{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KCWHBFU7GJLKUM5W7HTH5WOM26","short_pith_number":"pith:KCWHBFU7","canonical_record":{"source":{"id":"2605.14420","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T06:06:43Z","cross_cats_sorted":[],"title_canon_sha256":"009dbf78b25110196922624fc51b4f534fa998a308da3ec9f027563ca85210fd","abstract_canon_sha256":"c91590de42b5a804214f8208f8df15cd4f4dbe0bac972796c53d66bc2643e8bf"},"schema_version":"1.0"},"canonical_sha256":"50ac70969f3256aa33b6f9e67ed9ccd7a77775061ea916528042308045e2b7ea","source":{"kind":"arxiv","id":"2605.14420","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14420","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14420v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14420","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"KCWHBFU7GJLK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KCWHBFU7GJLKUM5W","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KCWHBFU7","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KCWHBFU7GJLKUM5W7HTH5WOM26","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14420","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T06:06:43Z","cross_cats_sorted":[],"title_canon_sha256":"009dbf78b25110196922624fc51b4f534fa998a308da3ec9f027563ca85210fd","abstract_canon_sha256":"c91590de42b5a804214f8208f8df15cd4f4dbe0bac972796c53d66bc2643e8bf"},"schema_version":"1.0"},"canonical_sha256":"50ac70969f3256aa33b6f9e67ed9ccd7a77775061ea916528042308045e2b7ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:07.260151Z","signature_b64":"1C48i2T0VI59tdyGj+UwSY+V/Cp4thVzyaTlTJGbTuCRIDCP0AcGPLcfB5QKlRBq87iwCUqVSYrfCc9ws4qGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50ac70969f3256aa33b6f9e67ed9ccd7a77775061ea916528042308045e2b7ea","last_reissued_at":"2026-05-17T23:39:07.259501Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:07.259501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14420","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IR+DeH5JQ026k5wf2PdPkpk6+UDYPROrn3inpMYYQZR8yHgLB9wfp93KaNqK62fxF6+0qhe7DXcEGPzAXjmlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T05:28:33.779569Z"},"content_sha256":"c424e4322d520245656de39ac1152af8cb543944a44f1e2ae7a9b766a7884e5a","schema_version":"1.0","event_id":"sha256:c424e4322d520245656de39ac1152af8cb543944a44f1e2ae7a9b766a7884e5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KCWHBFU7GJLKUM5W7HTH5WOM26","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Mapping multi-dimensional demographics to values lets LLMs align with pluralistic preferences more tightly than national labels allow.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Deyi Xiong, Lei Yang, Pengyun Zhu, Yuqi Ren, Zhen Wang","submitted_at":"2026-05-14T06:06:43Z","abstract_excerpt":"Current Large Language Models (LLMs) typically rely on coarse-grained national labels for pluralistic value alignment. However, such macro-level supervision often obscures intra-country value heterogeneity, yielding a loose alignment. We argue that resolving this limitation requires shifting from national labels to multi-dimensional demographic constraints, which can identify groups with predictable, high-consensus value preference. To this end, we propose DVMap (High-Consensus Demographic-Value Mapping), a framework for fine-grained pluralistic value alignment. In this framework, we first pre"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results demonstrate that DVMap effectively learns the manifold mapping from demographics to values, exhibiting strong generalization and robustness. On cross-demographic tests, Qwen3-8B-DVMap achieves 48.6% accuracy, surpassing the advanced open-source LLM DeepSeek-v3.2 (45.1%).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That respondents with consistent value preferences under identical demographics form high-consensus groups whose preferences generalize reliably to unseen demographic combinations, countries, and value dimensions without introducing selection bias from the filtering process.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DVMap extracts high-consensus demographic groups from survey data and applies structured CoT plus GRPO to align LLMs with pluralistic values, reporting 48.6% accuracy on cross-demographic generalization tests.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Mapping multi-dimensional demographics to values lets LLMs align with pluralistic preferences more tightly than national labels allow.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e7efeb561748dd2928a5e4244546c1a37df70476bf280d3190bad63fd10bdac4"},"source":{"id":"2605.14420","kind":"arxiv","version":1},"verdict":{"id":"7b321340-df51-4e83-b4c7-f707353752d6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:00:43.241257Z","strongest_claim":"Experimental results demonstrate that DVMap effectively learns the manifold mapping from demographics to values, exhibiting strong generalization and robustness. On cross-demographic tests, Qwen3-8B-DVMap achieves 48.6% accuracy, surpassing the advanced open-source LLM DeepSeek-v3.2 (45.1%).","one_line_summary":"DVMap extracts high-consensus demographic groups from survey data and applies structured CoT plus GRPO to align LLMs with pluralistic values, reporting 48.6% accuracy on cross-demographic generalization tests.