{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7TBVGQXNYIEBYW5O2HEKAVCJEE","short_pith_number":"pith:7TBVGQXN","schema_version":"1.0","canonical_sha256":"fcc35342edc2081c5baed1c8a054492121676c9cd289d799166d4c40b69f718e","source":{"kind":"arxiv","id":"2305.10722","version":3},"attestation_state":"computed","paper":{"title":"Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arjun Akula, Pradyumna Narayana, Sugato Basu, Tsu-Jui Fu, Varun Jampani, Weixi Feng, William Yang Wang, Xin Eric Wang, Xuehai He","submitted_at":"2023-05-18T05:41:36Z","abstract_excerpt":"Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified in text prompts, can we leverage the powerful representations learned by pre-trained diffusion models for discriminative tasks such as image-text matching? To answer this question, we propose a novel approach, Discriminative Stable Diffusion (DSD), which turns pre-trained text-to-image diffusion models into few-shot discriminative learners. Our approach mainl"},"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":"2305.10722","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T05:41:36Z","cross_cats_sorted":[],"title_canon_sha256":"def20a82ca08ec791a6fac8aeab39b4b0e4f9cc6db356115ddf77ff55a191dc3","abstract_canon_sha256":"c1605f055bcb81e652160982661abfbe290af1fa918bada9aebbf105e0773f03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:52.915942Z","signature_b64":"NhpJe2fKsxcYwFVThhlNEgCy/0SaQng0noGyRSbGm7cY81LXXDf14NG9qK2WYR1Fck26oSaYItKf+5QgeuvgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcc35342edc2081c5baed1c8a054492121676c9cd289d799166d4c40b69f718e","last_reissued_at":"2026-07-05T08:11:52.915518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:52.915518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arjun Akula, Pradyumna Narayana, Sugato Basu, Tsu-Jui Fu, Varun Jampani, Weixi Feng, William Yang Wang, Xin Eric Wang, Xuehai He","submitted_at":"2023-05-18T05:41:36Z","abstract_excerpt":"Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified in text prompts, can we leverage the powerful representations learned by pre-trained diffusion models for discriminative tasks such as image-text matching? To answer this question, we propose a novel approach, Discriminative Stable Diffusion (DSD), which turns pre-trained text-to-image diffusion models into few-shot discriminative learners. Our approach mainl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10722","kind":"arxiv","version":3},"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/2305.10722/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":"2305.10722","created_at":"2026-07-05T08:11:52.915574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10722v3","created_at":"2026-07-05T08:11:52.915574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10722","created_at":"2026-07-05T08:11:52.915574+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TBVGQXNYIEB","created_at":"2026-07-05T08:11:52.915574+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TBVGQXNYIEBYW5O","created_at":"2026-07-05T08:11:52.915574+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TBVGQXN","created_at":"2026-07-05T08:11:52.915574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TBVGQXNYIEBYW5O2HEKAVCJEE","json":"https://pith.science/pith/7TBVGQXNYIEBYW5O2HEKAVCJEE.json","graph_json":"https://pith.science/api/pith-number/7TBVGQXNYIEBYW5O2HEKAVCJEE/graph.json","events_json":"https://pith.science/api/pith-number/7TBVGQXNYIEBYW5O2HEKAVCJEE/events.json","paper":"https://pith.science/paper/7TBVGQXN"},"agent_actions":{"view_html":"https://pith.science/pith/7TBVGQXNYIEBYW5O2HEKAVCJEE","download_json":"https://pith.science/pith/7TBVGQXNYIEBYW5O2HEKAVCJEE.json","view_paper":"https://pith.science/paper/7TBVGQXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10722&json=true","fetch_graph":"https://pith.science/api/pith-number/7TBVGQXNYIEBYW5O2HEKAVCJEE/graph.json","fetch_events":"https://pith.science/api/pith-number/7TBVGQXNYIEBYW5O2HEKAVCJEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TBVGQXNYIEBYW5O2HEKAVCJEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TBVGQXNYIEBYW5O2HEKAVCJEE/action/storage_attestation","attest_author":"https://pith.science/pith/7TBVGQXNYIEBYW5O2HEKAVCJEE/action/author_attestation","sign_citation":"https://pith.science/pith/7TBVGQXNYIEBYW5O2HEKAVCJEE/action/citation_signature","submit_replication":"https://pith.science/pith/7TBVGQXNYIEBYW5O2HEKAVCJEE/action/replication_record"}},"created_at":"2026-07-05T08:11:52.915574+00:00","updated_at":"2026-07-05T08:11:52.915574+00:00"}