{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DW34Q44V6CS7VPXRBDCE23ERVM","short_pith_number":"pith:DW34Q44V","schema_version":"1.0","canonical_sha256":"1db7c87395f0a5fabef108c44d6c91ab023a410beb572e06de78ae5be7c00b48","source":{"kind":"arxiv","id":"2202.01153","version":1},"attestation_state":"computed","paper":{"title":"Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amit Dhurandhar, Dennis Wei, Karthikeyan Natesan Ramamurthy, Zaid Bin Tariq","submitted_at":"2022-02-02T17:28:56Z","abstract_excerpt":"Post-hoc explanations for black box models have been studied extensively in classification and regression settings. However, explanations for models that output similarity between two inputs have received comparatively lesser attention. In this paper, we provide model agnostic local explanations for similarity learners applicable to tabular and text data. We first propose a method that provides feature attributions to explain the similarity between a pair of inputs as determined by a black box similarity learner. We then propose analogies as a new form of explanation in machine learning. Here "},"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":"2202.01153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-02T17:28:56Z","cross_cats_sorted":[],"title_canon_sha256":"fe1369273e7ffbb88094b3bbb4cf45007f34001c0ee2dbf5cb5a8bc561fe8a30","abstract_canon_sha256":"a7df3c3b3f474e4b7b77613f4e6b93195a0323b21d31a5ac0046e66fccb1f45d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:53:42.316391Z","signature_b64":"STl5IftYIRO0gNj63a4PsE+VhOKpBNpqY4KDa2or/Mnu8R2nCvk+mC9qsJk3TABloD56u/nyULexK+y50BvmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1db7c87395f0a5fabef108c44d6c91ab023a410beb572e06de78ae5be7c00b48","last_reissued_at":"2026-07-05T03:53:42.315947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:53:42.315947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amit Dhurandhar, Dennis Wei, Karthikeyan Natesan Ramamurthy, Zaid Bin Tariq","submitted_at":"2022-02-02T17:28:56Z","abstract_excerpt":"Post-hoc explanations for black box models have been studied extensively in classification and regression settings. However, explanations for models that output similarity between two inputs have received comparatively lesser attention. In this paper, we provide model agnostic local explanations for similarity learners applicable to tabular and text data. We first propose a method that provides feature attributions to explain the similarity between a pair of inputs as determined by a black box similarity learner. We then propose analogies as a new form of explanation in machine learning. Here "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01153","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/2202.01153/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":"2202.01153","created_at":"2026-07-05T03:53:42.316007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.01153v1","created_at":"2026-07-05T03:53:42.316007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01153","created_at":"2026-07-05T03:53:42.316007+00:00"},{"alias_kind":"pith_short_12","alias_value":"DW34Q44V6CS7","created_at":"2026-07-05T03:53:42.316007+00:00"},{"alias_kind":"pith_short_16","alias_value":"DW34Q44V6CS7VPXR","created_at":"2026-07-05T03:53:42.316007+00:00"},{"alias_kind":"pith_short_8","alias_value":"DW34Q44V","created_at":"2026-07-05T03:53:42.316007+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/DW34Q44V6CS7VPXRBDCE23ERVM","json":"https://pith.science/pith/DW34Q44V6CS7VPXRBDCE23ERVM.json","graph_json":"https://pith.science/api/pith-number/DW34Q44V6CS7VPXRBDCE23ERVM/graph.json","events_json":"https://pith.science/api/pith-number/DW34Q44V6CS7VPXRBDCE23ERVM/events.json","paper":"https://pith.science/paper/DW34Q44V"},"agent_actions":{"view_html":"https://pith.science/pith/DW34Q44V6CS7VPXRBDCE23ERVM","download_json":"https://pith.science/pith/DW34Q44V6CS7VPXRBDCE23ERVM.json","view_paper":"https://pith.science/paper/DW34Q44V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.01153&json=true","fetch_graph":"https://pith.science/api/pith-number/DW34Q44V6CS7VPXRBDCE23ERVM/graph.json","fetch_events":"https://pith.science/api/pith-number/DW34Q44V6CS7VPXRBDCE23ERVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DW34Q44V6CS7VPXRBDCE23ERVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DW34Q44V6CS7VPXRBDCE23ERVM/action/storage_attestation","attest_author":"https://pith.science/pith/DW34Q44V6CS7VPXRBDCE23ERVM/action/author_attestation","sign_citation":"https://pith.science/pith/DW34Q44V6CS7VPXRBDCE23ERVM/action/citation_signature","submit_replication":"https://pith.science/pith/DW34Q44V6CS7VPXRBDCE23ERVM/action/replication_record"}},"created_at":"2026-07-05T03:53:42.316007+00:00","updated_at":"2026-07-05T03:53:42.316007+00:00"}