{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MTRZGUU56WCJ5G7HZBZQUFEWSY","short_pith_number":"pith:MTRZGUU5","schema_version":"1.0","canonical_sha256":"64e393529df5849e9be7c8730a14969616539cc5a93ebccc60f132fe98dca10d","source":{"kind":"arxiv","id":"2403.04875","version":1},"attestation_state":"computed","paper":{"title":"Aligning GPTRec with Beyond-Accuracy Goals with Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Aleksandr Petrov, Craig Macdonald","submitted_at":"2024-03-07T19:47:48Z","abstract_excerpt":"Adaptations of Transformer models, such as BERT4Rec and SASRec, achieve state-of-the-art performance in the sequential recommendation task according to accuracy-based metrics, such as NDCG. These models treat items as tokens and then utilise a score-and-rank approach (Top-K strategy), where the model first computes item scores and then ranks them according to this score. While this approach works well for accuracy-based metrics, it is hard to use it for optimising more complex beyond-accuracy metrics such as diversity. Recently, the GPTRec model, which uses a different Next-K strategy, has bee"},"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":"2403.04875","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-03-07T19:47:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2233b92fcb2dbff3e3dad1a054dbd87946bb3c862c364cbbc203daa4d0441f86","abstract_canon_sha256":"5e8ac9684aec9886521839f6a953861efa041ba3b19802b81633b7f2e1e7c66d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:35.175291Z","signature_b64":"wUauaB/5LjIzcbboywe3vKi+djseB1ggUya2ZmCFyDROBAjv6lBsCTlSeUGahrfcNB0vv0C+FJjIxCGZW+y1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64e393529df5849e9be7c8730a14969616539cc5a93ebccc60f132fe98dca10d","last_reissued_at":"2026-07-05T07:53:35.174824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:35.174824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning GPTRec with Beyond-Accuracy Goals with Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Aleksandr Petrov, Craig Macdonald","submitted_at":"2024-03-07T19:47:48Z","abstract_excerpt":"Adaptations of Transformer models, such as BERT4Rec and SASRec, achieve state-of-the-art performance in the sequential recommendation task according to accuracy-based metrics, such as NDCG. These models treat items as tokens and then utilise a score-and-rank approach (Top-K strategy), where the model first computes item scores and then ranks them according to this score. While this approach works well for accuracy-based metrics, it is hard to use it for optimising more complex beyond-accuracy metrics such as diversity. Recently, the GPTRec model, which uses a different Next-K strategy, has bee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04875","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/2403.04875/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":"2403.04875","created_at":"2026-07-05T07:53:35.174879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.04875v1","created_at":"2026-07-05T07:53:35.174879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04875","created_at":"2026-07-05T07:53:35.174879+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTRZGUU56WCJ","created_at":"2026-07-05T07:53:35.174879+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTRZGUU56WCJ5G7H","created_at":"2026-07-05T07:53:35.174879+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTRZGUU5","created_at":"2026-07-05T07:53:35.174879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01910","citing_title":"GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MTRZGUU56WCJ5G7HZBZQUFEWSY","json":"https://pith.science/pith/MTRZGUU56WCJ5G7HZBZQUFEWSY.json","graph_json":"https://pith.science/api/pith-number/MTRZGUU56WCJ5G7HZBZQUFEWSY/graph.json","events_json":"https://pith.science/api/pith-number/MTRZGUU56WCJ5G7HZBZQUFEWSY/events.json","paper":"https://pith.science/paper/MTRZGUU5"},"agent_actions":{"view_html":"https://pith.science/pith/MTRZGUU56WCJ5G7HZBZQUFEWSY","download_json":"https://pith.science/pith/MTRZGUU56WCJ5G7HZBZQUFEWSY.json","view_paper":"https://pith.science/paper/MTRZGUU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.04875&json=true","fetch_graph":"https://pith.science/api/pith-number/MTRZGUU56WCJ5G7HZBZQUFEWSY/graph.json","fetch_events":"https://pith.science/api/pith-number/MTRZGUU56WCJ5G7HZBZQUFEWSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTRZGUU56WCJ5G7HZBZQUFEWSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTRZGUU56WCJ5G7HZBZQUFEWSY/action/storage_attestation","attest_author":"https://pith.science/pith/MTRZGUU56WCJ5G7HZBZQUFEWSY/action/author_attestation","sign_citation":"https://pith.science/pith/MTRZGUU56WCJ5G7HZBZQUFEWSY/action/citation_signature","submit_replication":"https://pith.science/pith/MTRZGUU56WCJ5G7HZBZQUFEWSY/action/replication_record"}},"created_at":"2026-07-05T07:53:35.174879+00:00","updated_at":"2026-07-05T07:53:35.174879+00:00"}