{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YCP6BX7DCRJBHHSUDL4FRCJ6BD","short_pith_number":"pith:YCP6BX7D","schema_version":"1.0","canonical_sha256":"c09fe0dfe31452139e541af858893e08d0785a990c58bd645c99d8511e40d710","source":{"kind":"arxiv","id":"2509.01184","version":1},"attestation_state":"computed","paper":{"title":"MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Binhao Wang, Chao Feng, Fuzhen Zhuang, Shanqi Liu, Shukuan Wang, Xiang Li, Yanze Zhang, Yutian Xiao, Zhao Zhang","submitted_at":"2025-09-01T07:08:44Z","abstract_excerpt":"Click-through rate (CTR) prediction serves as a cornerstone of recommender systems. Despite the strong performance of current CTR models based on user behavior modeling, they are still severely limited by interaction sparsity, especially in low-active user scenarios. To address this issue, data augmentation of user behavior is a promising research direction. However, existing data augmentation methods heavily rely on collaborative signals while overlooking the rich multimodal features of items, leading to insufficient modeling of low-active users.\n  To alleviate this problem, we propose a nove"},"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":"2509.01184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-09-01T07:08:44Z","cross_cats_sorted":[],"title_canon_sha256":"63b1b925210fb3f79b04365a34b68634eef57a222f30714f95d41189c7930a05","abstract_canon_sha256":"691d69ab2e56ae8879fdfd46c8407d58bd4f3d0276c9dd2ce955ec9b3516bd36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:55.673291Z","signature_b64":"K8mAlacDnRtzMtTPM8MBGlAnrLbldq5Tgfz4USnFjzsB3BKUenNNc+OCVcsLb+lXRw/8h/6T2jL0OlSI1FitBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c09fe0dfe31452139e541af858893e08d0785a990c58bd645c99d8511e40d710","last_reissued_at":"2026-07-05T12:02:55.672780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:55.672780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Binhao Wang, Chao Feng, Fuzhen Zhuang, Shanqi Liu, Shukuan Wang, Xiang Li, Yanze Zhang, Yutian Xiao, Zhao Zhang","submitted_at":"2025-09-01T07:08:44Z","abstract_excerpt":"Click-through rate (CTR) prediction serves as a cornerstone of recommender systems. Despite the strong performance of current CTR models based on user behavior modeling, they are still severely limited by interaction sparsity, especially in low-active user scenarios. To address this issue, data augmentation of user behavior is a promising research direction. However, existing data augmentation methods heavily rely on collaborative signals while overlooking the rich multimodal features of items, leading to insufficient modeling of low-active users.\n  To alleviate this problem, we propose a nove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01184","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/2509.01184/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":"2509.01184","created_at":"2026-07-05T12:02:55.672842+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01184v1","created_at":"2026-07-05T12:02:55.672842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01184","created_at":"2026-07-05T12:02:55.672842+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCP6BX7DCRJB","created_at":"2026-07-05T12:02:55.672842+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCP6BX7DCRJBHHSU","created_at":"2026-07-05T12:02:55.672842+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCP6BX7D","created_at":"2026-07-05T12:02:55.672842+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24605","citing_title":"ScaleToT: Generalizing Structured LLM Reasoning for Billion-Scale Low-Activity User Modeling","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YCP6BX7DCRJBHHSUDL4FRCJ6BD","json":"https://pith.science/pith/YCP6BX7DCRJBHHSUDL4FRCJ6BD.json","graph_json":"https://pith.science/api/pith-number/YCP6BX7DCRJBHHSUDL4FRCJ6BD/graph.json","events_json":"https://pith.science/api/pith-number/YCP6BX7DCRJBHHSUDL4FRCJ6BD/events.json","paper":"https://pith.science/paper/YCP6BX7D"},"agent_actions":{"view_html":"https://pith.science/pith/YCP6BX7DCRJBHHSUDL4FRCJ6BD","download_json":"https://pith.science/pith/YCP6BX7DCRJBHHSUDL4FRCJ6BD.json","view_paper":"https://pith.science/paper/YCP6BX7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01184&json=true","fetch_graph":"https://pith.science/api/pith-number/YCP6BX7DCRJBHHSUDL4FRCJ6BD/graph.json","fetch_events":"https://pith.science/api/pith-number/YCP6BX7DCRJBHHSUDL4FRCJ6BD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCP6BX7DCRJBHHSUDL4FRCJ6BD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCP6BX7DCRJBHHSUDL4FRCJ6BD/action/storage_attestation","attest_author":"https://pith.science/pith/YCP6BX7DCRJBHHSUDL4FRCJ6BD/action/author_attestation","sign_citation":"https://pith.science/pith/YCP6BX7DCRJBHHSUDL4FRCJ6BD/action/citation_signature","submit_replication":"https://pith.science/pith/YCP6BX7DCRJBHHSUDL4FRCJ6BD/action/replication_record"}},"created_at":"2026-07-05T12:02:55.672842+00:00","updated_at":"2026-07-05T12:02:55.672842+00:00"}