{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D2SWHHHLI5IEQCDRKGYBR2LY3S","short_pith_number":"pith:D2SWHHHL","schema_version":"1.0","canonical_sha256":"1ea5639ceb475048087151b018e978dc82dc74a5845b2933bcaee1e3f4e978a1","source":{"kind":"arxiv","id":"2503.22675","version":3},"attestation_state":"computed","paper":{"title":"Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Jiakai Tang, Jian Wu, Jun Xu, Sunhao Dai, Teng Shi, Wen Chen, Xu Chen, Yuning Jiang","submitted_at":"2025-03-28T17:59:03Z","abstract_excerpt":"Sequential Recommendation (SeqRec) aims to predict the next item by capturing sequential patterns from users' historical interactions, playing a crucial role in many real-world recommender systems. However, existing approaches predominantly adopt a direct forward computation paradigm, where the final hidden state of the sequence encoder serves as the user representation. We argue that this inference paradigm, due to its limited computational depth, struggles to model the complex evolving nature of user preferences and lacks a nuanced understanding of long-tail items, leading to suboptimal perf"},"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":"2503.22675","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-03-28T17:59:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d183444a0e12a3d37137c95b338e44a5b7481c42370565f837d182859bbbf245","abstract_canon_sha256":"478682e7ef155a080223178ad590d7baee75ad2c839dff773a53c3be0e14c500"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:41.544904Z","signature_b64":"rHB397rhPlA8YOOEoxfn2M6q8LtVky81+qwr1YX2h7ihFnckosPMNMm3jwr1adMEHWaRDPhG6lkOoDylWLzBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ea5639ceb475048087151b018e978dc82dc74a5845b2933bcaee1e3f4e978a1","last_reissued_at":"2026-07-05T11:46:41.544406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:41.544406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Jiakai Tang, Jian Wu, Jun Xu, Sunhao Dai, Teng Shi, Wen Chen, Xu Chen, Yuning Jiang","submitted_at":"2025-03-28T17:59:03Z","abstract_excerpt":"Sequential Recommendation (SeqRec) aims to predict the next item by capturing sequential patterns from users' historical interactions, playing a crucial role in many real-world recommender systems. However, existing approaches predominantly adopt a direct forward computation paradigm, where the final hidden state of the sequence encoder serves as the user representation. We argue that this inference paradigm, due to its limited computational depth, struggles to model the complex evolving nature of user preferences and lacks a nuanced understanding of long-tail items, leading to suboptimal perf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22675","kind":"arxiv","version":3},"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/2503.22675/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":"2503.22675","created_at":"2026-07-05T11:46:41.544464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22675v3","created_at":"2026-07-05T11:46:41.544464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22675","created_at":"2026-07-05T11:46:41.544464+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2SWHHHLI5IE","created_at":"2026-07-05T11:46:41.544464+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2SWHHHLI5IEQCDR","created_at":"2026-07-05T11:46:41.544464+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2SWHHHL","created_at":"2026-07-05T11:46:41.544464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07075","citing_title":"Beyond Matching: Category-Guided Latent Intent Reasoning for Generative Retrieval in E-Commerce","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06970","citing_title":"SSRLive: Live Streaming Recommendation with Dynamic Semantic ID","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03727","citing_title":"When Does Latent Reasoning Help? MeRa: Metric-Space Bias for Spatial Prediction","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03221","citing_title":"VirtualMLE: A Virtual ML Engineer that Optimizes Sequential Recommenders","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28888","citing_title":"Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06947","citing_title":"DREAM: Dynamic Refinement of Early Assignment Mappings","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2601.18664","citing_title":"S$^2$GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18769","citing_title":"ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17648","citing_title":"SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2510.27157","citing_title":"A Survey on Generative Recommendation: Data, Model, and Tasks","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22925","citing_title":"BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2503.16419","citing_title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26760","citing_title":"Factorized Latent Reasoning for LLM-based Recommendation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06165","citing_title":"Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost","ref_index":189,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19550","citing_title":"LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12110","citing_title":"SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2SWHHHLI5IEQCDRKGYBR2LY3S","json":"https://pith.science/pith/D2SWHHHLI5IEQCDRKGYBR2LY3S.json","graph_json":"https://pith.science/api/pith-number/D2SWHHHLI5IEQCDRKGYBR2LY3S/graph.json","events_json":"https://pith.science/api/pith-number/D2SWHHHLI5IEQCDRKGYBR2LY3S/events.json","paper":"https://pith.science/paper/D2SWHHHL"},"agent_actions":{"view_html":"https://pith.science/pith/D2SWHHHLI5IEQCDRKGYBR2LY3S","download_json":"https://pith.science/pith/D2SWHHHLI5IEQCDRKGYBR2LY3S.json","view_paper":"https://pith.science/paper/D2SWHHHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22675&json=true","fetch_graph":"https://pith.science/api/pith-number/D2SWHHHLI5IEQCDRKGYBR2LY3S/graph.json","fetch_events":"https://pith.science/api/pith-number/D2SWHHHLI5IEQCDRKGYBR2LY3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2SWHHHLI5IEQCDRKGYBR2LY3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2SWHHHLI5IEQCDRKGYBR2LY3S/action/storage_attestation","attest_author":"https://pith.science/pith/D2SWHHHLI5IEQCDRKGYBR2LY3S/action/author_attestation","sign_citation":"https://pith.science/pith/D2SWHHHLI5IEQCDRKGYBR2LY3S/action/citation_signature","submit_replication":"https://pith.science/pith/D2SWHHHLI5IEQCDRKGYBR2LY3S/action/replication_record"}},"created_at":"2026-07-05T11:46:41.544464+00:00","updated_at":"2026-07-05T11:46:41.544464+00:00"}