{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3VW3AMO3PWHCEC3H5YKTKSZNG3","short_pith_number":"pith:3VW3AMO3","schema_version":"1.0","canonical_sha256":"dd6db031db7d8e220b67ee15354b2d36dc22d12222ce0fa59620ed8e2d30cd62","source":{"kind":"arxiv","id":"2412.12594","version":1},"attestation_state":"computed","paper":{"title":"A Simple and Efficient Baseline for Zero-Shot Generative Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bao Li, Buhua Liu, Haoyi Xiong, Shiyan Zhang, Zeke Xie, Zhiqiang Xu, Zipeng Qi","submitted_at":"2024-12-17T06:50:23Z","abstract_excerpt":"Large diffusion models have become mainstream generative models in both academic studies and industrial AIGC applications. Recently, a number of works further explored how to employ the power of large diffusion models as zero-shot classifiers. While recent zero-shot diffusion-based classifiers have made performance advancement on benchmark datasets, they still suffered badly from extremely slow classification speed (e.g., ~1000 seconds per classifying single image on ImageNet). The extremely slow classification speed strongly prohibits existing zero-shot diffusion-based classifiers from practi"},"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":"2412.12594","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T06:50:23Z","cross_cats_sorted":[],"title_canon_sha256":"096ba2f77230bd3d01840b2e4a6d99a77c78ece82289a7e7c5125a1445a152c0","abstract_canon_sha256":"fdc7609c8939a44969f94a2ef36cb394520ed0de5cdb9f92bb2b90b38d3beae6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:17.600874Z","signature_b64":"UeqBFBuodpJ38q4rYMSWkGM+y9MTZI7ARnPwWpsJbWayPuAIjojcSLEE5oexvfxOpaItkU1nN/OyWlJnm01fCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd6db031db7d8e220b67ee15354b2d36dc22d12222ce0fa59620ed8e2d30cd62","last_reissued_at":"2026-07-05T09:50:17.600388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:17.600388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple and Efficient Baseline for Zero-Shot Generative Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bao Li, Buhua Liu, Haoyi Xiong, Shiyan Zhang, Zeke Xie, Zhiqiang Xu, Zipeng Qi","submitted_at":"2024-12-17T06:50:23Z","abstract_excerpt":"Large diffusion models have become mainstream generative models in both academic studies and industrial AIGC applications. Recently, a number of works further explored how to employ the power of large diffusion models as zero-shot classifiers. While recent zero-shot diffusion-based classifiers have made performance advancement on benchmark datasets, they still suffered badly from extremely slow classification speed (e.g., ~1000 seconds per classifying single image on ImageNet). The extremely slow classification speed strongly prohibits existing zero-shot diffusion-based classifiers from practi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12594","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/2412.12594/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":"2412.12594","created_at":"2026-07-05T09:50:17.600449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12594v1","created_at":"2026-07-05T09:50:17.600449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12594","created_at":"2026-07-05T09:50:17.600449+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VW3AMO3PWHC","created_at":"2026-07-05T09:50:17.600449+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VW3AMO3PWHCEC3H","created_at":"2026-07-05T09:50:17.600449+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VW3AMO3","created_at":"2026-07-05T09:50:17.600449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02284","citing_title":"FlowCIR: Semantic Transport via Flow Matching for Zero-Shot Composed Image Retrieval","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00183","citing_title":"DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VW3AMO3PWHCEC3H5YKTKSZNG3","json":"https://pith.science/pith/3VW3AMO3PWHCEC3H5YKTKSZNG3.json","graph_json":"https://pith.science/api/pith-number/3VW3AMO3PWHCEC3H5YKTKSZNG3/graph.json","events_json":"https://pith.science/api/pith-number/3VW3AMO3PWHCEC3H5YKTKSZNG3/events.json","paper":"https://pith.science/paper/3VW3AMO3"},"agent_actions":{"view_html":"https://pith.science/pith/3VW3AMO3PWHCEC3H5YKTKSZNG3","download_json":"https://pith.science/pith/3VW3AMO3PWHCEC3H5YKTKSZNG3.json","view_paper":"https://pith.science/paper/3VW3AMO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12594&json=true","fetch_graph":"https://pith.science/api/pith-number/3VW3AMO3PWHCEC3H5YKTKSZNG3/graph.json","fetch_events":"https://pith.science/api/pith-number/3VW3AMO3PWHCEC3H5YKTKSZNG3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VW3AMO3PWHCEC3H5YKTKSZNG3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VW3AMO3PWHCEC3H5YKTKSZNG3/action/storage_attestation","attest_author":"https://pith.science/pith/3VW3AMO3PWHCEC3H5YKTKSZNG3/action/author_attestation","sign_citation":"https://pith.science/pith/3VW3AMO3PWHCEC3H5YKTKSZNG3/action/citation_signature","submit_replication":"https://pith.science/pith/3VW3AMO3PWHCEC3H5YKTKSZNG3/action/replication_record"}},"created_at":"2026-07-05T09:50:17.600449+00:00","updated_at":"2026-07-05T09:50:17.600449+00:00"}