{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5C5H7QA37LMAQ6IHLDNAKZJ6KX","short_pith_number":"pith:5C5H7QA3","schema_version":"1.0","canonical_sha256":"e8ba7fc01bfad808790758da05653e55c9ba9d6ebf352cacefb4a637825cf287","source":{"kind":"arxiv","id":"2605.27043","version":1},"attestation_state":"computed","paper":{"title":"Causal Representation Learning for Generalisable Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Ciar\\'an M. Gilligan-Lee, Michael O'Riordan, Oriol Corcoll, Yorgos Felekis","submitted_at":"2026-05-26T13:58:36Z","abstract_excerpt":"Predictive models trained on observational data often fail to generalise to the distributions they encounter when deployed, especially when the training data is a product of the system being optimised. Recommender systems are a canonical example: they are trained on interaction logs confounded by the deployed policy, past user behaviour, and platform filtering. As a result, the training distribution differs substantially from the candidate distribution scored at serving time, a gap that makes offline metrics unreliable predictors of online performance. We address the distribution shift problem"},"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":"2605.27043","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-26T13:58:36Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"74903d335b4ddc09200f0cf32a1d8d624674fbcac94a1b607b56c6885ef77b70","abstract_canon_sha256":"75bac256a4b0cb404e1a23facf71f0ebce6d41ec76ed741cb0b2b100562a46c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:25.519740Z","signature_b64":"7/Mva3p3jSN0hUqIic8g/aDqlEOASe7Bp61ZCXpLEebb6zG5RIQJj9v5ApY19H1mvyHwlcfyJVW+HrZifn05DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8ba7fc01bfad808790758da05653e55c9ba9d6ebf352cacefb4a637825cf287","last_reissued_at":"2026-05-27T01:06:25.519072Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:25.519072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Representation Learning for Generalisable Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Ciar\\'an M. Gilligan-Lee, Michael O'Riordan, Oriol Corcoll, Yorgos Felekis","submitted_at":"2026-05-26T13:58:36Z","abstract_excerpt":"Predictive models trained on observational data often fail to generalise to the distributions they encounter when deployed, especially when the training data is a product of the system being optimised. Recommender systems are a canonical example: they are trained on interaction logs confounded by the deployed policy, past user behaviour, and platform filtering. As a result, the training distribution differs substantially from the candidate distribution scored at serving time, a gap that makes offline metrics unreliable predictors of online performance. We address the distribution shift problem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27043","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/2605.27043/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":"2605.27043","created_at":"2026-05-27T01:06:25.519153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27043v1","created_at":"2026-05-27T01:06:25.519153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27043","created_at":"2026-05-27T01:06:25.519153+00:00"},{"alias_kind":"pith_short_12","alias_value":"5C5H7QA37LMA","created_at":"2026-05-27T01:06:25.519153+00:00"},{"alias_kind":"pith_short_16","alias_value":"5C5H7QA37LMAQ6IH","created_at":"2026-05-27T01:06:25.519153+00:00"},{"alias_kind":"pith_short_8","alias_value":"5C5H7QA3","created_at":"2026-05-27T01:06:25.519153+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/5C5H7QA37LMAQ6IHLDNAKZJ6KX","json":"https://pith.science/pith/5C5H7QA37LMAQ6IHLDNAKZJ6KX.json","graph_json":"https://pith.science/api/pith-number/5C5H7QA37LMAQ6IHLDNAKZJ6KX/graph.json","events_json":"https://pith.science/api/pith-number/5C5H7QA37LMAQ6IHLDNAKZJ6KX/events.json","paper":"https://pith.science/paper/5C5H7QA3"},"agent_actions":{"view_html":"https://pith.science/pith/5C5H7QA37LMAQ6IHLDNAKZJ6KX","download_json":"https://pith.science/pith/5C5H7QA37LMAQ6IHLDNAKZJ6KX.json","view_paper":"https://pith.science/paper/5C5H7QA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27043&json=true","fetch_graph":"https://pith.science/api/pith-number/5C5H7QA37LMAQ6IHLDNAKZJ6KX/graph.json","fetch_events":"https://pith.science/api/pith-number/5C5H7QA37LMAQ6IHLDNAKZJ6KX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5C5H7QA37LMAQ6IHLDNAKZJ6KX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5C5H7QA37LMAQ6IHLDNAKZJ6KX/action/storage_attestation","attest_author":"https://pith.science/pith/5C5H7QA37LMAQ6IHLDNAKZJ6KX/action/author_attestation","sign_citation":"https://pith.science/pith/5C5H7QA37LMAQ6IHLDNAKZJ6KX/action/citation_signature","submit_replication":"https://pith.science/pith/5C5H7QA37LMAQ6IHLDNAKZJ6KX/action/replication_record"}},"created_at":"2026-05-27T01:06:25.519153+00:00","updated_at":"2026-05-27T01:06:25.519153+00:00"}