{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GGZQFVKTD5I2NFRAH3ZRLCIBIO","short_pith_number":"pith:GGZQFVKT","schema_version":"1.0","canonical_sha256":"31b302d5531f51a696203ef315890143a1801777520bb2316535573b8a73927c","source":{"kind":"arxiv","id":"2304.04250","version":3},"attestation_state":"computed","paper":{"title":"Editable User Profiles for Controllable Text Recommendation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.HC","cs.LG"],"primary_cat":"cs.IR","authors_text":"Andrew McCallum, Hamed Zamani, Mahmood Jasim, Sheshera Mysore","submitted_at":"2023-04-09T14:52:18Z","abstract_excerpt":"Methods for making high-quality recommendations often rely on learning latent representations from interaction data. These methods, while performant, do not provide ready mechanisms for users to control the recommendation they receive. Our work tackles this problem by proposing LACE, a novel concept value bottleneck model for controllable text recommendations. LACE represents each user with a succinct set of human-readable concepts through retrieval given user-interacted documents and learns personalized representations of the concepts based on user documents. This concept based user profile i"},"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":"2304.04250","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2023-04-09T14:52:18Z","cross_cats_sorted":["cs.CL","cs.HC","cs.LG"],"title_canon_sha256":"57f4a55ae2ad1cf4453bc0b8bf2274cfd292084308a8d13bdc6ff8b64180a1ab","abstract_canon_sha256":"320bf35309e5ec093778031e9eda2029a0e42aa8f965a2ce2505bd254075a5d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:24.784797Z","signature_b64":"Fu/v9ctP2i9uSnKbZaNRlV+6djn1gmjNPwCgT2c0IJBc8ru6es6k+5D+QOIrIc50nll/oeJnxsEJkzx6ULkpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31b302d5531f51a696203ef315890143a1801777520bb2316535573b8a73927c","last_reissued_at":"2026-07-05T07:01:24.784383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:24.784383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Editable User Profiles for Controllable Text Recommendation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.HC","cs.LG"],"primary_cat":"cs.IR","authors_text":"Andrew McCallum, Hamed Zamani, Mahmood Jasim, Sheshera Mysore","submitted_at":"2023-04-09T14:52:18Z","abstract_excerpt":"Methods for making high-quality recommendations often rely on learning latent representations from interaction data. These methods, while performant, do not provide ready mechanisms for users to control the recommendation they receive. Our work tackles this problem by proposing LACE, a novel concept value bottleneck model for controllable text recommendations. LACE represents each user with a succinct set of human-readable concepts through retrieval given user-interacted documents and learns personalized representations of the concepts based on user documents. This concept based user profile i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04250","kind":"arxiv","version":3},"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/2304.04250/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":"2304.04250","created_at":"2026-07-05T07:01:24.784442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04250v3","created_at":"2026-07-05T07:01:24.784442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04250","created_at":"2026-07-05T07:01:24.784442+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGZQFVKTD5I2","created_at":"2026-07-05T07:01:24.784442+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGZQFVKTD5I2NFRA","created_at":"2026-07-05T07:01:24.784442+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGZQFVKT","created_at":"2026-07-05T07:01:24.784442+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.06606","citing_title":"Vulnerability of Text-Matching in ML/AI Conference Reviewer Assignments to Collusions","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGZQFVKTD5I2NFRAH3ZRLCIBIO","json":"https://pith.science/pith/GGZQFVKTD5I2NFRAH3ZRLCIBIO.json","graph_json":"https://pith.science/api/pith-number/GGZQFVKTD5I2NFRAH3ZRLCIBIO/graph.json","events_json":"https://pith.science/api/pith-number/GGZQFVKTD5I2NFRAH3ZRLCIBIO/events.json","paper":"https://pith.science/paper/GGZQFVKT"},"agent_actions":{"view_html":"https://pith.science/pith/GGZQFVKTD5I2NFRAH3ZRLCIBIO","download_json":"https://pith.science/pith/GGZQFVKTD5I2NFRAH3ZRLCIBIO.json","view_paper":"https://pith.science/paper/GGZQFVKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04250&json=true","fetch_graph":"https://pith.science/api/pith-number/GGZQFVKTD5I2NFRAH3ZRLCIBIO/graph.json","fetch_events":"https://pith.science/api/pith-number/GGZQFVKTD5I2NFRAH3ZRLCIBIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGZQFVKTD5I2NFRAH3ZRLCIBIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGZQFVKTD5I2NFRAH3ZRLCIBIO/action/storage_attestation","attest_author":"https://pith.science/pith/GGZQFVKTD5I2NFRAH3ZRLCIBIO/action/author_attestation","sign_citation":"https://pith.science/pith/GGZQFVKTD5I2NFRAH3ZRLCIBIO/action/citation_signature","submit_replication":"https://pith.science/pith/GGZQFVKTD5I2NFRAH3ZRLCIBIO/action/replication_record"}},"created_at":"2026-07-05T07:01:24.784442+00:00","updated_at":"2026-07-05T07:01:24.784442+00:00"}