{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:53OWXT2NSO7VUIA4NFX5FRHDKI","short_pith_number":"pith:53OWXT2N","schema_version":"1.0","canonical_sha256":"eedd6bcf4d93bf5a201c696fd2c4e3522730b52b02562ba45c29212634c3540d","source":{"kind":"arxiv","id":"2504.10507","version":7},"attestation_state":"computed","paper":{"title":"PinRec: Unified Generative Retrieval for Pinterest Recommender Systems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Anirudhan Badrinath, Charles Rosenberg, Edoardo Botta, Jaewon Yang, Jiajing Xu, Laksh Bhasin, Prabhat Agarwal, Yilin Chen, Yi-Ping Hsu","submitted_at":"2025-04-09T17:46:12Z","abstract_excerpt":"Generative retrieval methods employ sequential modeling techniques, like transformers, to generate candidate items for recommender systems. These methods have demonstrated promising results in academic benchmarks, surpassing traditional retrieval models such as two-tower architectures. However, a key limitation is that current approaches require a separate model for each product surface, as building a unified model that accommodates the different business needs of various surfaces has proven challenging. Furthermore, existing methods often fail to capture the evolution of user interests over a"},"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":"2504.10507","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-09T17:46:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e538ebc2d633d2d9640ec6219dfea5c026ce973f96f225770cc88b2918aada60","abstract_canon_sha256":"3b92735cd3177a37bc8c48d3ff5c258d60e47edc605766a43a412bccca11164e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:11:55.104962Z","signature_b64":"1EPBAmw9/mzbv+2E6fZSR14F7wrwtmEX2ot4Flr82u/PNLbGzocL3ztFjl8i2BtM1O6/4ihMKxBpzmBm/64NAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eedd6bcf4d93bf5a201c696fd2c4e3522730b52b02562ba45c29212634c3540d","last_reissued_at":"2026-06-23T01:11:55.104286Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:11:55.104286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PinRec: Unified Generative Retrieval for Pinterest Recommender Systems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Anirudhan Badrinath, Charles Rosenberg, Edoardo Botta, Jaewon Yang, Jiajing Xu, Laksh Bhasin, Prabhat Agarwal, Yilin Chen, Yi-Ping Hsu","submitted_at":"2025-04-09T17:46:12Z","abstract_excerpt":"Generative retrieval methods employ sequential modeling techniques, like transformers, to generate candidate items for recommender systems. These methods have demonstrated promising results in academic benchmarks, surpassing traditional retrieval models such as two-tower architectures. However, a key limitation is that current approaches require a separate model for each product surface, as building a unified model that accommodates the different business needs of various surfaces has proven challenging. Furthermore, existing methods often fail to capture the evolution of user interests over a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10507","kind":"arxiv","version":7},"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/2504.10507/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":"2504.10507","created_at":"2026-06-23T01:11:55.104393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10507v7","created_at":"2026-06-23T01:11:55.104393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10507","created_at":"2026-06-23T01:11:55.104393+00:00"},{"alias_kind":"pith_short_12","alias_value":"53OWXT2NSO7V","created_at":"2026-06-23T01:11:55.104393+00:00"},{"alias_kind":"pith_short_16","alias_value":"53OWXT2NSO7VUIA4","created_at":"2026-06-23T01:11:55.104393+00:00"},{"alias_kind":"pith_short_8","alias_value":"53OWXT2N","created_at":"2026-06-23T01:11:55.104393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":9,"sample":[{"citing_arxiv_id":"2510.21242","citing_title":"Bi-Level Optimization for Generative Recommendation: Bridging Tokenization and Generation","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2508.20900","citing_title":"OneRec-V2 Technical Report","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14512","citing_title":"Asymmetric Generative Recommendation via Multi-Expert Projection and Multi-Faceted Hierarchical Quantization","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02684","citing_title":"MBGR: Multi-Business Prediction for Generative Recommendation at Meituan","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04976","citing_title":"Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24472","citing_title":"Modeling Behavioral Intensity and Transitions for Generative Recommendation","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07739","citing_title":"Efficient Dataset Selection for Continual Adaptation of Generative Recommenders","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13273","citing_title":"Mitigating Collaborative Semantic ID Staleness in Generative Retrieval","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13468","citing_title":"From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53OWXT2NSO7VUIA4NFX5FRHDKI","json":"https://pith.science/pith/53OWXT2NSO7VUIA4NFX5FRHDKI.json","graph_json":"https://pith.science/api/pith-number/53OWXT2NSO7VUIA4NFX5FRHDKI/graph.json","events_json":"https://pith.science/api/pith-number/53OWXT2NSO7VUIA4NFX5FRHDKI/events.json","paper":"https://pith.science/paper/53OWXT2N"},"agent_actions":{"view_html":"https://pith.science/pith/53OWXT2NSO7VUIA4NFX5FRHDKI","download_json":"https://pith.science/pith/53OWXT2NSO7VUIA4NFX5FRHDKI.json","view_paper":"https://pith.science/paper/53OWXT2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10507&json=true","fetch_graph":"https://pith.science/api/pith-number/53OWXT2NSO7VUIA4NFX5FRHDKI/graph.json","fetch_events":"https://pith.science/api/pith-number/53OWXT2NSO7VUIA4NFX5FRHDKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53OWXT2NSO7VUIA4NFX5FRHDKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53OWXT2NSO7VUIA4NFX5FRHDKI/action/storage_attestation","attest_author":"https://pith.science/pith/53OWXT2NSO7VUIA4NFX5FRHDKI/action/author_attestation","sign_citation":"https://pith.science/pith/53OWXT2NSO7VUIA4NFX5FRHDKI/action/citation_signature","submit_replication":"https://pith.science/pith/53OWXT2NSO7VUIA4NFX5FRHDKI/action/replication_record"}},"created_at":"2026-06-23T01:11:55.104393+00:00","updated_at":"2026-06-23T01:11:55.104393+00:00"}