{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:34WJBXM4KNTZ7KNRZPDXTPNX4K","short_pith_number":"pith:34WJBXM4","schema_version":"1.0","canonical_sha256":"df2c90dd9c53679fa9b1cbc779bdb7e2a3414a890ce83c5ecaf0c50b9cf76541","source":{"kind":"arxiv","id":"2606.19635","version":1},"attestation_state":"computed","paper":{"title":"Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Aniruddh Nath, Baykal Cakici, Lichan Hong, Li Wei, Lukasz Heldt, Raghu Keshavan, Shao-Chuan Wang, Xilun Chen, Xinyang Xi","submitted_at":"2026-06-17T22:27:36Z","abstract_excerpt":"Large Recommendation Models (LRMs) have demonstrated promising capabilities in industry-scale recommendation tasks. However, holistically integrating traditional signals into these transformer-based architectures effectively and efficiently remains a major challenge. Conventional approaches that \"textualize\" these signals directly or create discrete item representations often lead to excessively long prompts, substantial memory footprints, and high computational overhead. To overcome these limitations, we propose \"Token Factory\", a framework designed to transform traditional signals into \"soft"},"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":"2606.19635","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-17T22:27:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"419cef17a905142292df86ca1a43fe7d8ac01bd360ea5fd349464ef53fb1aa00","abstract_canon_sha256":"858acaafbb65a64ec9c93158e69d6eac3e7e673fb61691365bf5095883746d12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:30.935980Z","signature_b64":"8AwWgSk90s2HpGtMDGvbyHD7iLNSMeuzIiHwtiUVluguaHjdD1y//aqOkTVxlm97q8ag2zMTaMqwGigXdAsMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df2c90dd9c53679fa9b1cbc779bdb7e2a3414a890ce83c5ecaf0c50b9cf76541","last_reissued_at":"2026-06-19T16:12:30.935627Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:30.935627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Aniruddh Nath, Baykal Cakici, Lichan Hong, Li Wei, Lukasz Heldt, Raghu Keshavan, Shao-Chuan Wang, Xilun Chen, Xinyang Xi","submitted_at":"2026-06-17T22:27:36Z","abstract_excerpt":"Large Recommendation Models (LRMs) have demonstrated promising capabilities in industry-scale recommendation tasks. However, holistically integrating traditional signals into these transformer-based architectures effectively and efficiently remains a major challenge. Conventional approaches that \"textualize\" these signals directly or create discrete item representations often lead to excessively long prompts, substantial memory footprints, and high computational overhead. To overcome these limitations, we propose \"Token Factory\", a framework designed to transform traditional signals into \"soft"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19635","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/2606.19635/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":"2606.19635","created_at":"2026-06-19T16:12:30.935690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19635v1","created_at":"2026-06-19T16:12:30.935690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19635","created_at":"2026-06-19T16:12:30.935690+00:00"},{"alias_kind":"pith_short_12","alias_value":"34WJBXM4KNTZ","created_at":"2026-06-19T16:12:30.935690+00:00"},{"alias_kind":"pith_short_16","alias_value":"34WJBXM4KNTZ7KNR","created_at":"2026-06-19T16:12:30.935690+00:00"},{"alias_kind":"pith_short_8","alias_value":"34WJBXM4","created_at":"2026-06-19T16:12:30.935690+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/34WJBXM4KNTZ7KNRZPDXTPNX4K","json":"https://pith.science/pith/34WJBXM4KNTZ7KNRZPDXTPNX4K.json","graph_json":"https://pith.science/api/pith-number/34WJBXM4KNTZ7KNRZPDXTPNX4K/graph.json","events_json":"https://pith.science/api/pith-number/34WJBXM4KNTZ7KNRZPDXTPNX4K/events.json","paper":"https://pith.science/paper/34WJBXM4"},"agent_actions":{"view_html":"https://pith.science/pith/34WJBXM4KNTZ7KNRZPDXTPNX4K","download_json":"https://pith.science/pith/34WJBXM4KNTZ7KNRZPDXTPNX4K.json","view_paper":"https://pith.science/paper/34WJBXM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19635&json=true","fetch_graph":"https://pith.science/api/pith-number/34WJBXM4KNTZ7KNRZPDXTPNX4K/graph.json","fetch_events":"https://pith.science/api/pith-number/34WJBXM4KNTZ7KNRZPDXTPNX4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34WJBXM4KNTZ7KNRZPDXTPNX4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34WJBXM4KNTZ7KNRZPDXTPNX4K/action/storage_attestation","attest_author":"https://pith.science/pith/34WJBXM4KNTZ7KNRZPDXTPNX4K/action/author_attestation","sign_citation":"https://pith.science/pith/34WJBXM4KNTZ7KNRZPDXTPNX4K/action/citation_signature","submit_replication":"https://pith.science/pith/34WJBXM4KNTZ7KNRZPDXTPNX4K/action/replication_record"}},"created_at":"2026-06-19T16:12:30.935690+00:00","updated_at":"2026-06-19T16:12:30.935690+00:00"}