{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7ZZJVM2EO2HSMWOQBLSXWBSR7D","short_pith_number":"pith:7ZZJVM2E","schema_version":"1.0","canonical_sha256":"fe729ab344768f2659d00ae57b0651f8da52c27641756f3b1ac7729bbde1c542","source":{"kind":"arxiv","id":"2006.10966","version":1},"attestation_state":"computed","paper":{"title":"Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dehua Cheng, Eric Zhou, Hanpeng Liu, Michael Tsang, Xue Feng, Yan Liu","submitted_at":"2020-06-19T05:14:34Z","abstract_excerpt":"Recommendation is a prevalent application of machine learning that affects many users; therefore, it is important for recommender models to be accurate and interpretable. In this work, we propose a method to both interpret and augment the predictions of black-box recommender systems. In particular, we propose to interpret feature interactions from a source recommender model and explicitly encode these interactions in a target recommender model, where both source and target models are black-boxes. By not assuming the structure of the recommender system, our approach can be used in general setti"},"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":"2006.10966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-19T05:14:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f5630754687520e9b5863cff011bbe36233661e77e154ad3215b07512e8eb9f2","abstract_canon_sha256":"618ce935d807ec6dbb94e82de4f7fa2299b526f55e969db9b89dbe1463a88b92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:27.401452Z","signature_b64":"/yks4O3/M2fSxPukkWVxYLj0huiD3tveWm8T3vmDJEuXjjzvUptz9ap/DYoapuNdDX63aAPmdaOxYiA2d49XDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe729ab344768f2659d00ae57b0651f8da52c27641756f3b1ac7729bbde1c542","last_reissued_at":"2026-07-05T01:11:27.400803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:27.400803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dehua Cheng, Eric Zhou, Hanpeng Liu, Michael Tsang, Xue Feng, Yan Liu","submitted_at":"2020-06-19T05:14:34Z","abstract_excerpt":"Recommendation is a prevalent application of machine learning that affects many users; therefore, it is important for recommender models to be accurate and interpretable. In this work, we propose a method to both interpret and augment the predictions of black-box recommender systems. In particular, we propose to interpret feature interactions from a source recommender model and explicitly encode these interactions in a target recommender model, where both source and target models are black-boxes. By not assuming the structure of the recommender system, our approach can be used in general setti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10966","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/2006.10966/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":"2006.10966","created_at":"2026-07-05T01:11:27.400884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10966v1","created_at":"2026-07-05T01:11:27.400884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10966","created_at":"2026-07-05T01:11:27.400884+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ZZJVM2EO2HS","created_at":"2026-07-05T01:11:27.400884+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ZZJVM2EO2HSMWOQ","created_at":"2026-07-05T01:11:27.400884+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ZZJVM2E","created_at":"2026-07-05T01:11:27.400884+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17248","citing_title":"Efficient Quantification of Multimodal Interaction at Sample Level","ref_index":2018,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ZZJVM2EO2HSMWOQBLSXWBSR7D","json":"https://pith.science/pith/7ZZJVM2EO2HSMWOQBLSXWBSR7D.json","graph_json":"https://pith.science/api/pith-number/7ZZJVM2EO2HSMWOQBLSXWBSR7D/graph.json","events_json":"https://pith.science/api/pith-number/7ZZJVM2EO2HSMWOQBLSXWBSR7D/events.json","paper":"https://pith.science/paper/7ZZJVM2E"},"agent_actions":{"view_html":"https://pith.science/pith/7ZZJVM2EO2HSMWOQBLSXWBSR7D","download_json":"https://pith.science/pith/7ZZJVM2EO2HSMWOQBLSXWBSR7D.json","view_paper":"https://pith.science/paper/7ZZJVM2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10966&json=true","fetch_graph":"https://pith.science/api/pith-number/7ZZJVM2EO2HSMWOQBLSXWBSR7D/graph.json","fetch_events":"https://pith.science/api/pith-number/7ZZJVM2EO2HSMWOQBLSXWBSR7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ZZJVM2EO2HSMWOQBLSXWBSR7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ZZJVM2EO2HSMWOQBLSXWBSR7D/action/storage_attestation","attest_author":"https://pith.science/pith/7ZZJVM2EO2HSMWOQBLSXWBSR7D/action/author_attestation","sign_citation":"https://pith.science/pith/7ZZJVM2EO2HSMWOQBLSXWBSR7D/action/citation_signature","submit_replication":"https://pith.science/pith/7ZZJVM2EO2HSMWOQBLSXWBSR7D/action/replication_record"}},"created_at":"2026-07-05T01:11:27.400884+00:00","updated_at":"2026-07-05T01:11:27.400884+00:00"}