{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:32FSCD7YTIHYLVX4V563J75KTZ","short_pith_number":"pith:32FSCD7Y","schema_version":"1.0","canonical_sha256":"de8b210ff89a0f85d6fcaf7db4ffaa9e51241ca062f6b7ad105308579ea95102","source":{"kind":"arxiv","id":"2009.13211","version":2},"attestation_state":"computed","paper":{"title":"Instance-based Counterfactual Explanations for Time Series Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Derek Greene, Eoin Delaney, Mark T. Keane","submitted_at":"2020-09-28T10:52:48Z","abstract_excerpt":"In recent years, there has been a rapidly expanding focus on explaining the predictions made by black-box AI systems that handle image and tabular data. However, considerably less attention has been paid to explaining the predictions of opaque AI systems handling time series data. In this paper, we advance a novel model-agnostic, case-based technique -- Native Guide -- that generates counterfactual explanations for time series classifiers. Given a query time series, $T_{q}$, for which a black-box classification system predicts class, $c$, a counterfactual time series explanation shows how $T_{"},"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":"2009.13211","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-28T10:52:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bba49ba3d8b8b87b56be97c53094783131763ada84ac601d843d37324ca6aae0","abstract_canon_sha256":"dad1810356e0c3815902f88d4d13136007d29a962a84c316a17ff8e116dab3ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:59.582413Z","signature_b64":"j1fnY0Ek1hQtCsVopcz5cNmEnf6lkL8fLPCRO5VhiLUSFclXbMy4G45x2lIhUgCKv1QtysyAAxgDttXDfYA5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de8b210ff89a0f85d6fcaf7db4ffaa9e51241ca062f6b7ad105308579ea95102","last_reissued_at":"2026-07-05T02:51:59.581809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:59.581809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instance-based Counterfactual Explanations for Time Series Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Derek Greene, Eoin Delaney, Mark T. Keane","submitted_at":"2020-09-28T10:52:48Z","abstract_excerpt":"In recent years, there has been a rapidly expanding focus on explaining the predictions made by black-box AI systems that handle image and tabular data. However, considerably less attention has been paid to explaining the predictions of opaque AI systems handling time series data. In this paper, we advance a novel model-agnostic, case-based technique -- Native Guide -- that generates counterfactual explanations for time series classifiers. Given a query time series, $T_{q}$, for which a black-box classification system predicts class, $c$, a counterfactual time series explanation shows how $T_{"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13211","kind":"arxiv","version":2},"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/2009.13211/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":"2009.13211","created_at":"2026-07-05T02:51:59.581870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.13211v2","created_at":"2026-07-05T02:51:59.581870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13211","created_at":"2026-07-05T02:51:59.581870+00:00"},{"alias_kind":"pith_short_12","alias_value":"32FSCD7YTIHY","created_at":"2026-07-05T02:51:59.581870+00:00"},{"alias_kind":"pith_short_16","alias_value":"32FSCD7YTIHYLVX4","created_at":"2026-07-05T02:51:59.581870+00:00"},{"alias_kind":"pith_short_8","alias_value":"32FSCD7Y","created_at":"2026-07-05T02:51:59.581870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18049","citing_title":"ConTex: Reformulating Counterfactual Generation For Time Series Forecasting","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32FSCD7YTIHYLVX4V563J75KTZ","json":"https://pith.science/pith/32FSCD7YTIHYLVX4V563J75KTZ.json","graph_json":"https://pith.science/api/pith-number/32FSCD7YTIHYLVX4V563J75KTZ/graph.json","events_json":"https://pith.science/api/pith-number/32FSCD7YTIHYLVX4V563J75KTZ/events.json","paper":"https://pith.science/paper/32FSCD7Y"},"agent_actions":{"view_html":"https://pith.science/pith/32FSCD7YTIHYLVX4V563J75KTZ","download_json":"https://pith.science/pith/32FSCD7YTIHYLVX4V563J75KTZ.json","view_paper":"https://pith.science/paper/32FSCD7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.13211&json=true","fetch_graph":"https://pith.science/api/pith-number/32FSCD7YTIHYLVX4V563J75KTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/32FSCD7YTIHYLVX4V563J75KTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32FSCD7YTIHYLVX4V563J75KTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32FSCD7YTIHYLVX4V563J75KTZ/action/storage_attestation","attest_author":"https://pith.science/pith/32FSCD7YTIHYLVX4V563J75KTZ/action/author_attestation","sign_citation":"https://pith.science/pith/32FSCD7YTIHYLVX4V563J75KTZ/action/citation_signature","submit_replication":"https://pith.science/pith/32FSCD7YTIHYLVX4V563J75KTZ/action/replication_record"}},"created_at":"2026-07-05T02:51:59.581870+00:00","updated_at":"2026-07-05T02:51:59.581870+00:00"}