{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TJPHZEXHEQINRVFLIDRZIUQ37B","short_pith_number":"pith:TJPHZEXH","schema_version":"1.0","canonical_sha256":"9a5e7c92e72410d8d4ab40e394521bf861981000383c9763d626fa5284ef8480","source":{"kind":"arxiv","id":"2305.01115","version":2},"attestation_state":"computed","paper":{"title":"In-Context Learning Unlocked for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mingyuan Zhou, Pengcheng He, Weizhu Chen, Yadong Lu, Yelong Shen, Yifan Jiang, Zhangyang Wang, Zhendong Wang","submitted_at":"2023-05-01T23:03:37Z","abstract_excerpt":"We present Prompt Diffusion, a framework for enabling in-context learning in diffusion-based generative models. Given a pair of task-specific example images, such as depth from/to image and scribble from/to image, and a text guidance, our model automatically understands the underlying task and performs the same task on a new query image following the text guidance. To achieve this, we propose a vision-language prompt that can model a wide range of vision-language tasks and a diffusion model that takes it as input. The diffusion model is trained jointly over six different tasks using these prom"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.01115","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-01T23:03:37Z","cross_cats_sorted":[],"title_canon_sha256":"4093a729c002fbf699b9a23f285e8e248022318fa0529ecb13e55a6e5f2319c1","abstract_canon_sha256":"68b63608a4267547a90efa24b0f119727c0b012cf0842e403a046ba733b5073c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:28.573053Z","signature_b64":"Pd9HhtIejEjzG4UDisCSNqFZmzI3RkIq/g8LnmfMvhZPg3iShYPfr68qOHKgcdlgK6e9JziGS+u5hAov+MCJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a5e7c92e72410d8d4ab40e394521bf861981000383c9763d626fa5284ef8480","last_reissued_at":"2026-07-05T07:02:28.572547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:28.572547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Learning Unlocked for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mingyuan Zhou, Pengcheng He, Weizhu Chen, Yadong Lu, Yelong Shen, Yifan Jiang, Zhangyang Wang, Zhendong Wang","submitted_at":"2023-05-01T23:03:37Z","abstract_excerpt":"We present Prompt Diffusion, a framework for enabling in-context learning in diffusion-based generative models. Given a pair of task-specific example images, such as depth from/to image and scribble from/to image, and a text guidance, our model automatically understands the underlying task and performs the same task on a new query image following the text guidance. To achieve this, we propose a vision-language prompt that can model a wide range of vision-language tasks and a diffusion model that takes it as input. The diffusion model is trained jointly over six different tasks using these prom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01115","kind":"arxiv","version":2},"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/2305.01115/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.01115","created_at":"2026-07-05T07:02:28.572610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01115v2","created_at":"2026-07-05T07:02:28.572610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01115","created_at":"2026-07-05T07:02:28.572610+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJPHZEXHEQIN","created_at":"2026-07-05T07:02:28.572610+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJPHZEXHEQINRVFL","created_at":"2026-07-05T07:02:28.572610+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJPHZEXH","created_at":"2026-07-05T07:02:28.572610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10905","citing_title":"Beyond Model Size: Probing the Gaps in Visual in-Context Learning by Training a Tiny Model","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07171","citing_title":"When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07940","citing_title":"Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TJPHZEXHEQINRVFLIDRZIUQ37B","json":"https://pith.science/pith/TJPHZEXHEQINRVFLIDRZIUQ37B.json","graph_json":"https://pith.science/api/pith-number/TJPHZEXHEQINRVFLIDRZIUQ37B/graph.json","events_json":"https://pith.science/api/pith-number/TJPHZEXHEQINRVFLIDRZIUQ37B/events.json","paper":"https://pith.science/paper/TJPHZEXH"},"agent_actions":{"view_html":"https://pith.science/pith/TJPHZEXHEQINRVFLIDRZIUQ37B","download_json":"https://pith.science/pith/TJPHZEXHEQINRVFLIDRZIUQ37B.json","view_paper":"https://pith.science/paper/TJPHZEXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01115&json=true","fetch_graph":"https://pith.science/api/pith-number/TJPHZEXHEQINRVFLIDRZIUQ37B/graph.json","fetch_events":"https://pith.science/api/pith-number/TJPHZEXHEQINRVFLIDRZIUQ37B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJPHZEXHEQINRVFLIDRZIUQ37B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJPHZEXHEQINRVFLIDRZIUQ37B/action/storage_attestation","attest_author":"https://pith.science/pith/TJPHZEXHEQINRVFLIDRZIUQ37B/action/author_attestation","sign_citation":"https://pith.science/pith/TJPHZEXHEQINRVFLIDRZIUQ37B/action/citation_signature","submit_replication":"https://pith.science/pith/TJPHZEXHEQINRVFLIDRZIUQ37B/action/replication_record"}},"created_at":"2026-07-05T07:02:28.572610+00:00","updated_at":"2026-07-05T07:02:28.572610+00:00"}