{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F3B3KGLJNHD7VAXVZBMTULONZY","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":"5153960960df084090a6a0456a9608c65b18f89d6e021a7cd1db348c475e1c28","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-01T06:58:27Z","title_canon_sha256":"a77de42ad99865405473f147e356cd53ea0975f9a8d9c94b04bab99e6b16d3c3"},"schema_version":"1.0","source":{"id":"2503.17365","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17365","created_at":"2026-07-05T10:47:37Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17365v2","created_at":"2026-07-05T10:47:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17365","created_at":"2026-07-05T10:47:37Z"},{"alias_kind":"pith_short_12","alias_value":"F3B3KGLJNHD7","created_at":"2026-07-05T10:47:37Z"},{"alias_kind":"pith_short_16","alias_value":"F3B3KGLJNHD7VAXV","created_at":"2026-07-05T10:47:37Z"},{"alias_kind":"pith_short_8","alias_value":"F3B3KGLJ","created_at":"2026-07-05T10:47:37Z"}],"graph_snapshots":[{"event_id":"sha256:0c01b6fa78b33c107132f50781fb74b3e64e0d6bc9b980b685cc1cd1796ed33e","target":"graph","created_at":"2026-07-05T10:47:37Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.17365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent incidents highlight safety risks in Large Language Models (LLMs), motivating research into alignment methods like Constitutional AI (CAI). This paper explores CAI's self-critique mechanism on small, uncensored 7-9B parameter models: DeepSeek-R1-8B, Gemma-2-9B, Llama 3.1-8B, and Qwen2.5-7B. We show that while Llama-based models exhibited significant harm reduction through self-critique, other architectures demonstrated less improvement in harm detection after abliteration. These results suggest CAI's effectiveness may vary depending on model architecture and reasoning capabilities.","authors_text":"Antonio-Gabriel Chac\\'on Menke (Shibaura Institute of Technology, Kempten University of Applied Sciences), Phan Xuan Tan (Shibaura Institute of Technology)","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-01T06:58:27Z","title":"How Effective Is Constitutional AI in Small LLMs? A Study on DeepSeek-R1 and Its Peers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17365","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4f4309b63bac68cf4dc14696bf258f4c8de350ddf3a944d8e05232d5874c36b2","target":"record","created_at":"2026-07-05T10:47:37Z","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":"5153960960df084090a6a0456a9608c65b18f89d6e021a7cd1db348c475e1c28","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-01T06:58:27Z","title_canon_sha256":"a77de42ad99865405473f147e356cd53ea0975f9a8d9c94b04bab99e6b16d3c3"},"schema_version":"1.0","source":{"id":"2503.17365","kind":"arxiv","version":2}},"canonical_sha256":"2ec3b5196969c7fa82f5c8593a2dcdce2f994f11ec8ba226ab9f89602abfcd13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ec3b5196969c7fa82f5c8593a2dcdce2f994f11ec8ba226ab9f89602abfcd13","first_computed_at":"2026-07-05T10:47:37.033173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:37.033173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MiXUDZbD7+9VjA2N1i1/LKKH3FMeCXfjyhUX8vi91Sp42ISoMaQjvFvejW2LRX7a0GBr7b2ivGT2heF7hL8NAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:37.033708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.17365","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f4309b63bac68cf4dc14696bf258f4c8de350ddf3a944d8e05232d5874c36b2","sha256:0c01b6fa78b33c107132f50781fb74b3e64e0d6bc9b980b685cc1cd1796ed33e"],"state_sha256":"ec91e7f12fbe559743e6b693333baad970e7eff080a3ee39505c585fddd844ed"}