{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FOP2LENPCGACZPG7KH27YHNAON","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":"e623dee918b0be093e6c8b29a3e3e35d00e59c5779db765f3361d1eb531cc9b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T14:40:55Z","title_canon_sha256":"e7b6629c929eaa52fa4a1ecfc7f73ab54fa0caf5b3745cd87394f89f22a815b1"},"schema_version":"1.0","source":{"id":"2312.14733","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14733","created_at":"2026-07-05T07:27:19Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14733v1","created_at":"2026-07-05T07:27:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14733","created_at":"2026-07-05T07:27:19Z"},{"alias_kind":"pith_short_12","alias_value":"FOP2LENPCGAC","created_at":"2026-07-05T07:27:19Z"},{"alias_kind":"pith_short_16","alias_value":"FOP2LENPCGACZPG7","created_at":"2026-07-05T07:27:19Z"},{"alias_kind":"pith_short_8","alias_value":"FOP2LENP","created_at":"2026-07-05T07:27:19Z"}],"graph_snapshots":[{"event_id":"sha256:293103ff722cd721cb7822d70ae0e1b2b1c6086251e73fe2f1245641f3af8156","target":"graph","created_at":"2026-07-05T07:27:19Z","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/2312.14733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The issue of generative pretraining for vision models has persisted as a long-standing conundrum. At present, the text-to-image (T2I) diffusion model demonstrates remarkable proficiency in generating high-definition images matching textual inputs, a feat made possible through its pre-training on large-scale image-text pairs. This leads to a natural inquiry: can diffusion models be utilized to tackle visual perception tasks? In this paper, we propose a simple yet effective scheme to harness a diffusion model for visual perception tasks. Our key insight is to introduce learnable embeddings (meta","authors_text":"Bingyi Kang, Jiashi Feng, Li Zhang, Qiang Wan, Zilong Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T14:40:55Z","title":"Harnessing Diffusion Models for Visual Perception with Meta Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14733","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:bae5299ebc6c82f9145a7922923049f36ee2ca058a18103b9ff943a0e6f0713e","target":"record","created_at":"2026-07-05T07:27:19Z","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":"e623dee918b0be093e6c8b29a3e3e35d00e59c5779db765f3361d1eb531cc9b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T14:40:55Z","title_canon_sha256":"e7b6629c929eaa52fa4a1ecfc7f73ab54fa0caf5b3745cd87394f89f22a815b1"},"schema_version":"1.0","source":{"id":"2312.14733","kind":"arxiv","version":1}},"canonical_sha256":"2b9fa591af11802cbcdf51f5fc1da0736abaa67e654b5aff06c753cc72889f63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b9fa591af11802cbcdf51f5fc1da0736abaa67e654b5aff06c753cc72889f63","first_computed_at":"2026-07-05T07:27:19.136329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:19.136329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gu39/AnHjWH8T1YnP5ihQzwD0PBUA4Wez+rANCUll0C3xlYC59bRGp4LBX7o9hTUPLqXONcWpb6LUZ7VXmjWBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:19.136752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14733","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bae5299ebc6c82f9145a7922923049f36ee2ca058a18103b9ff943a0e6f0713e","sha256:293103ff722cd721cb7822d70ae0e1b2b1c6086251e73fe2f1245641f3af8156"],"state_sha256":"c5b07d69d8602024b8fb9c9b166bc15c24075a8496d648b86062c5f1d8ae973c"}