{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2DBBRGE3OASQJJ43LAXGMYBPB5","short_pith_number":"pith:2DBBRGE3","schema_version":"1.0","canonical_sha256":"d0c218989b702504a79b582e66602f0f5a927413fdce1626d316c9c5a3cc532a","source":{"kind":"arxiv","id":"1808.09781","version":1},"attestation_state":"computed","paper":{"title":"Self-Attentive Sequential Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Julian McAuley, Wang-Cheng Kang","submitted_at":"2018-08-20T04:28:05Z","abstract_excerpt":"Sequential dynamics are a key feature of many modern recommender systems, which seek to capture the `context' of users' activities on the basis of actions they have performed recently. To capture such patterns, two approaches have proliferated: Markov Chains (MCs) and Recurrent Neural Networks (RNNs). Markov Chains assume that a user's next action can be predicted on the basis of just their last (or last few) actions, while RNNs in principle allow for longer-term semantics to be uncovered. Generally speaking, MC-based methods perform best in extremely sparse datasets, where model parsimony is "},"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":"1808.09781","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-08-20T04:28:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1f70dae6f69ae2ac959f29e09b6a22260c494f9f344ef6245fcde51e86c8ae4c","abstract_canon_sha256":"08e51ceb70ae634b84822bc031c84fe67f354a6524dde576d151afcb88a7890e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:54.475899Z","signature_b64":"+cuiIwuoAI6KPA6xghG/A+BgPqSyCIg0BZLAmd/W01ULNsYqvjIVAsMFWmiDiBOxdr2YHsKSvfCSRAvtS3lPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0c218989b702504a79b582e66602f0f5a927413fdce1626d316c9c5a3cc532a","last_reissued_at":"2026-05-18T00:06:54.475432Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:54.475432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Attentive Sequential Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Julian McAuley, Wang-Cheng Kang","submitted_at":"2018-08-20T04:28:05Z","abstract_excerpt":"Sequential dynamics are a key feature of many modern recommender systems, which seek to capture the `context' of users' activities on the basis of actions they have performed recently. To capture such patterns, two approaches have proliferated: Markov Chains (MCs) and Recurrent Neural Networks (RNNs). Markov Chains assume that a user's next action can be predicted on the basis of just their last (or last few) actions, while RNNs in principle allow for longer-term semantics to be uncovered. Generally speaking, MC-based methods perform best in extremely sparse datasets, where model parsimony is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09781","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":""},"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":"1808.09781","created_at":"2026-05-18T00:06:54.475498+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.09781v1","created_at":"2026-05-18T00:06:54.475498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09781","created_at":"2026-05-18T00:06:54.475498+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DBBRGE3OASQ","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DBBRGE3OASQJJ43","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DBBRGE3","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2606.12198","citing_title":"LLM-Based User Personas for Recommendations at Scale","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10243","citing_title":"DUET -- Dual User Embedding Transformers for Offsite Conversion Prediction","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03221","citing_title":"VirtualMLE: A Virtual ML Engineer that Optimizes Sequential Recommenders","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27865","citing_title":"From Bootstrapping to Sequence Modeling: A Unified Generative Framework for Personalized Landing-Page Modeling","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06837","citing_title":"A Self-Attentive model for Knowledge Tracing","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11553","citing_title":"TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21536","citing_title":"Pre-trained LLMs Meet Sequential Recommenders: Efficient User-Centric Knowledge Distillation","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DBBRGE3OASQJJ43LAXGMYBPB5","json":"https://pith.science/pith/2DBBRGE3OASQJJ43LAXGMYBPB5.json","graph_json":"https://pith.science/api/pith-number/2DBBRGE3OASQJJ43LAXGMYBPB5/graph.json","events_json":"https://pith.science/api/pith-number/2DBBRGE3OASQJJ43LAXGMYBPB5/events.json","paper":"https://pith.science/paper/2DBBRGE3"},"agent_actions":{"view_html":"https://pith.science/pith/2DBBRGE3OASQJJ43LAXGMYBPB5","download_json":"https://pith.science/pith/2DBBRGE3OASQJJ43LAXGMYBPB5.json","view_paper":"https://pith.science/paper/2DBBRGE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.09781&json=true","fetch_graph":"https://pith.science/api/pith-number/2DBBRGE3OASQJJ43LAXGMYBPB5/graph.json","fetch_events":"https://pith.science/api/pith-number/2DBBRGE3OASQJJ43LAXGMYBPB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DBBRGE3OASQJJ43LAXGMYBPB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DBBRGE3OASQJJ43LAXGMYBPB5/action/storage_attestation","attest_author":"https://pith.science/pith/2DBBRGE3OASQJJ43LAXGMYBPB5/action/author_attestation","sign_citation":"https://pith.science/pith/2DBBRGE3OASQJJ43LAXGMYBPB5/action/citation_signature","submit_replication":"https://pith.science/pith/2DBBRGE3OASQJJ43LAXGMYBPB5/action/replication_record"}},"created_at":"2026-05-18T00:06:54.475498+00:00","updated_at":"2026-05-18T00:06:54.475498+00:00"}