{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R5LLWHIXQ672CCH65CMUNWSRJL","short_pith_number":"pith:R5LLWHIX","schema_version":"1.0","canonical_sha256":"8f56bb1d1787bfa108fee89946da514af6328506d886dadabd1174f15040cb7d","source":{"kind":"arxiv","id":"2307.08702","version":1},"attestation_state":"computed","paper":{"title":"Diffusion Models Beat GANs on Image Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Archana Swaminathan, Matthew Gwilliam, Namitha Padmanabhan, Soumik Mukhopadhyay, Srinidhi Hegde, Tianyi Zhou, Vatsal Agarwal","submitted_at":"2023-07-17T17:59:40Z","abstract_excerpt":"While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which uses a single pre-training stage to address both families of tasks simultaneously. We identify diffusion models as a prime candidate. Diffusion models have risen to prominence as a state-of-the-art method for image generation, denoising, inpainting, super-resolution, manipulation, etc. Such models involve training a U-Net to iteratively predict and remove noise, and the resulting model can synthesize high fideli"},"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":"2307.08702","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-17T17:59:40Z","cross_cats_sorted":[],"title_canon_sha256":"4c9b876bce6a1c28cec14a8d3b70063b1c05496c6063d31d43f0468130baf257","abstract_canon_sha256":"79583a40d4366a01f8e2fe90c10c99148315e2144344f08f38fe427a4592b913"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:27.898214Z","signature_b64":"nSq/6h5IdOZBH0rc7lj2Bkh+5UygueIqCHaemDomnDAYK3gDTZyfr3wHyqh8bYs8kvrPd0B1kINAAHOz1YP7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f56bb1d1787bfa108fee89946da514af6328506d886dadabd1174f15040cb7d","last_reissued_at":"2026-07-05T06:31:27.897737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:27.897737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Models Beat GANs on Image Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Archana Swaminathan, Matthew Gwilliam, Namitha Padmanabhan, Soumik Mukhopadhyay, Srinidhi Hegde, Tianyi Zhou, Vatsal Agarwal","submitted_at":"2023-07-17T17:59:40Z","abstract_excerpt":"While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which uses a single pre-training stage to address both families of tasks simultaneously. We identify diffusion models as a prime candidate. Diffusion models have risen to prominence as a state-of-the-art method for image generation, denoising, inpainting, super-resolution, manipulation, etc. Such models involve training a U-Net to iteratively predict and remove noise, and the resulting model can synthesize high fideli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08702","kind":"arxiv","version":1},"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/2307.08702/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":"2307.08702","created_at":"2026-07-05T06:31:27.897793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08702v1","created_at":"2026-07-05T06:31:27.897793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08702","created_at":"2026-07-05T06:31:27.897793+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5LLWHIXQ672","created_at":"2026-07-05T06:31:27.897793+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5LLWHIXQ672CCH6","created_at":"2026-07-05T06:31:27.897793+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5LLWHIX","created_at":"2026-07-05T06:31:27.897793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24888","citing_title":"DiffusionBench: On Holistic Evaluation of Diffusion Transformers","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09718","citing_title":"Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06813","citing_title":"Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23310","citing_title":"Balanced Diffusion-Guided Fusion for Multimodal Remote Sensing Classification","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2602.15423","citing_title":"GaiaFlow: Semantic-Guided Diffusion Tuning for Carbon-Frugal Search","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R5LLWHIXQ672CCH65CMUNWSRJL","json":"https://pith.science/pith/R5LLWHIXQ672CCH65CMUNWSRJL.json","graph_json":"https://pith.science/api/pith-number/R5LLWHIXQ672CCH65CMUNWSRJL/graph.json","events_json":"https://pith.science/api/pith-number/R5LLWHIXQ672CCH65CMUNWSRJL/events.json","paper":"https://pith.science/paper/R5LLWHIX"},"agent_actions":{"view_html":"https://pith.science/pith/R5LLWHIXQ672CCH65CMUNWSRJL","download_json":"https://pith.science/pith/R5LLWHIXQ672CCH65CMUNWSRJL.json","view_paper":"https://pith.science/paper/R5LLWHIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08702&json=true","fetch_graph":"https://pith.science/api/pith-number/R5LLWHIXQ672CCH65CMUNWSRJL/graph.json","fetch_events":"https://pith.science/api/pith-number/R5LLWHIXQ672CCH65CMUNWSRJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5LLWHIXQ672CCH65CMUNWSRJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5LLWHIXQ672CCH65CMUNWSRJL/action/storage_attestation","attest_author":"https://pith.science/pith/R5LLWHIXQ672CCH65CMUNWSRJL/action/author_attestation","sign_citation":"https://pith.science/pith/R5LLWHIXQ672CCH65CMUNWSRJL/action/citation_signature","submit_replication":"https://pith.science/pith/R5LLWHIXQ672CCH65CMUNWSRJL/action/replication_record"}},"created_at":"2026-07-05T06:31:27.897793+00:00","updated_at":"2026-07-05T06:31:27.897793+00:00"}