{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OPNKACRYXAPWRLLUV3EL5V3JGL","short_pith_number":"pith:OPNKACRY","schema_version":"1.0","canonical_sha256":"73daa00a38b81f68ad74aec8bed76932cbcebd9e6b2dca856e25c5e7f38780cc","source":{"kind":"arxiv","id":"2211.10370","version":1},"attestation_state":"computed","paper":{"title":"Invariant Learning via Diffusion Dreamed Distribution Shifts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Levine, Priyatham Kattakinda, Soheil Feizi","submitted_at":"2022-11-18T17:07:43Z","abstract_excerpt":"Though the background is an important signal for image classification, over reliance on it can lead to incorrect predictions when spurious correlations between foreground and background are broken at test time. Training on a dataset where these correlations are unbiased would lead to more robust models. In this paper, we propose such a dataset called Diffusion Dreamed Distribution Shifts (D3S). D3S consists of synthetic images generated through StableDiffusion using text prompts and image guides obtained by pasting a sample foreground image onto a background template image. Using this scalable"},"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":"2211.10370","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-18T17:07:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec8563662b1b9bd7c1becd33e6f1438a256f17d82ea11aa8dbc869da1ae1ed74","abstract_canon_sha256":"42a899a1e52112ede1ec0f3a62feb1cafe9bb5191eb12840ce0a981367d9d98a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:21.480684Z","signature_b64":"1E0pmF6pDcumQh2QRioSTq/cCNjvH0O7XMuZjrSJ5vT5BX7MygNqZQ16fMmhEswhK8Wmov3E9qKom+nqw16kCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73daa00a38b81f68ad74aec8bed76932cbcebd9e6b2dca856e25c5e7f38780cc","last_reissued_at":"2026-07-05T05:17:21.480331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:21.480331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Invariant Learning via Diffusion Dreamed Distribution Shifts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Levine, Priyatham Kattakinda, Soheil Feizi","submitted_at":"2022-11-18T17:07:43Z","abstract_excerpt":"Though the background is an important signal for image classification, over reliance on it can lead to incorrect predictions when spurious correlations between foreground and background are broken at test time. Training on a dataset where these correlations are unbiased would lead to more robust models. In this paper, we propose such a dataset called Diffusion Dreamed Distribution Shifts (D3S). D3S consists of synthetic images generated through StableDiffusion using text prompts and image guides obtained by pasting a sample foreground image onto a background template image. Using this scalable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10370","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/2211.10370/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":"2211.10370","created_at":"2026-07-05T05:17:21.480383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.10370v1","created_at":"2026-07-05T05:17:21.480383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10370","created_at":"2026-07-05T05:17:21.480383+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPNKACRYXAPW","created_at":"2026-07-05T05:17:21.480383+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPNKACRYXAPWRLLU","created_at":"2026-07-05T05:17:21.480383+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPNKACRY","created_at":"2026-07-05T05:17:21.480383+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10686","citing_title":"MaskMedPaint: Masked Medical Image Inpainting with Diffusion Models for Mitigation of Spurious Correlations","ref_index":90,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OPNKACRYXAPWRLLUV3EL5V3JGL","json":"https://pith.science/pith/OPNKACRYXAPWRLLUV3EL5V3JGL.json","graph_json":"https://pith.science/api/pith-number/OPNKACRYXAPWRLLUV3EL5V3JGL/graph.json","events_json":"https://pith.science/api/pith-number/OPNKACRYXAPWRLLUV3EL5V3JGL/events.json","paper":"https://pith.science/paper/OPNKACRY"},"agent_actions":{"view_html":"https://pith.science/pith/OPNKACRYXAPWRLLUV3EL5V3JGL","download_json":"https://pith.science/pith/OPNKACRYXAPWRLLUV3EL5V3JGL.json","view_paper":"https://pith.science/paper/OPNKACRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.10370&json=true","fetch_graph":"https://pith.science/api/pith-number/OPNKACRYXAPWRLLUV3EL5V3JGL/graph.json","fetch_events":"https://pith.science/api/pith-number/OPNKACRYXAPWRLLUV3EL5V3JGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPNKACRYXAPWRLLUV3EL5V3JGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPNKACRYXAPWRLLUV3EL5V3JGL/action/storage_attestation","attest_author":"https://pith.science/pith/OPNKACRYXAPWRLLUV3EL5V3JGL/action/author_attestation","sign_citation":"https://pith.science/pith/OPNKACRYXAPWRLLUV3EL5V3JGL/action/citation_signature","submit_replication":"https://pith.science/pith/OPNKACRYXAPWRLLUV3EL5V3JGL/action/replication_record"}},"created_at":"2026-07-05T05:17:21.480383+00:00","updated_at":"2026-07-05T05:17:21.480383+00:00"}