{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VZGLVJCEZLYAIXQSUP7YHN7GGO","short_pith_number":"pith:VZGLVJCE","schema_version":"1.0","canonical_sha256":"ae4cbaa444caf0045e12a3ff83b7e6339ff567888dba922c0c17620d62769b24","source":{"kind":"arxiv","id":"2306.06234","version":1},"attestation_state":"computed","paper":{"title":"Using Foundation Models to Detect Policy Violations with Minimal Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Frederick Liu, Mukund Sundararajan, Sid Mittal, Vineet Gupta","submitted_at":"2023-06-09T20:08:48Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.06234","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-09T20:08:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db13841b6c34acb155d86e88940e19c894b3d5d024b2188c710a4031a65484f7","abstract_canon_sha256":"b60069942b863d7b874c02bd3eb0ca9f6e7967433a08b0a92d429394ed0103ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:22.280832Z","signature_b64":"wx3/n0xKVwNlRdckaJHA+fTta8xMSc1UkgQ9mtYuDjjZtrPnsqSB4YqJ9qzp7Ho9AqfXEE7gNG7+id2+gEZeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae4cbaa444caf0045e12a3ff83b7e6339ff567888dba922c0c17620d62769b24","last_reissued_at":"2026-07-05T06:19:22.280425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:22.280425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Foundation Models to Detect Policy Violations with Minimal Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Frederick Liu, Mukund Sundararajan, Sid Mittal, Vineet Gupta","submitted_at":"2023-06-09T20:08:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06234","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.06234/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.06234","created_at":"2026-07-05T06:19:22.280485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06234v1","created_at":"2026-07-05T06:19:22.280485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06234","created_at":"2026-07-05T06:19:22.280485+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZGLVJCEZLYA","created_at":"2026-07-05T06:19:22.280485+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZGLVJCEZLYAIXQS","created_at":"2026-07-05T06:19:22.280485+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZGLVJCE","created_at":"2026-07-05T06:19:22.280485+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZGLVJCEZLYAIXQSUP7YHN7GGO","json":"https://pith.science/pith/VZGLVJCEZLYAIXQSUP7YHN7GGO.json","graph_json":"https://pith.science/api/pith-number/VZGLVJCEZLYAIXQSUP7YHN7GGO/graph.json","events_json":"https://pith.science/api/pith-number/VZGLVJCEZLYAIXQSUP7YHN7GGO/events.json","paper":"https://pith.science/paper/VZGLVJCE"},"agent_actions":{"view_html":"https://pith.science/pith/VZGLVJCEZLYAIXQSUP7YHN7GGO","download_json":"https://pith.science/pith/VZGLVJCEZLYAIXQSUP7YHN7GGO.json","view_paper":"https://pith.science/paper/VZGLVJCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06234&json=true","fetch_graph":"https://pith.science/api/pith-number/VZGLVJCEZLYAIXQSUP7YHN7GGO/graph.json","fetch_events":"https://pith.science/api/pith-number/VZGLVJCEZLYAIXQSUP7YHN7GGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZGLVJCEZLYAIXQSUP7YHN7GGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZGLVJCEZLYAIXQSUP7YHN7GGO/action/storage_attestation","attest_author":"https://pith.science/pith/VZGLVJCEZLYAIXQSUP7YHN7GGO/action/author_attestation","sign_citation":"https://pith.science/pith/VZGLVJCEZLYAIXQSUP7YHN7GGO/action/citation_signature","submit_replication":"https://pith.science/pith/VZGLVJCEZLYAIXQSUP7YHN7GGO/action/replication_record"}},"created_at":"2026-07-05T06:19:22.280485+00:00","updated_at":"2026-07-05T06:19:22.280485+00:00"}