{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AKF4OPQBKR3BCAQ2NJBA3CSSZB","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":"accb73257ce2140233708fa4eeba075f1a7a2e7f3015638fb48435f9a6b5e175","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T00:09:28Z","title_canon_sha256":"e4cfaa10f742e09c1c84a8bdd68bf0fc85dc926c52fcf0a995e66309236c203b"},"schema_version":"1.0","source":{"id":"2601.05437","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.05437","created_at":"2026-05-20T01:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2601.05437v3","created_at":"2026-05-20T01:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.05437","created_at":"2026-05-20T01:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"AKF4OPQBKR3B","created_at":"2026-05-20T01:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"AKF4OPQBKR3BCAQ2","created_at":"2026-05-20T01:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"AKF4OPQB","created_at":"2026-05-20T01:05:05Z"}],"graph_snapshots":[{"event_id":"sha256:7652db0d586b8bd488a1a7cd7bbac25832db750931f7a95e4ef649f4f70dd96e","target":"graph","created_at":"2026-05-20T01:05:05Z","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":"Models represent and distinguish moral foundations in a manner that aligns with human judgments, and this moral geometry naturally emerges from pretraining and is selectively rewired by post-training; steering along dense vectors or sparse SAE features produces predictable shifts in foundation-relevant behavior."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the chosen Moral Foundations Theory categories and the SAE feature extraction faithfully capture the models' internal moral concepts rather than imposing an external taxonomy or detecting spurious correlations."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Moral foundations in LLMs form distributed, layered representations that align with human perceptions, emerge from pretraining, and causally influence outputs when steered via dense vectors or sparse features."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Large language models develop internal representations of moral foundations that align with human judgments and emerge naturally during pretraining."}],"snapshot_sha256":"b64b2bfc9bedb53cfe0a377193f17ac33089468fb77d279909fb0fe5cad252e0"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7c493822b549d0aa63e919326c21f4034b258aa9969bdaf706a14b8f38994438"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.05437/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models often produce human-like moral judgments, but it is unclear whether this reflects an internal conceptual structure or superficial ``moral mimicry.'' Using Moral Foundations Theory (MFT) as an analytic framework, we study how moral foundations are encoded, organized, and expressed across 14 base and instruction-tuned LLMs spanning four model families (Llama, Qwen2.5, Qwen3-MoE, Mistral) and scales from 7B to 70B. We employ a multi-level approach combining (i) layer-wise analysis of MFT concept representations and their alignment with human moral perceptions, (ii) pretraine","authors_text":"Bowen Yi, Chenxiao Yu, Farzan Karimi-Malekabadi, Jinyi Ye, Morteza Dehghani, Shrikanth Narayanan, Suhaib Abdurahman, Yue Zhao","cross_cats":["cs.AI"],"headline":"Large language models develop internal representations of moral foundations that align with human judgments and emerge naturally during pretraining.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T00:09:28Z","title":"Tracing Moral Foundations in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.05437","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T16:59:48.755039Z","id":"b05af869-480c-4c50-9d0e-3898f96bbcaa","model_set":{"reader":"grok-4.3"},"one_line_summary":"Moral foundations in LLMs form distributed, layered representations that align with human perceptions, emerge from pretraining, and causally influence outputs when steered via dense vectors or sparse features.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Large language models develop internal representations of moral foundations that align with human judgments and emerge naturally during pretraining.","strongest_claim":"Models represent and distinguish moral foundations in a manner that aligns with human judgments, and this moral geometry naturally emerges from pretraining and is selectively rewired by post-training; steering along dense vectors or sparse SAE features produces predictable shifts in foundation-relevant behavior.","weakest_assumption":"That the chosen Moral Foundations Theory categories and the SAE feature extraction faithfully capture the models' internal moral concepts rather than imposing an external taxonomy or detecting spurious correlations."}},"verdict_id":"b05af869-480c-4c50-9d0e-3898f96bbcaa"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b753f49ee0d2006d80e39c120de00c1abdbb5c8e585c738ef01f48cefea25f5d","target":"record","created_at":"2026-05-20T01:05:05Z","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":"accb73257ce2140233708fa4eeba075f1a7a2e7f3015638fb48435f9a6b5e175","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T00:09:28Z","title_canon_sha256":"e4cfaa10f742e09c1c84a8bdd68bf0fc85dc926c52fcf0a995e66309236c203b"},"schema_version":"1.0","source":{"id":"2601.05437","kind":"arxiv","version":3}},"canonical_sha256":"028bc73e01547611021a6a420d8a52c86b195b7e4a0a6509d5d62dbfbfa6e618","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"028bc73e01547611021a6a420d8a52c86b195b7e4a0a6509d5d62dbfbfa6e618","first_computed_at":"2026-05-20T01:05:05.847808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:05.847808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uts1P3FsEy4SNmvXmZByuveACcT7gSRXOZRGS2BhhyYDT4Za58oXjv40Hz2wjpaXiYVbfl2DJn/l3mmWLO78Dg==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:05.848526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.05437","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b753f49ee0d2006d80e39c120de00c1abdbb5c8e585c738ef01f48cefea25f5d","sha256:7652db0d586b8bd488a1a7cd7bbac25832db750931f7a95e4ef649f4f70dd96e"],"state_sha256":"d5b761296017ecfc98f6cc3e166b769f6942380376aec015da8e51499ab5604c"}