{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RM3E6Q6BIBI6LISYPTXIQCBZPY","short_pith_number":"pith:RM3E6Q6B","schema_version":"1.0","canonical_sha256":"8b364f43c14051e5a2587cee8808397e28b79f9d762afdfa0cdb1fddec420546","source":{"kind":"arxiv","id":"2311.10708","version":2},"attestation_state":"computed","paper":{"title":"SelfEval: Leveraging the discriminative nature of generative models for evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ishan Misra, Sai Saketh Rambhatla","submitted_at":"2023-11-17T18:58:16Z","abstract_excerpt":"We present an automated way to evaluate the text alignment of text-to-image generative diffusion models using standard image-text recognition datasets. Our method, called SelfEval, uses the generative model to compute the likelihood of real images given text prompts, and the likelihood can be used to perform recognition tasks with the generative model. We evaluate generative models on standard datasets created for multimodal text-image discriminative learning and assess fine-grained aspects of their performance: attribute binding, color recognition, counting, shape recognition, spatial underst"},"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":"2311.10708","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-17T18:58:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"715816379f51cb658b58bdf7bc59458321e16d66da733b341c45eae0c0859eeb","abstract_canon_sha256":"67c21161039b075f8207f90452211fbcf07be4ee353746e93adbd625260da20f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:54.214629Z","signature_b64":"dFnVti3gadxEyGbDecFoLtTFdGw4wa+8S1ZPhT941Djade8Q1cDfNuPyeb9cYMw20p0HKkhfVKwoY2Z4HJ+uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b364f43c14051e5a2587cee8808397e28b79f9d762afdfa0cdb1fddec420546","last_reissued_at":"2026-07-05T09:40:54.214127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:54.214127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SelfEval: Leveraging the discriminative nature of generative models for evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ishan Misra, Sai Saketh Rambhatla","submitted_at":"2023-11-17T18:58:16Z","abstract_excerpt":"We present an automated way to evaluate the text alignment of text-to-image generative diffusion models using standard image-text recognition datasets. Our method, called SelfEval, uses the generative model to compute the likelihood of real images given text prompts, and the likelihood can be used to perform recognition tasks with the generative model. We evaluate generative models on standard datasets created for multimodal text-image discriminative learning and assess fine-grained aspects of their performance: attribute binding, color recognition, counting, shape recognition, spatial underst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10708","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/2311.10708/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":"2311.10708","created_at":"2026-07-05T09:40:54.214178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10708v2","created_at":"2026-07-05T09:40:54.214178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10708","created_at":"2026-07-05T09:40:54.214178+00:00"},{"alias_kind":"pith_short_12","alias_value":"RM3E6Q6BIBI6","created_at":"2026-07-05T09:40:54.214178+00:00"},{"alias_kind":"pith_short_16","alias_value":"RM3E6Q6BIBI6LISY","created_at":"2026-07-05T09:40:54.214178+00:00"},{"alias_kind":"pith_short_8","alias_value":"RM3E6Q6B","created_at":"2026-07-05T09:40:54.214178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.13720","citing_title":"Movie Gen: A Cast of Media Foundation Models","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RM3E6Q6BIBI6LISYPTXIQCBZPY","json":"https://pith.science/pith/RM3E6Q6BIBI6LISYPTXIQCBZPY.json","graph_json":"https://pith.science/api/pith-number/RM3E6Q6BIBI6LISYPTXIQCBZPY/graph.json","events_json":"https://pith.science/api/pith-number/RM3E6Q6BIBI6LISYPTXIQCBZPY/events.json","paper":"https://pith.science/paper/RM3E6Q6B"},"agent_actions":{"view_html":"https://pith.science/pith/RM3E6Q6BIBI6LISYPTXIQCBZPY","download_json":"https://pith.science/pith/RM3E6Q6BIBI6LISYPTXIQCBZPY.json","view_paper":"https://pith.science/paper/RM3E6Q6B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10708&json=true","fetch_graph":"https://pith.science/api/pith-number/RM3E6Q6BIBI6LISYPTXIQCBZPY/graph.json","fetch_events":"https://pith.science/api/pith-number/RM3E6Q6BIBI6LISYPTXIQCBZPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RM3E6Q6BIBI6LISYPTXIQCBZPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RM3E6Q6BIBI6LISYPTXIQCBZPY/action/storage_attestation","attest_author":"https://pith.science/pith/RM3E6Q6BIBI6LISYPTXIQCBZPY/action/author_attestation","sign_citation":"https://pith.science/pith/RM3E6Q6BIBI6LISYPTXIQCBZPY/action/citation_signature","submit_replication":"https://pith.science/pith/RM3E6Q6BIBI6LISYPTXIQCBZPY/action/replication_record"}},"created_at":"2026-07-05T09:40:54.214178+00:00","updated_at":"2026-07-05T09:40:54.214178+00:00"}