{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:22ICPDEJQLKEYIIL7JW3MDCFPE","short_pith_number":"pith:22ICPDEJ","schema_version":"1.0","canonical_sha256":"d690278c8982d44c210bfa6db60c457920b9b29a9afd0158b257ffe85997ce7d","source":{"kind":"arxiv","id":"2308.06739","version":1},"attestation_state":"computed","paper":{"title":"Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuhui Xue, David Junhao Zhang, Mike Zheng Shou, Mutian Xu, Song Bai, Wenqing Zhang, Xiaoguang Han","submitted_at":"2023-08-13T10:07:46Z","abstract_excerpt":"Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additional challenges due to concerns regarding data privacy. Recently, synthetic images generated by text-to-image diffusion models, have shown great potential for benefiting image recognition. Although promising, there has been inadequate exploration dedicated to unsupervised learning on diffusion-generated images. To address this, we start by uncovering that diffusion models' cross-attention layers inherently provide annot"},"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":"2308.06739","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-13T10:07:46Z","cross_cats_sorted":[],"title_canon_sha256":"5e163f22f72dd5f0e09af6503e04a7ffae8939674e11502955bbdb321ab24110","abstract_canon_sha256":"8e36a3e749a2ef6585c5ee66b586f43ea7d40b82802338759f48d5744c578503"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:44.545814Z","signature_b64":"iu6Sd39e2BBJsmLsWbbur008I5Dkcneups15B5Lekz2Ggefw4AB2EL5qy6PGyY5HO0KsVJYaR1Q23g+3+FxfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d690278c8982d44c210bfa6db60c457920b9b29a9afd0158b257ffe85997ce7d","last_reissued_at":"2026-07-05T06:40:44.545428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:44.545428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuhui Xue, David Junhao Zhang, Mike Zheng Shou, Mutian Xu, Song Bai, Wenqing Zhang, Xiaoguang Han","submitted_at":"2023-08-13T10:07:46Z","abstract_excerpt":"Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additional challenges due to concerns regarding data privacy. Recently, synthetic images generated by text-to-image diffusion models, have shown great potential for benefiting image recognition. Although promising, there has been inadequate exploration dedicated to unsupervised learning on diffusion-generated images. To address this, we start by uncovering that diffusion models' cross-attention layers inherently provide annot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06739","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/2308.06739/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":"2308.06739","created_at":"2026-07-05T06:40:44.545478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.06739v1","created_at":"2026-07-05T06:40:44.545478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06739","created_at":"2026-07-05T06:40:44.545478+00:00"},{"alias_kind":"pith_short_12","alias_value":"22ICPDEJQLKE","created_at":"2026-07-05T06:40:44.545478+00:00"},{"alias_kind":"pith_short_16","alias_value":"22ICPDEJQLKEYIIL","created_at":"2026-07-05T06:40:44.545478+00:00"},{"alias_kind":"pith_short_8","alias_value":"22ICPDEJ","created_at":"2026-07-05T06:40:44.545478+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/22ICPDEJQLKEYIIL7JW3MDCFPE","json":"https://pith.science/pith/22ICPDEJQLKEYIIL7JW3MDCFPE.json","graph_json":"https://pith.science/api/pith-number/22ICPDEJQLKEYIIL7JW3MDCFPE/graph.json","events_json":"https://pith.science/api/pith-number/22ICPDEJQLKEYIIL7JW3MDCFPE/events.json","paper":"https://pith.science/paper/22ICPDEJ"},"agent_actions":{"view_html":"https://pith.science/pith/22ICPDEJQLKEYIIL7JW3MDCFPE","download_json":"https://pith.science/pith/22ICPDEJQLKEYIIL7JW3MDCFPE.json","view_paper":"https://pith.science/paper/22ICPDEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.06739&json=true","fetch_graph":"https://pith.science/api/pith-number/22ICPDEJQLKEYIIL7JW3MDCFPE/graph.json","fetch_events":"https://pith.science/api/pith-number/22ICPDEJQLKEYIIL7JW3MDCFPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22ICPDEJQLKEYIIL7JW3MDCFPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22ICPDEJQLKEYIIL7JW3MDCFPE/action/storage_attestation","attest_author":"https://pith.science/pith/22ICPDEJQLKEYIIL7JW3MDCFPE/action/author_attestation","sign_citation":"https://pith.science/pith/22ICPDEJQLKEYIIL7JW3MDCFPE/action/citation_signature","submit_replication":"https://pith.science/pith/22ICPDEJQLKEYIIL7JW3MDCFPE/action/replication_record"}},"created_at":"2026-07-05T06:40:44.545478+00:00","updated_at":"2026-07-05T06:40:44.545478+00:00"}