{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MCIUQITUC33RJV2ZLHWXAPFM7P","short_pith_number":"pith:MCIUQITU","schema_version":"1.0","canonical_sha256":"609148227416f714d75959ed703cacfbf3924ea635f36965160dabcc53c07103","source":{"kind":"arxiv","id":"2504.06609","version":1},"attestation_state":"computed","paper":{"title":"InteractRank: Personalized Web-Scale Search Pre-Ranking with Cross Interaction Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Aditya Subramanian, Bhawna Juneja, Jaewon Yang, Prabhat Agarwal, Sujay Khandagale, Yuting Wang","submitted_at":"2025-04-09T06:13:58Z","abstract_excerpt":"Modern search systems use a multi-stage architecture to deliver personalized results efficiently. Key stages include retrieval, pre-ranking, full ranking, and blending, which refine billions of items to top selections. The pre-ranking stage, vital for scoring and filtering hundreds of thousands of items down to a few thousand, typically relies on two tower models due to their computational efficiency, despite often lacking in capturing complex interactions. While query-item cross interaction features are paramount for full ranking, integrating them into pre-ranking models presents efficiency-r"},"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":"2504.06609","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-09T06:13:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d6e54f1a2dec4f4d18ae60ed282ec4e6bbb930da43dc73bcf051d4632fd96c46","abstract_canon_sha256":"9a97ecc42f9e1a24f4b3550ceb79ec35fd09b5c89f11af310e019150f5d5808d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:29.792599Z","signature_b64":"AANhFPdnU9uGTLaeQDYuXMi5hFb65q3Nah+vlKx+qA0aDhO5MDn1w8r7gqPZAkcu5K8nnhPLznlyzsO9PH9wCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"609148227416f714d75959ed703cacfbf3924ea635f36965160dabcc53c07103","last_reissued_at":"2026-07-05T10:46:29.792140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:29.792140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InteractRank: Personalized Web-Scale Search Pre-Ranking with Cross Interaction Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Aditya Subramanian, Bhawna Juneja, Jaewon Yang, Prabhat Agarwal, Sujay Khandagale, Yuting Wang","submitted_at":"2025-04-09T06:13:58Z","abstract_excerpt":"Modern search systems use a multi-stage architecture to deliver personalized results efficiently. Key stages include retrieval, pre-ranking, full ranking, and blending, which refine billions of items to top selections. The pre-ranking stage, vital for scoring and filtering hundreds of thousands of items down to a few thousand, typically relies on two tower models due to their computational efficiency, despite often lacking in capturing complex interactions. While query-item cross interaction features are paramount for full ranking, integrating them into pre-ranking models presents efficiency-r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06609","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/2504.06609/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":"2504.06609","created_at":"2026-07-05T10:46:29.792197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.06609v1","created_at":"2026-07-05T10:46:29.792197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06609","created_at":"2026-07-05T10:46:29.792197+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCIUQITUC33R","created_at":"2026-07-05T10:46:29.792197+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCIUQITUC33RJV2Z","created_at":"2026-07-05T10:46:29.792197+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCIUQITU","created_at":"2026-07-05T10:46:29.792197+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/MCIUQITUC33RJV2ZLHWXAPFM7P","json":"https://pith.science/pith/MCIUQITUC33RJV2ZLHWXAPFM7P.json","graph_json":"https://pith.science/api/pith-number/MCIUQITUC33RJV2ZLHWXAPFM7P/graph.json","events_json":"https://pith.science/api/pith-number/MCIUQITUC33RJV2ZLHWXAPFM7P/events.json","paper":"https://pith.science/paper/MCIUQITU"},"agent_actions":{"view_html":"https://pith.science/pith/MCIUQITUC33RJV2ZLHWXAPFM7P","download_json":"https://pith.science/pith/MCIUQITUC33RJV2ZLHWXAPFM7P.json","view_paper":"https://pith.science/paper/MCIUQITU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.06609&json=true","fetch_graph":"https://pith.science/api/pith-number/MCIUQITUC33RJV2ZLHWXAPFM7P/graph.json","fetch_events":"https://pith.science/api/pith-number/MCIUQITUC33RJV2ZLHWXAPFM7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCIUQITUC33RJV2ZLHWXAPFM7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCIUQITUC33RJV2ZLHWXAPFM7P/action/storage_attestation","attest_author":"https://pith.science/pith/MCIUQITUC33RJV2ZLHWXAPFM7P/action/author_attestation","sign_citation":"https://pith.science/pith/MCIUQITUC33RJV2ZLHWXAPFM7P/action/citation_signature","submit_replication":"https://pith.science/pith/MCIUQITUC33RJV2ZLHWXAPFM7P/action/replication_record"}},"created_at":"2026-07-05T10:46:29.792197+00:00","updated_at":"2026-07-05T10:46:29.792197+00:00"}