{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NSXUWN2Y6Z4LFGBQ33JT45ARP2","short_pith_number":"pith:NSXUWN2Y","schema_version":"1.0","canonical_sha256":"6caf4b3758f678b29830ded33e74117e8a66614e7a1a159d40ec800ec5907666","source":{"kind":"arxiv","id":"2412.01985","version":1},"attestation_state":"computed","paper":{"title":"Improving feature interactions at Pinterest under industry constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Aditya Mantha, Dhruvil Deven Badani, Matthew Lawhon, Siddarth Malreddy, Usha Amrutha Nookala","submitted_at":"2024-12-02T21:29:16Z","abstract_excerpt":"Adopting advances in recommendation systems is often challenging in industrial settings due to unique constraints. This paper aims to highlight these constraints through the lens of feature interactions. Feature interactions are critical for accurately predicting user behavior in recommendation systems and online advertising. Despite numerous novel techniques showing superior performance on benchmark datasets like Criteo, their direct application in industrial settings is hindered by constraints such as model latency, GPU memory limitations and model reproducibility. In this paper, we share ou"},"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":"2412.01985","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-02T21:29:16Z","cross_cats_sorted":[],"title_canon_sha256":"15573e770edf715c1c97b6b0ef85939bd2549374650ba1ec7f90abb1c46568f4","abstract_canon_sha256":"a13a838eaad991ad6caf69ced1c85c7b23837281a9820d0a6964da8d2752999b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:41.917197Z","signature_b64":"BvI2Shvo2jaid7NKabLN4L7YC3X75Tns0rxGdw7JRVHDSqs8CgPwzqXjLaIsRdzcqZI9GA0BcviPaSMX7ywiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6caf4b3758f678b29830ded33e74117e8a66614e7a1a159d40ec800ec5907666","last_reissued_at":"2026-07-05T09:43:41.916706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:41.916706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving feature interactions at Pinterest under industry constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Aditya Mantha, Dhruvil Deven Badani, Matthew Lawhon, Siddarth Malreddy, Usha Amrutha Nookala","submitted_at":"2024-12-02T21:29:16Z","abstract_excerpt":"Adopting advances in recommendation systems is often challenging in industrial settings due to unique constraints. This paper aims to highlight these constraints through the lens of feature interactions. Feature interactions are critical for accurately predicting user behavior in recommendation systems and online advertising. Despite numerous novel techniques showing superior performance on benchmark datasets like Criteo, their direct application in industrial settings is hindered by constraints such as model latency, GPU memory limitations and model reproducibility. In this paper, we share ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01985","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/2412.01985/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":"2412.01985","created_at":"2026-07-05T09:43:41.916763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01985v1","created_at":"2026-07-05T09:43:41.916763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01985","created_at":"2026-07-05T09:43:41.916763+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSXUWN2Y6Z4L","created_at":"2026-07-05T09:43:41.916763+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSXUWN2Y6Z4LFGBQ","created_at":"2026-07-05T09:43:41.916763+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSXUWN2Y","created_at":"2026-07-05T09:43:41.916763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02267","citing_title":"TransAct V2: Lifelong User Action Sequence Modeling on Pinterest Recommendation","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NSXUWN2Y6Z4LFGBQ33JT45ARP2","json":"https://pith.science/pith/NSXUWN2Y6Z4LFGBQ33JT45ARP2.json","graph_json":"https://pith.science/api/pith-number/NSXUWN2Y6Z4LFGBQ33JT45ARP2/graph.json","events_json":"https://pith.science/api/pith-number/NSXUWN2Y6Z4LFGBQ33JT45ARP2/events.json","paper":"https://pith.science/paper/NSXUWN2Y"},"agent_actions":{"view_html":"https://pith.science/pith/NSXUWN2Y6Z4LFGBQ33JT45ARP2","download_json":"https://pith.science/pith/NSXUWN2Y6Z4LFGBQ33JT45ARP2.json","view_paper":"https://pith.science/paper/NSXUWN2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01985&json=true","fetch_graph":"https://pith.science/api/pith-number/NSXUWN2Y6Z4LFGBQ33JT45ARP2/graph.json","fetch_events":"https://pith.science/api/pith-number/NSXUWN2Y6Z4LFGBQ33JT45ARP2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSXUWN2Y6Z4LFGBQ33JT45ARP2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSXUWN2Y6Z4LFGBQ33JT45ARP2/action/storage_attestation","attest_author":"https://pith.science/pith/NSXUWN2Y6Z4LFGBQ33JT45ARP2/action/author_attestation","sign_citation":"https://pith.science/pith/NSXUWN2Y6Z4LFGBQ33JT45ARP2/action/citation_signature","submit_replication":"https://pith.science/pith/NSXUWN2Y6Z4LFGBQ33JT45ARP2/action/replication_record"}},"created_at":"2026-07-05T09:43:41.916763+00:00","updated_at":"2026-07-05T09:43:41.916763+00:00"}