{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Q4XWL6WIIPV5EJQZA475LVEHF2","short_pith_number":"pith:Q4XWL6WI","schema_version":"1.0","canonical_sha256":"872f65fac843ebd22619073fd5d4872e9aae4c2bbfa4a4ccb8f8ea0eaf248f8d","source":{"kind":"arxiv","id":"2006.04528","version":2},"attestation_state":"computed","paper":{"title":"Evaluation of Similarity-based Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kazuaki Hanawa, Kentaro Inui, Satoshi Hara, Sho Yokoi","submitted_at":"2020-06-08T12:39:46Z","abstract_excerpt":"Explaining the predictions made by complex machine learning models helps users to understand and accept the predicted outputs with confidence. One promising way is to use similarity-based explanation that provides similar instances as evidence to support model predictions. Several relevance metrics are used for this purpose. In this study, we investigated relevance metrics that can provide reasonable explanations to users. Specifically, we adopted three tests to evaluate whether the relevance metrics satisfy the minimal requirements for similarity-based explanation. Our experiments revealed th"},"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":"2006.04528","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T12:39:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1862a727d79f071f61705303f4ddeff139bd252ed2d0e36b52b6cd22feefd290","abstract_canon_sha256":"73491660da28718b20b6765f09ecd6a18cfffc02b9e6028743ee788c06918e5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:19.655196Z","signature_b64":"3ZNoKqrWpl+NrpXXZQ+37BMAyuqxmldy8iLORd6udw5zngvMeDq7AC6oA+50x8/4SVUKHNgDj7OAhbwzvSmvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"872f65fac843ebd22619073fd5d4872e9aae4c2bbfa4a4ccb8f8ea0eaf248f8d","last_reissued_at":"2026-07-05T02:25:19.654699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:19.654699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of Similarity-based Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kazuaki Hanawa, Kentaro Inui, Satoshi Hara, Sho Yokoi","submitted_at":"2020-06-08T12:39:46Z","abstract_excerpt":"Explaining the predictions made by complex machine learning models helps users to understand and accept the predicted outputs with confidence. One promising way is to use similarity-based explanation that provides similar instances as evidence to support model predictions. Several relevance metrics are used for this purpose. In this study, we investigated relevance metrics that can provide reasonable explanations to users. Specifically, we adopted three tests to evaluate whether the relevance metrics satisfy the minimal requirements for similarity-based explanation. Our experiments revealed th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04528","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/2006.04528/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":"2006.04528","created_at":"2026-07-05T02:25:19.654762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04528v2","created_at":"2026-07-05T02:25:19.654762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04528","created_at":"2026-07-05T02:25:19.654762+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4XWL6WIIPV5","created_at":"2026-07-05T02:25:19.654762+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4XWL6WIIPV5EJQZ","created_at":"2026-07-05T02:25:19.654762+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4XWL6WI","created_at":"2026-07-05T02:25:19.654762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12147","citing_title":"Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q4XWL6WIIPV5EJQZA475LVEHF2","json":"https://pith.science/pith/Q4XWL6WIIPV5EJQZA475LVEHF2.json","graph_json":"https://pith.science/api/pith-number/Q4XWL6WIIPV5EJQZA475LVEHF2/graph.json","events_json":"https://pith.science/api/pith-number/Q4XWL6WIIPV5EJQZA475LVEHF2/events.json","paper":"https://pith.science/paper/Q4XWL6WI"},"agent_actions":{"view_html":"https://pith.science/pith/Q4XWL6WIIPV5EJQZA475LVEHF2","download_json":"https://pith.science/pith/Q4XWL6WIIPV5EJQZA475LVEHF2.json","view_paper":"https://pith.science/paper/Q4XWL6WI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04528&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4XWL6WIIPV5EJQZA475LVEHF2/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4XWL6WIIPV5EJQZA475LVEHF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4XWL6WIIPV5EJQZA475LVEHF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4XWL6WIIPV5EJQZA475LVEHF2/action/storage_attestation","attest_author":"https://pith.science/pith/Q4XWL6WIIPV5EJQZA475LVEHF2/action/author_attestation","sign_citation":"https://pith.science/pith/Q4XWL6WIIPV5EJQZA475LVEHF2/action/citation_signature","submit_replication":"https://pith.science/pith/Q4XWL6WIIPV5EJQZA475LVEHF2/action/replication_record"}},"created_at":"2026-07-05T02:25:19.654762+00:00","updated_at":"2026-07-05T02:25:19.654762+00:00"}