mzwTta3CDEh4m28S0RKGM7TWuMlBMTdWRjR7650Y0StdHpVv8Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:53.122368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.02153","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4739648814d545505ffd42a7de6bb923cb2afc7c646ae4af0ab52abe5f1e5c5b","sha256:a0fcf757539585e21dda156d424fa7b75ff7e11d3c66122686d16952ed223b1d"],"state_sha256":"505a6625cf51e98be41b0c41859e0790ed7f8e7bc047e38cd481d10c479559f4"}