{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UY7H35MERQSYXDTY5YJJNZNA44","short_pith_number":"pith:UY7H35ME","schema_version":"1.0","canonical_sha256":"a63e7df5848c258b8e78ee1296e5a0e72244d7a0d5fb04e80a3b0e658e815063","source":{"kind":"arxiv","id":"2312.10325","version":2},"attestation_state":"computed","paper":{"title":"An Attentive Inductive Bias for Sequential Recommendation beyond the Self-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Hyowon Wi, Jeongwhan Choi, Noseong Park, Yehjin Shin","submitted_at":"2023-12-16T05:23:08Z","abstract_excerpt":"Sequential recommendation (SR) models based on Transformers have achieved remarkable successes. The self-attention mechanism of Transformers for computer vision and natural language processing suffers from the oversmoothing problem, i.e., hidden representations becoming similar to tokens. In the SR domain, we, for the first time, show that the same problem occurs. We present pioneering investigations that reveal the low-pass filtering nature of self-attention in the SR, which causes oversmoothing. To this end, we propose a novel method called $\\textbf{B}$eyond $\\textbf{S}$elf-$\\textbf{A}$ttent"},"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":"2312.10325","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-16T05:23:08Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"7ea1258a4b8c867abad93d8e34d64f332a7bd1bd8f62069aa5afbbc028336e70","abstract_canon_sha256":"cd9762200ba4aac2d978be491d64d13914bf2d86aaac70ca7d13a6ef85a4f115"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:28.822800Z","signature_b64":"rLiO5ez12yuL0O4BxjHT1HkVT+oWXlm00DSC3aGVG3NprJjwkBAanYM/G47mQqs2HIBinNSLuXmDrD6chjpdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a63e7df5848c258b8e78ee1296e5a0e72244d7a0d5fb04e80a3b0e658e815063","last_reissued_at":"2026-07-05T07:46:28.822258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:28.822258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Attentive Inductive Bias for Sequential Recommendation beyond the Self-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Hyowon Wi, Jeongwhan Choi, Noseong Park, Yehjin Shin","submitted_at":"2023-12-16T05:23:08Z","abstract_excerpt":"Sequential recommendation (SR) models based on Transformers have achieved remarkable successes. The self-attention mechanism of Transformers for computer vision and natural language processing suffers from the oversmoothing problem, i.e., hidden representations becoming similar to tokens. In the SR domain, we, for the first time, show that the same problem occurs. We present pioneering investigations that reveal the low-pass filtering nature of self-attention in the SR, which causes oversmoothing. To this end, we propose a novel method called $\\textbf{B}$eyond $\\textbf{S}$elf-$\\textbf{A}$ttent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10325","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/2312.10325/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":"2312.10325","created_at":"2026-07-05T07:46:28.822323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.10325v2","created_at":"2026-07-05T07:46:28.822323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10325","created_at":"2026-07-05T07:46:28.822323+00:00"},{"alias_kind":"pith_short_12","alias_value":"UY7H35MERQSY","created_at":"2026-07-05T07:46:28.822323+00:00"},{"alias_kind":"pith_short_16","alias_value":"UY7H35MERQSYXDTY","created_at":"2026-07-05T07:46:28.822323+00:00"},{"alias_kind":"pith_short_8","alias_value":"UY7H35ME","created_at":"2026-07-05T07:46:28.822323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10312","citing_title":"Beyond Semantic Understanding: Preserving Collaborative Frequency Components in LLM-based Recommendation","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UY7H35MERQSYXDTY5YJJNZNA44","json":"https://pith.science/pith/UY7H35MERQSYXDTY5YJJNZNA44.json","graph_json":"https://pith.science/api/pith-number/UY7H35MERQSYXDTY5YJJNZNA44/graph.json","events_json":"https://pith.science/api/pith-number/UY7H35MERQSYXDTY5YJJNZNA44/events.json","paper":"https://pith.science/paper/UY7H35ME"},"agent_actions":{"view_html":"https://pith.science/pith/UY7H35MERQSYXDTY5YJJNZNA44","download_json":"https://pith.science/pith/UY7H35MERQSYXDTY5YJJNZNA44.json","view_paper":"https://pith.science/paper/UY7H35ME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.10325&json=true","fetch_graph":"https://pith.science/api/pith-number/UY7H35MERQSYXDTY5YJJNZNA44/graph.json","fetch_events":"https://pith.science/api/pith-number/UY7H35MERQSYXDTY5YJJNZNA44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UY7H35MERQSYXDTY5YJJNZNA44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UY7H35MERQSYXDTY5YJJNZNA44/action/storage_attestation","attest_author":"https://pith.science/pith/UY7H35MERQSYXDTY5YJJNZNA44/action/author_attestation","sign_citation":"https://pith.science/pith/UY7H35MERQSYXDTY5YJJNZNA44/action/citation_signature","submit_replication":"https://pith.science/pith/UY7H35MERQSYXDTY5YJJNZNA44/action/replication_record"}},"created_at":"2026-07-05T07:46:28.822323+00:00","updated_at":"2026-07-05T07:46:28.822323+00:00"}