{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G4GHMHBWFL7MDPPJFTBMA22ZWU","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":"7db267445fbb73c478a4ba284eb737d6fe47151f307d7fdbbf22dfe9dc31fa5a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-02T23:22:23Z","title_canon_sha256":"0a6d59f6026b8db4246e3eb66cb13bd5be108f1ead3cb0cb2b9b03fc1ba274cc"},"schema_version":"1.0","source":{"id":"2605.01642","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01642","created_at":"2026-06-08T01:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01642v2","created_at":"2026-06-08T01:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01642","created_at":"2026-06-08T01:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"G4GHMHBWFL7M","created_at":"2026-06-08T01:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"G4GHMHBWFL7MDPPJ","created_at":"2026-06-08T01:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"G4GHMHBW","created_at":"2026-06-08T01:05:11Z"}],"graph_snapshots":[{"event_id":"sha256:afa1a28f9623a526557a7df3bf3ce6d20457b00327abbcc32bf42a6533ba0eeb","target":"graph","created_at":"2026-06-08T01:05:11Z","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":"APA has three stages: (1) learning compact personalized reward models via low-rank reward basis decomposition, (2) using these models as a jury that collectively selects among candidate outputs through social-choice-theoretic voting, and (3) efficiently adapting the jury over time by fitting new annotator weights over the fixed reward bases as values shift."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That low-rank reward basis decomposition captures enough structure of individual preferences for weight-only adaptation to track genuine value shifts without requiring updates to the bases themselves."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"APA is a modular pipeline that decomposes preferences into compact reward bases, aggregates them via jury voting, and adapts only annotator weights over time to track shifting values."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A pipeline called Adaptive Pluralistic Alignment lets AI systems update their pluralistic alignment by adapting only the weights on fixed reward model bases as values evolve."}],"snapshot_sha256":"37a9c34592236c6f1f268d08c5c44f64dcae2b52695a78f748a02347dd33edd0"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T17:38:53.658885Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T17:06:53.677301Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.01642/integrity.json","findings":[],"snapshot_sha256":"64177b1b75c49b2aa47ce8e766227233f29d58a3025c5f1f35ab22e8c4e1b63e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prevailing alignment methods target a fixed set of preferences and therefore risk forcing value lock-in as societal norms evolve over time. We introduce Adaptive Pluralistic Alignment (APA), a modular pipeline for updating pluralistically aligned AI systems to track evolving values and avoid value lock-in without repeating costly pretraining or large-scale data collection. APA has three stages: (1) learning compact personalized reward models via low-rank reward basis decomposition, (2) using these models as a jury that collectively selects among candidate outputs through social-choice-theoreti","authors_text":"Rachel Freedman","cross_cats":[],"headline":"A pipeline called Adaptive Pluralistic Alignment lets AI systems update their pluralistic alignment by adapting only the weights on fixed reward model bases as values evolve.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-02T23:22:23Z","title":"Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.01642","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-09T14:03:40.273306Z","id":"eb02e5e7-cc9a-461d-8b4f-4a9f595192a1","model_set":{"reader":"grok-4.3"},"one_line_summary":"APA is a modular pipeline that decomposes preferences into compact reward bases, aggregates them via jury voting, and adapts only annotator weights over time to track shifting values.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A pipeline called Adaptive Pluralistic Alignment lets AI systems update their pluralistic alignment by adapting only the weights on fixed reward model bases as values evolve.","strongest_claim":"APA has three stages: (1) learning compact personalized reward models via low-rank reward basis decomposition, (2) using these models as a jury that collectively selects among candidate outputs through social-choice-theoretic voting, and (3) efficiently adapting the jury over time by fitting new annotator weights over the fixed reward bases as values shift.","weakest_assumption":"That low-rank reward basis decomposition captures enough structure of individual preferences for weight-only adaptation to track genuine value shifts without requiring updates to the bases themselves."}},"verdict_id":"eb02e5e7-cc9a-461d-8b4f-4a9f595192a1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:69c06ae91a3bc16374f95a3bde5c52d1a9b4e7679d7dc352eecfa184b544c7a4","target":"record","created_at":"2026-06-08T01:05:11Z","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":"7db267445fbb73c478a4ba284eb737d6fe47151f307d7fdbbf22dfe9dc31fa5a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-02T23:22:23Z","title_canon_sha256":"0a6d59f6026b8db4246e3eb66cb13bd5be108f1ead3cb0cb2b9b03fc1ba274cc"},"schema_version":"1.0","source":{"id":"2605.01642","kind":"arxiv","version":2}},"canonical_sha256":"370c761c362afec1bde92cc2c06b59b536e1521cb265041bf4a6f62f979ed328","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"370c761c362afec1bde92cc2c06b59b536e1521cb265041bf4a6f62f979ed328","first_computed_at":"2026-06-08T01:05:11.480182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:05:11.480182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SatNPo5N42RAxIXaLn5SlgcBwOcT6VEjDYBeIaH4+yFfax0KDLagFlUym5N5Pk1RNF3QB32RtNF6+gsKErnkBQ==","signature_status":"signed_v1","signed_at":"2026-06-08T01:05:11.481116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.01642","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69c06ae91a3bc16374f95a3bde5c52d1a9b4e7679d7dc352eecfa184b544c7a4","sha256:afa1a28f9623a526557a7df3bf3ce6d20457b00327abbcc32bf42a6533ba0eeb"],"state_sha256":"fb314cfe702fc50b18ffc18c46582b6384821d617f86d89bdc65f30c4d1a0928"}