{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NU2B2POZSPCRV5UPZ4UQRKQEZO","short_pith_number":"pith:NU2B2POZ","schema_version":"1.0","canonical_sha256":"6d341d3dd993c51af68fcf2908aa04cb9bdf83e0c11266cbeec32379eacbd7b8","source":{"kind":"arxiv","id":"2605.30901","version":1},"attestation_state":"computed","paper":{"title":"Density-Guided Robust Counterfactual Explanations on Tabular Data under Model Multiplicity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinglin Li, Jun Tan, Ning Gui, Qi Fang, Qing Guo, Zicheng Xu","submitted_at":"2026-05-29T06:36:33Z","abstract_excerpt":"Counterfactual explanations (CEs) are essential for actionable recourse, yet their reliability is often compromised in low-density regions, where classifiers exhibit high variance. Unlike existing methods that rely on expensive ensemble intersections to define stability, we propose \\textit{DensityFlow}, a generative framework that constructs robust CEs by adhering to the high-confidence data manifold. Specifically, we model the counterfactual generation as continuous-time dynamics parameterized by Neural ODE, guided by a differentiable density score to actively avoid uncertain, low-density are"},"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":"2605.30901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T06:36:33Z","cross_cats_sorted":[],"title_canon_sha256":"57aa17b8c7b96b663a0735c419c03acf303a9b455b9a77c5b81af1322bb8a9e4","abstract_canon_sha256":"4abc1063b4af34024151dca5ee627b104cd00fe324d8db1804da2ab517d93aa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:24.642525Z","signature_b64":"WXayiETRqMtDR6m9/1RgIjnM5aW6GFfOsbjFGuxTZndqVhDVdiJ3srpxkMB5uZ47XaM0pZWc/5cfql/MDqXKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d341d3dd993c51af68fcf2908aa04cb9bdf83e0c11266cbeec32379eacbd7b8","last_reissued_at":"2026-06-01T01:03:24.641784Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:24.641784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Density-Guided Robust Counterfactual Explanations on Tabular Data under Model Multiplicity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinglin Li, Jun Tan, Ning Gui, Qi Fang, Qing Guo, Zicheng Xu","submitted_at":"2026-05-29T06:36:33Z","abstract_excerpt":"Counterfactual explanations (CEs) are essential for actionable recourse, yet their reliability is often compromised in low-density regions, where classifiers exhibit high variance. Unlike existing methods that rely on expensive ensemble intersections to define stability, we propose \\textit{DensityFlow}, a generative framework that constructs robust CEs by adhering to the high-confidence data manifold. Specifically, we model the counterfactual generation as continuous-time dynamics parameterized by Neural ODE, guided by a differentiable density score to actively avoid uncertain, low-density are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30901","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/2605.30901/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":"2605.30901","created_at":"2026-06-01T01:03:24.641877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30901v1","created_at":"2026-06-01T01:03:24.641877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30901","created_at":"2026-06-01T01:03:24.641877+00:00"},{"alias_kind":"pith_short_12","alias_value":"NU2B2POZSPCR","created_at":"2026-06-01T01:03:24.641877+00:00"},{"alias_kind":"pith_short_16","alias_value":"NU2B2POZSPCRV5UP","created_at":"2026-06-01T01:03:24.641877+00:00"},{"alias_kind":"pith_short_8","alias_value":"NU2B2POZ","created_at":"2026-06-01T01:03:24.641877+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/NU2B2POZSPCRV5UPZ4UQRKQEZO","json":"https://pith.science/pith/NU2B2POZSPCRV5UPZ4UQRKQEZO.json","graph_json":"https://pith.science/api/pith-number/NU2B2POZSPCRV5UPZ4UQRKQEZO/graph.json","events_json":"https://pith.science/api/pith-number/NU2B2POZSPCRV5UPZ4UQRKQEZO/events.json","paper":"https://pith.science/paper/NU2B2POZ"},"agent_actions":{"view_html":"https://pith.science/pith/NU2B2POZSPCRV5UPZ4UQRKQEZO","download_json":"https://pith.science/pith/NU2B2POZSPCRV5UPZ4UQRKQEZO.json","view_paper":"https://pith.science/paper/NU2B2POZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30901&json=true","fetch_graph":"https://pith.science/api/pith-number/NU2B2POZSPCRV5UPZ4UQRKQEZO/graph.json","fetch_events":"https://pith.science/api/pith-number/NU2B2POZSPCRV5UPZ4UQRKQEZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NU2B2POZSPCRV5UPZ4UQRKQEZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NU2B2POZSPCRV5UPZ4UQRKQEZO/action/storage_attestation","attest_author":"https://pith.science/pith/NU2B2POZSPCRV5UPZ4UQRKQEZO/action/author_attestation","sign_citation":"https://pith.science/pith/NU2B2POZSPCRV5UPZ4UQRKQEZO/action/citation_signature","submit_replication":"https://pith.science/pith/NU2B2POZSPCRV5UPZ4UQRKQEZO/action/replication_record"}},"created_at":"2026-06-01T01:03:24.641877+00:00","updated_at":"2026-06-01T01:03:24.641877+00:00"}