{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P357I44XEV4D7WUME4KYDF2UMQ","short_pith_number":"pith:P357I44X","schema_version":"1.0","canonical_sha256":"7efbf4739725783fda8c2715819754640420eb44e9061d04355a022078977cf8","source":{"kind":"arxiv","id":"2502.11509","version":1},"attestation_state":"computed","paper":{"title":"DifCluE: Generating Counterfactual Explanations with Diffusion Autoencoders and modal clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amit Sangroya, Lovekesh Vig, Suparshva Jain","submitted_at":"2025-02-17T07:17:37Z","abstract_excerpt":"Generating multiple counterfactual explanations for different modes within a class presents a significant challenge, as these modes are distinct yet converge under the same classification. Diffusion probabilistic models (DPMs) have demonstrated a strong ability to capture the underlying modes of data distributions. In this paper, we harness the power of a Diffusion Autoencoder to generate multiple distinct counterfactual explanations. By clustering in the latent space, we uncover the directions corresponding to the different modes within a class, enabling the generation of diverse and meaningf"},"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":"2502.11509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T07:17:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"243c73095a92ae277b1893c289bfb7361037584c440e20c6062d51650651ba0d","abstract_canon_sha256":"f3f779f03a1a907f212af63ebc54c0f47e8d25aec6d5202e1ab9cb22c6206370"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:17.756130Z","signature_b64":"XgBSxCNqHGaiOUmgroizSSeHeBhKzLf7sAZw/bPogUuiaWqclHo1a1Dp82Z4bhFSU7gB+0aeCje5RMAFRGRkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7efbf4739725783fda8c2715819754640420eb44e9061d04355a022078977cf8","last_reissued_at":"2026-07-05T10:17:17.755599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:17.755599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DifCluE: Generating Counterfactual Explanations with Diffusion Autoencoders and modal clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amit Sangroya, Lovekesh Vig, Suparshva Jain","submitted_at":"2025-02-17T07:17:37Z","abstract_excerpt":"Generating multiple counterfactual explanations for different modes within a class presents a significant challenge, as these modes are distinct yet converge under the same classification. Diffusion probabilistic models (DPMs) have demonstrated a strong ability to capture the underlying modes of data distributions. In this paper, we harness the power of a Diffusion Autoencoder to generate multiple distinct counterfactual explanations. By clustering in the latent space, we uncover the directions corresponding to the different modes within a class, enabling the generation of diverse and meaningf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11509","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/2502.11509/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":"2502.11509","created_at":"2026-07-05T10:17:17.755661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11509v1","created_at":"2026-07-05T10:17:17.755661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11509","created_at":"2026-07-05T10:17:17.755661+00:00"},{"alias_kind":"pith_short_12","alias_value":"P357I44XEV4D","created_at":"2026-07-05T10:17:17.755661+00:00"},{"alias_kind":"pith_short_16","alias_value":"P357I44XEV4D7WUM","created_at":"2026-07-05T10:17:17.755661+00:00"},{"alias_kind":"pith_short_8","alias_value":"P357I44X","created_at":"2026-07-05T10:17:17.755661+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/P357I44XEV4D7WUME4KYDF2UMQ","json":"https://pith.science/pith/P357I44XEV4D7WUME4KYDF2UMQ.json","graph_json":"https://pith.science/api/pith-number/P357I44XEV4D7WUME4KYDF2UMQ/graph.json","events_json":"https://pith.science/api/pith-number/P357I44XEV4D7WUME4KYDF2UMQ/events.json","paper":"https://pith.science/paper/P357I44X"},"agent_actions":{"view_html":"https://pith.science/pith/P357I44XEV4D7WUME4KYDF2UMQ","download_json":"https://pith.science/pith/P357I44XEV4D7WUME4KYDF2UMQ.json","view_paper":"https://pith.science/paper/P357I44X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11509&json=true","fetch_graph":"https://pith.science/api/pith-number/P357I44XEV4D7WUME4KYDF2UMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/P357I44XEV4D7WUME4KYDF2UMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P357I44XEV4D7WUME4KYDF2UMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P357I44XEV4D7WUME4KYDF2UMQ/action/storage_attestation","attest_author":"https://pith.science/pith/P357I44XEV4D7WUME4KYDF2UMQ/action/author_attestation","sign_citation":"https://pith.science/pith/P357I44XEV4D7WUME4KYDF2UMQ/action/citation_signature","submit_replication":"https://pith.science/pith/P357I44XEV4D7WUME4KYDF2UMQ/action/replication_record"}},"created_at":"2026-07-05T10:17:17.755661+00:00","updated_at":"2026-07-05T10:17:17.755661+00:00"}