{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PKCHSRLPJT6INVMYZPNCSKZBKK","short_pith_number":"pith:PKCHSRLP","schema_version":"1.0","canonical_sha256":"7a8479456f4cfc86d598cbda292b21529d1595ba991fcaf7037c4ecfeb3b4bc8","source":{"kind":"arxiv","id":"2509.09682","version":6},"attestation_state":"computed","paper":{"title":"Faster and Memory-Efficient Training of Sequential Recommendation Models for Large Catalogs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Alexey Vasilev, Alexey Zaytsev, Anna Volodkevich, Daniil Volkov, Darya Denisova, Dmitry Redko, Egor Shvetsov, Maxim Zhelnin, Petr Sokerin, Ruslan Izmailov, Valeriy Shevchenko","submitted_at":"2025-08-13T15:03:38Z","abstract_excerpt":"Sequential recommendations (SR) with transformer-based architectures are widely adopted in real-world applications, where SR models require frequent retraining to adapt to ever-changing user preferences. However, training transformer-based SR models often encounters a high computational cost associated with scoring extensive item catalogs, often exceeding thousands of items. This occurs mainly due to the use of cross-entropy loss, where peak memory scales proportionally to catalog size, batch size, and sequence length. Recognizing this, practitioners in the field of recommendation systems typi"},"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":"2509.09682","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-13T15:03:38Z","cross_cats_sorted":[],"title_canon_sha256":"7745848544ae8a0d2b43b16df3f42a1e0c3ec335d5707704e8a042b461b7d3fb","abstract_canon_sha256":"3cb0d71cc0045db36841d6cc4bcc95db41ce5ac833432f35951ac53e8faeb234"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:08.656353Z","signature_b64":"ZbBMIoWZ6DudwdlIY6WwJ7tbzFNPmqfWEMLHquskVyzjoZzKWTmiilCW00UGHLw1CGKsjtkywYKwtLQv0BvsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a8479456f4cfc86d598cbda292b21529d1595ba991fcaf7037c4ecfeb3b4bc8","last_reissued_at":"2026-05-21T01:05:08.655603Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:08.655603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faster and Memory-Efficient Training of Sequential Recommendation Models for Large Catalogs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Alexey Vasilev, Alexey Zaytsev, Anna Volodkevich, Daniil Volkov, Darya Denisova, Dmitry Redko, Egor Shvetsov, Maxim Zhelnin, Petr Sokerin, Ruslan Izmailov, Valeriy Shevchenko","submitted_at":"2025-08-13T15:03:38Z","abstract_excerpt":"Sequential recommendations (SR) with transformer-based architectures are widely adopted in real-world applications, where SR models require frequent retraining to adapt to ever-changing user preferences. However, training transformer-based SR models often encounters a high computational cost associated with scoring extensive item catalogs, often exceeding thousands of items. This occurs mainly due to the use of cross-entropy loss, where peak memory scales proportionally to catalog size, batch size, and sequence length. Recognizing this, practitioners in the field of recommendation systems typi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09682","kind":"arxiv","version":6},"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/2509.09682/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":"2509.09682","created_at":"2026-05-21T01:05:08.655710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09682v6","created_at":"2026-05-21T01:05:08.655710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09682","created_at":"2026-05-21T01:05:08.655710+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKCHSRLPJT6I","created_at":"2026-05-21T01:05:08.655710+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKCHSRLPJT6INVMY","created_at":"2026-05-21T01:05:08.655710+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKCHSRLP","created_at":"2026-05-21T01:05:08.655710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKCHSRLPJT6INVMYZPNCSKZBKK","json":"https://pith.science/pith/PKCHSRLPJT6INVMYZPNCSKZBKK.json","graph_json":"https://pith.science/api/pith-number/PKCHSRLPJT6INVMYZPNCSKZBKK/graph.json","events_json":"https://pith.science/api/pith-number/PKCHSRLPJT6INVMYZPNCSKZBKK/events.json","paper":"https://pith.science/paper/PKCHSRLP"},"agent_actions":{"view_html":"https://pith.science/pith/PKCHSRLPJT6INVMYZPNCSKZBKK","download_json":"https://pith.science/pith/PKCHSRLPJT6INVMYZPNCSKZBKK.json","view_paper":"https://pith.science/paper/PKCHSRLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09682&json=true","fetch_graph":"https://pith.science/api/pith-number/PKCHSRLPJT6INVMYZPNCSKZBKK/graph.json","fetch_events":"https://pith.science/api/pith-number/PKCHSRLPJT6INVMYZPNCSKZBKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKCHSRLPJT6INVMYZPNCSKZBKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKCHSRLPJT6INVMYZPNCSKZBKK/action/storage_attestation","attest_author":"https://pith.science/pith/PKCHSRLPJT6INVMYZPNCSKZBKK/action/author_attestation","sign_citation":"https://pith.science/pith/PKCHSRLPJT6INVMYZPNCSKZBKK/action/citation_signature","submit_replication":"https://pith.science/pith/PKCHSRLPJT6INVMYZPNCSKZBKK/action/replication_record"}},"created_at":"2026-05-21T01:05:08.655710+00:00","updated_at":"2026-05-21T01:05:08.655710+00:00"}