{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B5IILBLL45UHSFZSYIHBCQTV4P","short_pith_number":"pith:B5IILBLL","schema_version":"1.0","canonical_sha256":"0f5085856be768791732c20e114275e3e28739179f6c7b8e9e56aae9a602faa8","source":{"kind":"arxiv","id":"2404.16019","version":2},"attestation_state":"computed","paper":{"title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adina Williams, Alexander Whitefield, Andrew Bean, Bertie Vidgen, Hannah Rose Kirk, He He, Juan Ciro, Katerina Margatina, Max Bartolo, Paul R\\\"ottger, Rafael Mosquera, Scott A. Hale","submitted_at":"2024-04-24T17:51:36Z","abstract_excerpt":"Human feedback is central to the alignment of Large Language Models (LLMs). However, open questions remain about methods (how), domains (where), people (who) and objectives (to what end) of feedback processes. To navigate these questions, we introduce PRISM, a dataset that maps the sociodemographics and stated preferences of 1,500 diverse participants from 75 countries, to their contextual preferences and fine-grained feedback in 8,011 live conversations with 21 LLMs. With PRISM, we contribute (i) wider geographic and demographic participation in feedback; (ii) census-representative samples fo"},"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":"2404.16019","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T17:51:36Z","cross_cats_sorted":[],"title_canon_sha256":"7a68add9f7e7168b633b8a43e928c122ea5e4244ab4700ff2570062f03a28039","abstract_canon_sha256":"85033e233284c1f2cecd1967e3c4dd9256271124d7bd0fb0ea019b78f0a9dffe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:29.148139Z","signature_b64":"ZPD4k/tRok/v/ZeVW+Xn4DL8ckrn5h5RlJGEWP9HL/D8P23jA3RMi2YnQg5BGcVIaguIYch2WDQ872y5zg1rBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f5085856be768791732c20e114275e3e28739179f6c7b8e9e56aae9a602faa8","last_reissued_at":"2026-07-05T09:43:29.147631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:29.147631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adina Williams, Alexander Whitefield, Andrew Bean, Bertie Vidgen, Hannah Rose Kirk, He He, Juan Ciro, Katerina Margatina, Max Bartolo, Paul R\\\"ottger, Rafael Mosquera, Scott A. Hale","submitted_at":"2024-04-24T17:51:36Z","abstract_excerpt":"Human feedback is central to the alignment of Large Language Models (LLMs). However, open questions remain about methods (how), domains (where), people (who) and objectives (to what end) of feedback processes. To navigate these questions, we introduce PRISM, a dataset that maps the sociodemographics and stated preferences of 1,500 diverse participants from 75 countries, to their contextual preferences and fine-grained feedback in 8,011 live conversations with 21 LLMs. With PRISM, we contribute (i) wider geographic and demographic participation in feedback; (ii) census-representative samples fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16019","kind":"arxiv","version":2},"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/2404.16019/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":"2404.16019","created_at":"2026-07-05T09:43:29.147698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16019v2","created_at":"2026-07-05T09:43:29.147698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16019","created_at":"2026-07-05T09:43:29.147698+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5IILBLL45UH","created_at":"2026-07-05T09:43:29.147698+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5IILBLL45UHSFZS","created_at":"2026-07-05T09:43:29.147698+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5IILBLL","created_at":"2026-07-05T09:43:29.147698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06674","citing_title":"What Do People Actually Want From AI? Mapping Preference Plurality","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27580","citing_title":"Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27578","citing_title":"PEBS: Per-rater Empirical-Bayes Shrinkage for RLHF Reward-Model Calibration","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24279","citing_title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2501.18045","citing_title":"From tools to thieves: Measuring and understanding public perceptions of AI through crowdsourced metaphors","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2502.19463","citing_title":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2504.12501","citing_title":"Reinforcement Learning from Human Feedback","ref_index":219,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23231","citing_title":"PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10843","citing_title":"Training-Free Cultural Alignment of Large Language Models via Persona Disagreement","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10843","citing_title":"Training-Free Cultural Alignment of Large Language Models via Persona Disagreement","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20805","citing_title":"Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5IILBLL45UHSFZSYIHBCQTV4P","json":"https://pith.science/pith/B5IILBLL45UHSFZSYIHBCQTV4P.json","graph_json":"https://pith.science/api/pith-number/B5IILBLL45UHSFZSYIHBCQTV4P/graph.json","events_json":"https://pith.science/api/pith-number/B5IILBLL45UHSFZSYIHBCQTV4P/events.json","paper":"https://pith.science/paper/B5IILBLL"},"agent_actions":{"view_html":"https://pith.science/pith/B5IILBLL45UHSFZSYIHBCQTV4P","download_json":"https://pith.science/pith/B5IILBLL45UHSFZSYIHBCQTV4P.json","view_paper":"https://pith.science/paper/B5IILBLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16019&json=true","fetch_graph":"https://pith.science/api/pith-number/B5IILBLL45UHSFZSYIHBCQTV4P/graph.json","fetch_events":"https://pith.science/api/pith-number/B5IILBLL45UHSFZSYIHBCQTV4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5IILBLL45UHSFZSYIHBCQTV4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5IILBLL45UHSFZSYIHBCQTV4P/action/storage_attestation","attest_author":"https://pith.science/pith/B5IILBLL45UHSFZSYIHBCQTV4P/action/author_attestation","sign_citation":"https://pith.science/pith/B5IILBLL45UHSFZSYIHBCQTV4P/action/citation_signature","submit_replication":"https://pith.science/pith/B5IILBLL45UHSFZSYIHBCQTV4P/action/replication_record"}},"created_at":"2026-07-05T09:43:29.147698+00:00","updated_at":"2026-07-05T09:43:29.147698+00:00"}