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That respondents with consistent value preferences under identical demographics form high-consensus groups whose preferences generalize reliably to unseen demographic combinations, countries, and value dimensions without introducing selection bias from the filtering process.","pith_extraction_headline":"Mapping multi-dimensional demographics to values lets LLMs align with pluralistic preferences more tightly than national labels allow."},"references":{"count":13,"sample":[{"doi":"","year":2024,"title":"Association for Computational Linguistics","work_id":"0f9b87ad-f0c9-436f-9b1b-faa8e4a7c8ac","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"In9th International Conference on Learning Representa- tions, ICLR 2021, Virtual Event, Austria, May 3-7,","work_id":"c1e314ad-45cb-40dd-b862-9ec0b81988ab","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2005,"title":"The ghost in the machine has an american accent: value conflict in gpt-3","work_id":"9324c45e-22da-43e3-ab89-872beb2e2d38","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"GPT-4o System Card","work_id":"f37bf1c7-4964-4e56-9762-d20da8d9009f","ref_index":4,"cited_arxiv_id":"2410.21276","is_internal_anchor":true},{"doi":"","year":2023,"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","ref_index":5,"cited_arxiv_id":"2402.03300","is_internal_anchor":true}],"resolved_work":13,"snapshot_sha256":"263acef597a6a6c4e7132dd426fba196803313f84736e1e0457180bce9ceca5d","internal_anchors":3},"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"},"verdict_id":"7b321340-df51-4e83-b4c7-f707353752d6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uRVLy4ZsacSDVkIRy97YF2pOWgWKc8Kfywy2rfif4vIBT1Y0E7HH1NfsVI/KkFeB4mYOHE5y8u5LkwS3DbTxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T05:28:33.780527Z"},"content_sha256":"875429392f827305567c9a3a76ab5cb284306012866f4a6f539e08e3aa63e607","schema_version":"1.0","event_id":"sha256:875429392f827305567c9a3a76ab5cb284306012866f4a6f539e08e3aa63e607"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KCWHBFU7GJLKUM5W7HTH5WOM26/bundle.json","state_url":"https://pith.science/pith/KCWHBFU7GJLKUM5W7HTH5WOM26/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KCWHBFU7GJLKUM5W7HTH5WOM26/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-23T05:28:33Z","links":{"resolver":"https://pith.science/pith/KCWHBFU7GJLKUM5W7HTH5WOM26","bundle":"https://pith.science/pith/KCWHBFU7GJLKUM5W7HTH5WOM26/bundle.json","state":"https://pith.science/pith/KCWHBFU7GJLKUM5W7HTH5WOM26/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KCWHBFU7GJLKUM5W7HTH5WOM26/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KCWHBFU7GJLKUM5W7HTH5WOM26","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c91590de42b5a804214f8208f8df15cd4f4dbe0bac972796c53d66bc2643e8bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T06:06:43Z","title_canon_sha256":"009dbf78b25110196922624fc51b4f534fa998a308da3ec9f027563ca85210fd"},"schema_version":"1.0","source":{"id":"2605.14420","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14420","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14420v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14420","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"KCWHBFU7GJLK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KCWHBFU7GJLKUM5W","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KCWHBFU7","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:875429392f827305567c9a3a76ab5cb284306012866f4a6f539e08e3aa63e607","target":"graph","created_at":"2026-05-17T23:39:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experimental results demonstrate that DVMap effectively learns the manifold mapping from demographics to values, exhibiting strong generalization and robustness. On cross-demographic tests, Qwen3-8B-DVMap achieves 48.6% accuracy, surpassing the advanced open-source LLM DeepSeek-v3.2 (45.1%)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That respondents with consistent value preferences under identical demographics form high-consensus groups whose preferences generalize reliably to unseen demographic combinations, countries, and value dimensions without introducing selection bias from the filtering process."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DVMap extracts high-consensus demographic groups from survey data and applies structured CoT plus GRPO to align LLMs with pluralistic values, reporting 48.6% accuracy on cross-demographic generalization tests."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Mapping multi-dimensional demographics to values lets LLMs align with pluralistic preferences more tightly than national labels allow."