{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CJ7VKDR25VYZLUNBPB4XOQKPWO","short_pith_number":"pith:CJ7VKDR2","schema_version":"1.0","canonical_sha256":"127f550e3aed7195d1a1787977414fb3a7bd02ded458f574896391726eee05d9","source":{"kind":"arxiv","id":"2602.14110","version":2},"attestation_state":"computed","paper":{"title":"MixFormer: Co-Scaling Up Dense and Sequence in Industrial Recommenders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hao Zhang, Jinan Ni, Qiwei Chen, Xu Huang, Yuchao Zheng, Yunwen Huang, Zheng Chai, Zhifang Fan, Zhuoxing Wei","submitted_at":"2026-02-15T11:53:30Z","abstract_excerpt":"As industrial recommender systems enter a scaling-driven regime, Transformer architectures have become increasingly attractive for scaling models towards larger capacity and longer sequence. However, existing Transformer-based recommendation models remain structurally fragmented, where sequence modeling and feature interaction are implemented as separate modules with independent parameterization. Such designs introduce a fundamental co-scaling challenge, as model capacity must be suboptimally allocated between dense feature interaction and sequence modeling under a limited computational budget"},"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":"2602.14110","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-02-15T11:53:30Z","cross_cats_sorted":[],"title_canon_sha256":"0fbb1e82dcae2fd1bc04f1789a16169f440560c3b99c454ca76d669ec06ec688","abstract_canon_sha256":"7a19c22cffac8ed3e2971f13ad9a4c365c7dde16a0f9bb3ade091428345fd863"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:16:51.861514Z","signature_b64":"lyqB0itniyd3xCqu5FskcwR5FY99TZhh56+n9bnqjWEFkRv0OMg7doBKQQPmbLdxNyGyxg1d9vsexQN71opACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"127f550e3aed7195d1a1787977414fb3a7bd02ded458f574896391726eee05d9","last_reissued_at":"2026-07-03T01:16:51.860965Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:16:51.860965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MixFormer: Co-Scaling Up Dense and Sequence in Industrial Recommenders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hao Zhang, Jinan Ni, Qiwei Chen, Xu Huang, Yuchao Zheng, Yunwen Huang, Zheng Chai, Zhifang Fan, Zhuoxing Wei","submitted_at":"2026-02-15T11:53:30Z","abstract_excerpt":"As industrial recommender systems enter a scaling-driven regime, Transformer architectures have become increasingly attractive for scaling models towards larger capacity and longer sequence. However, existing Transformer-based recommendation models remain structurally fragmented, where sequence modeling and feature interaction are implemented as separate modules with independent parameterization. Such designs introduce a fundamental co-scaling challenge, as model capacity must be suboptimally allocated between dense feature interaction and sequence modeling under a limited computational budget"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14110","kind":"arxiv","version":2},"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/2602.14110/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":"2602.14110","created_at":"2026-07-03T01:16:51.861032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.14110v2","created_at":"2026-07-03T01:16:51.861032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14110","created_at":"2026-07-03T01:16:51.861032+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJ7VKDR25VYZ","created_at":"2026-07-03T01:16:51.861032+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJ7VKDR25VYZLUNB","created_at":"2026-07-03T01:16:51.861032+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJ7VKDR2","created_at":"2026-07-03T01:16:51.861032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2605.25583","citing_title":"LENS: A Staged Design for Interaction Granularity in Sequential CTR Prediction","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27243","citing_title":"NOVA: A Verification-Aware Agent Harness for Architecture Evolution in Industrial Recommender Systems","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15650","citing_title":"Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17878","citing_title":"RankUp: Towards High-rank Representations for Large Scale Advertising Recommender Systems","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19550","citing_title":"LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17878","citing_title":"RankUp: Towards High-rank Representations for Large Scale Advertising Recommender Systems","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15650","citing_title":"Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJ7VKDR25VYZLUNBPB4XOQKPWO","json":"https://pith.science/pith/CJ7VKDR25VYZLUNBPB4XOQKPWO.json","graph_json":"https://pith.science/api/pith-number/CJ7VKDR25VYZLUNBPB4XOQKPWO/graph.json","events_json":"https://pith.science/api/pith-number/CJ7VKDR25VYZLUNBPB4XOQKPWO/events.json","paper":"https://pith.science/paper/CJ7VKDR2"},"agent_actions":{"view_html":"https://pith.science/pith/CJ7VKDR25VYZLUNBPB4XOQKPWO","download_json":"https://pith.science/pith/CJ7VKDR25VYZLUNBPB4XOQKPWO.json","view_paper":"https://pith.science/paper/CJ7VKDR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.14110&json=true","fetch_graph":"https://pith.science/api/pith-number/CJ7VKDR25VYZLUNBPB4XOQKPWO/graph.json","fetch_events":"https://pith.science/api/pith-number/CJ7VKDR25VYZLUNBPB4XOQKPWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJ7VKDR25VYZLUNBPB4XOQKPWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJ7VKDR25VYZLUNBPB4XOQKPWO/action/storage_attestation","attest_author":"https://pith.science/pith/CJ7VKDR25VYZLUNBPB4XOQKPWO/action/author_attestation","sign_citation":"https://pith.science/pith/CJ7VKDR25VYZLUNBPB4XOQKPWO/action/citation_signature","submit_replication":"https://pith.science/pith/CJ7VKDR25VYZLUNBPB4XOQKPWO/action/replication_record"}},"created_at":"2026-07-03T01:16:51.861032+00:00","updated_at":"2026-07-03T01:16:51.861032+00:00"}