{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VZGLVJCEZLYAIXQSUP7YHN7GGO","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":"b60069942b863d7b874c02bd3eb0ca9f6e7967433a08b0a92d429394ed0103ec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T20:08:48Z","title_canon_sha256":"db13841b6c34acb155d86e88940e19c894b3d5d024b2188c710a4031a65484f7"},"schema_version":"1.0","source":{"id":"2306.06234","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06234","created_at":"2026-07-05T06:19:22Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06234v1","created_at":"2026-07-05T06:19:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06234","created_at":"2026-07-05T06:19:22Z"},{"alias_kind":"pith_short_12","alias_value":"VZGLVJCEZLYA","created_at":"2026-07-05T06:19:22Z"},{"alias_kind":"pith_short_16","alias_value":"VZGLVJCEZLYAIXQS","created_at":"2026-07-05T06:19:22Z"},{"alias_kind":"pith_short_8","alias_value":"VZGLVJCE","created_at":"2026-07-05T06:19:22Z"}],"graph_snapshots":[{"event_id":"sha256:8365b76ab8a2b095b03a0db685a055931683f2b32cee3c0986dc5a6cb7b05fa2","target":"graph","created_at":"2026-07-05T06:19:22Z","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/2306.06234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation models, i.e. large neural networks pre-trained on large text corpora, have revolutionized NLP. They can be instructed directly (e.g. (arXiv:2005.14165)) - this is called hard prompting - and they can be tuned using very little data (e.g. (arXiv:2104.08691)) - this technique is called soft prompting. We seek to leverage their capabilities to detect policy violations. Our contributions are: We identify a hard prompt that adapts chain-of-thought prompting to policy violation tasks. This prompt produces policy violation classifications, along with extractive explanations that justify th","authors_text":"Frederick Liu, Mukund Sundararajan, Sid Mittal, Vineet Gupta","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T20:08:48Z","title":"Using Foundation Models to Detect Policy Violations with Minimal Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06234","kind":"arxiv","version":1},"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:e357ed2c2f3bd8b836dc1724363a011e1490f6214e5fbba352bb09add54f9076","target":"record","created_at":"2026-07-05T06:19:22Z","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":"b60069942b863d7b874c02bd3eb0ca9f6e7967433a08b0a92d429394ed0103ec","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T20:08:48Z","title_canon_sha256":"db13841b6c34acb155d86e88940e19c894b3d5d024b2188c710a4031a65484f7"},"schema_version":"1.0","source":{"id":"2306.06234","kind":"arxiv","version":1}},"canonical_sha256":"ae4cbaa444caf0045e12a3ff83b7e6339ff567888dba922c0c17620d62769b24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae4cbaa444caf0045e12a3ff83b7e6339ff567888dba922c0c17620d62769b24","first_computed_at":"2026-07-05T06:19:22.280425Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:22.280425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wx3/n0xKVwNlRdckaJHA+fTta8xMSc1UkgQ9mtYuDjjZtrPnsqSB4YqJ9qzp7Ho9AqfXEE7gNG7+id2+gEZeDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:22.280832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.06234","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e357ed2c2f3bd8b836dc1724363a011e1490f6214e5fbba352bb09add54f9076","sha256:8365b76ab8a2b095b03a0db685a055931683f2b32cee3c0986dc5a6cb7b05fa2"],"state_sha256":"1378cde3dc8ddde59b489bf6a4da085fb08add7b4773d3a97b899bd36c8da652"}