}],"snapshot_sha256":"e7efeb561748dd2928a5e4244546c1a37df70476bf280d3190bad63fd10bdac4"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Current Large Language Models (LLMs) typically rely on coarse-grained national labels for pluralistic value alignment. However, such macro-level supervision often obscures intra-country value heterogeneity, yielding a loose alignment. We argue that resolving this limitation requires shifting from national labels to multi-dimensional demographic constraints, which can identify groups with predictable, high-consensus value preference. To this end, we propose DVMap (High-Consensus Demographic-Value Mapping), a framework for fine-grained pluralistic value alignment. In this framework, we first pre","authors_text":"Deyi Xiong, Lei Yang, Pengyun Zhu, Yuqi Ren, Zhen Wang","cross_cats":[],"headline":"Mapping multi-dimensional demographics to values lets LLMs align with pluralistic preferences more tightly than national labels allow.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T06:06:43Z","title":"DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping"},"references":{"count":13,"internal_anchors":3,"resolved_work":13,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Association for Computational Linguistics","work_id":"0f9b87ad-f0c9-436f-9b1b-faa8e4a7c8ac","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"In9th International Conference on Learning Representa- tions, ICLR 2021, Virtual Event, Austria, May 3-7,","work_id":"c1e314ad-45cb-40dd-b862-9ec0b81988ab","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"The ghost in the machine has an american accent: value conflict in gpt-3","work_id":"9324c45e-22da-43e3-ab89-872beb2e2d38","year":2005},{"cited_arxiv_id":"2410.21276","doi":"","is_internal_anchor":true,"ref_index":4,"title":"GPT-4o System Card","work_id":"f37bf1c7-4964-4e56-9762-d20da8d9009f","year":2024},{"cited_arxiv_id":"2402.03300","doi":"","is_internal_anchor":true,"ref_index":5,"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","year":2023}],"snapshot_sha256":"263acef597a6a6c4e7132dd426fba196803313f84736e1e0457180bce9ceca5d"},"source":{"id":"2605.14420","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:00:43.241257Z","id":"7b321340-df51-4e83-b4c7-f707353752d6","model_set":{"reader":"grok-4.3"},"one_line_summary":"DVMap extracts high-consensus demographic groups from survey data and applies structured CoT plus GRPO to align LLMs with pluralistic values, reporting 48.6% accuracy on cross-demographic generalization tests.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Mapping multi-dimensional demographics to values lets LLMs align with pluralistic preferences more tightly than national labels allow.","strongest_claim":"Experimental results demonstrate that DVMap effectively learns the manifold mapping from demographics to values, exhibiting strong generalization and robustness. On cross-demographic tests, Qwen3-8B-DVMap achieves 48.6% accuracy, surpassing the advanced open-source LLM DeepSeek-v3.2 (45.1%).","weakest_assumption":"That respondents with consistent value preferences under identical demographics form high-consensus groups whose preferences generalize reliably to unseen demographic combinations, countries, and value dimensions without introducing selection bias from the filtering process."}},"verdict_id":"7b321340-df51-4e83-b4c7-f707353752d6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c424e4322d520245656de39ac1152af8cb543944a44f1e2ae7a9b766a7884e5a","target":"record","created_at":"2026-05-17T23:39:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c91590de42b5a804214f8208f8df15cd4f4dbe0bac972796c53d66bc2643e8bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T06:06:43Z","title_canon_sha256":"009dbf78b25110196922624fc51b4f534fa998a308da3ec9f027563ca85210fd"},"schema_version":"1.0","source":{"id":"2605.14420","kind":"arxiv","version":1}},"canonical_sha256":"50ac70969f3256aa33b6f9e67ed9ccd7a77775061ea916528042308045e2b7ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50ac70969f3256aa33b6f9e67ed9ccd7a77775061ea916528042308045e2b7ea","first_computed_at":"2026-05-17T23:39:07.259501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:07.259501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1C48i2T0VI59tdyGj+UwSY+V/Cp4thVzyaTlTJGbTuCRIDCP0AcGPLcfB5QKlRBq87iwCUqVSYrfCc9ws4qGDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:07.260151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14420","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c424e4322d520245656de39ac1152af8cb543944a44f1e2ae7a9b766a7884e5a","sha256:875429392f827305567c9a3a76ab5cb284306012866f4a6f539e08e3aa63e607"],"state_sha256":"30059b502172b19933421090117031c92db04162a803be088b93514265da68a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WQaDa8k6T40vB0IjDEyS1mEIIuWFN8re9dy2Uro2z7wKqmWD7AqgGVa9fsgQ1jbtSgapROPfVfpwATvdEFTWAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T05:28:33.785268Z","bundle_sha256":"3c63c96b9c04cd4aed3840c90f3f0e8929a75eeb0da974cc9aebfe2d1a88c2f6"}}