{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5YLHP5AIV65PWOOSNKWE46FSDV","short_pith_number":"pith:5YLHP5AI","schema_version":"1.0","canonical_sha256":"ee1677f408afbafb39d26aac4e78b21d62fa9874673081227c2f3cf45cd1182c","source":{"kind":"arxiv","id":"2505.03655","version":1},"attestation_state":"computed","paper":{"title":"Counterfactual Inference for Eliminating Sentiment Bias in Recommender Systems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chengkai Huang, Le Pan, Lina Yao, Wenjie Zhang, Yuanjiang Cao","submitted_at":"2025-05-06T16:00:41Z","abstract_excerpt":"Recommender Systems (RSs) aim to provide personalized recommendations for users. A newly discovered bias, known as sentiment bias, uncovers a common phenomenon within Review-based RSs (RRSs): the recommendation accuracy of users or items with negative reviews deteriorates compared with users or items with positive reviews. Critical users and niche items are disadvantaged by such unfair recommendations. We study this problem from the perspective of counterfactual inference with two stages. At the model training stage, we build a causal graph and model how sentiment influences the final rating s"},"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":"2505.03655","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-06T16:00:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eda88453c489703ce198111a28eab78d7fec44a69d0f88fcb6c255296935e335","abstract_canon_sha256":"2b3105891e879a8a2c10966c8628a5eadb2ac3e75f9b7ab8d399710f87253555"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:20.040454Z","signature_b64":"zcPC8NTs6vokZPAnEOCoYukGdMX5r33YTeN/kPIotx/RwgXgMv6rk+SJZXsYodOOBwEC6cspWgJL1QMCw86ZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee1677f408afbafb39d26aac4e78b21d62fa9874673081227c2f3cf45cd1182c","last_reissued_at":"2026-07-05T10:59:20.039960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:20.039960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterfactual Inference for Eliminating Sentiment Bias in Recommender Systems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chengkai Huang, Le Pan, Lina Yao, Wenjie Zhang, Yuanjiang Cao","submitted_at":"2025-05-06T16:00:41Z","abstract_excerpt":"Recommender Systems (RSs) aim to provide personalized recommendations for users. A newly discovered bias, known as sentiment bias, uncovers a common phenomenon within Review-based RSs (RRSs): the recommendation accuracy of users or items with negative reviews deteriorates compared with users or items with positive reviews. Critical users and niche items are disadvantaged by such unfair recommendations. We study this problem from the perspective of counterfactual inference with two stages. At the model training stage, we build a causal graph and model how sentiment influences the final rating s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03655","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/2505.03655/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":"2505.03655","created_at":"2026-07-05T10:59:20.040017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03655v1","created_at":"2026-07-05T10:59:20.040017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03655","created_at":"2026-07-05T10:59:20.040017+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YLHP5AIV65P","created_at":"2026-07-05T10:59:20.040017+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YLHP5AIV65PWOOS","created_at":"2026-07-05T10:59:20.040017+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YLHP5AI","created_at":"2026-07-05T10:59:20.040017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26760","citing_title":"Factorized Latent Reasoning for LLM-based Recommendation","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5YLHP5AIV65PWOOSNKWE46FSDV","json":"https://pith.science/pith/5YLHP5AIV65PWOOSNKWE46FSDV.json","graph_json":"https://pith.science/api/pith-number/5YLHP5AIV65PWOOSNKWE46FSDV/graph.json","events_json":"https://pith.science/api/pith-number/5YLHP5AIV65PWOOSNKWE46FSDV/events.json","paper":"https://pith.science/paper/5YLHP5AI"},"agent_actions":{"view_html":"https://pith.science/pith/5YLHP5AIV65PWOOSNKWE46FSDV","download_json":"https://pith.science/pith/5YLHP5AIV65PWOOSNKWE46FSDV.json","view_paper":"https://pith.science/paper/5YLHP5AI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03655&json=true","fetch_graph":"https://pith.science/api/pith-number/5YLHP5AIV65PWOOSNKWE46FSDV/graph.json","fetch_events":"https://pith.science/api/pith-number/5YLHP5AIV65PWOOSNKWE46FSDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YLHP5AIV65PWOOSNKWE46FSDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YLHP5AIV65PWOOSNKWE46FSDV/action/storage_attestation","attest_author":"https://pith.science/pith/5YLHP5AIV65PWOOSNKWE46FSDV/action/author_attestation","sign_citation":"https://pith.science/pith/5YLHP5AIV65PWOOSNKWE46FSDV/action/citation_signature","submit_replication":"https://pith.science/pith/5YLHP5AIV65PWOOSNKWE46FSDV/action/replication_record"}},"created_at":"2026-07-05T10:59:20.040017+00:00","updated_at":"2026-07-05T10:59:20.040017+00:00"}