{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LDOAWIAI5OCDN72ZUGKL7KUFYW","short_pith_number":"pith:LDOAWIAI","schema_version":"1.0","canonical_sha256":"58dc0b2008eb8436ff59a194bfaa85c590b0ced99d8b5e064003516c7428aba7","source":{"kind":"arxiv","id":"2209.07997","version":1},"attestation_state":"computed","paper":{"title":"Recursive Attentive Methods with Reused Item Representations for Sequential Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bo Peng, Srinivasan Parthasarathy, Xia Ning","submitted_at":"2022-09-16T15:17:30Z","abstract_excerpt":"Sequential recommendation aims to recommend the next item of users' interest based on their historical interactions. Recently, the self-attention mechanism has been adapted for sequential recommendation, and demonstrated state-of-the-art performance. However, in this manuscript, we show that the self-attention-based sequential recommendation methods could suffer from the localization-deficit issue. As a consequence, in these methods, over the first few blocks, the item representations may quickly diverge from their original representations, and thus, impairs the learning in the following block"},"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":"2209.07997","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-09-16T15:17:30Z","cross_cats_sorted":[],"title_canon_sha256":"2d64ae44fdca75de16a8bf9dccb9ca4443c2f15d94e45cfe1f045b3f8d24e2a6","abstract_canon_sha256":"7d1128b848a2d99557deda93a1965fe624ce416b2cd6079d24014e9e6b05b32e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:12.422359Z","signature_b64":"TQixpfUS2VWO8XggtvWJMRJaH7E/Nkm1ZtTVt54FJvN2OWbY/LD4354hyigliZ8iJTfWGpeNDs21049SJCOdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58dc0b2008eb8436ff59a194bfaa85c590b0ced99d8b5e064003516c7428aba7","last_reissued_at":"2026-07-05T04:58:12.421948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:12.421948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recursive Attentive Methods with Reused Item Representations for Sequential Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bo Peng, Srinivasan Parthasarathy, Xia Ning","submitted_at":"2022-09-16T15:17:30Z","abstract_excerpt":"Sequential recommendation aims to recommend the next item of users' interest based on their historical interactions. Recently, the self-attention mechanism has been adapted for sequential recommendation, and demonstrated state-of-the-art performance. However, in this manuscript, we show that the self-attention-based sequential recommendation methods could suffer from the localization-deficit issue. As a consequence, in these methods, over the first few blocks, the item representations may quickly diverge from their original representations, and thus, impairs the learning in the following block"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07997","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/2209.07997/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":"2209.07997","created_at":"2026-07-05T04:58:12.422003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.07997v1","created_at":"2026-07-05T04:58:12.422003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07997","created_at":"2026-07-05T04:58:12.422003+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDOAWIAI5OCD","created_at":"2026-07-05T04:58:12.422003+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDOAWIAI5OCDN72Z","created_at":"2026-07-05T04:58:12.422003+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDOAWIAI","created_at":"2026-07-05T04:58:12.422003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03131","citing_title":"RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDOAWIAI5OCDN72ZUGKL7KUFYW","json":"https://pith.science/pith/LDOAWIAI5OCDN72ZUGKL7KUFYW.json","graph_json":"https://pith.science/api/pith-number/LDOAWIAI5OCDN72ZUGKL7KUFYW/graph.json","events_json":"https://pith.science/api/pith-number/LDOAWIAI5OCDN72ZUGKL7KUFYW/events.json","paper":"https://pith.science/paper/LDOAWIAI"},"agent_actions":{"view_html":"https://pith.science/pith/LDOAWIAI5OCDN72ZUGKL7KUFYW","download_json":"https://pith.science/pith/LDOAWIAI5OCDN72ZUGKL7KUFYW.json","view_paper":"https://pith.science/paper/LDOAWIAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.07997&json=true","fetch_graph":"https://pith.science/api/pith-number/LDOAWIAI5OCDN72ZUGKL7KUFYW/graph.json","fetch_events":"https://pith.science/api/pith-number/LDOAWIAI5OCDN72ZUGKL7KUFYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDOAWIAI5OCDN72ZUGKL7KUFYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDOAWIAI5OCDN72ZUGKL7KUFYW/action/storage_attestation","attest_author":"https://pith.science/pith/LDOAWIAI5OCDN72ZUGKL7KUFYW/action/author_attestation","sign_citation":"https://pith.science/pith/LDOAWIAI5OCDN72ZUGKL7KUFYW/action/citation_signature","submit_replication":"https://pith.science/pith/LDOAWIAI5OCDN72ZUGKL7KUFYW/action/replication_record"}},"created_at":"2026-07-05T04:58:12.422003+00:00","updated_at":"2026-07-05T04:58:12.422003+00:00"}