{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RLOFPROP6YAYEGVHKZTFHPSA7R","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":"be3bfd02519136b434ea5768acc4fa73da5bddcb26fd7cca16afe8695f81fe80","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-07T16:35:14Z","title_canon_sha256":"a28a9052e42abca3810a9b2de474ed3c475bd651857eb7ddcfca275e1d1dc9c0"},"schema_version":"1.0","source":{"id":"2412.06843","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06843","created_at":"2026-07-05T09:47:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06843v2","created_at":"2026-07-05T09:47:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06843","created_at":"2026-07-05T09:47:38Z"},{"alias_kind":"pith_short_12","alias_value":"RLOFPROP6YAY","created_at":"2026-07-05T09:47:38Z"},{"alias_kind":"pith_short_16","alias_value":"RLOFPROP6YAYEGVH","created_at":"2026-07-05T09:47:38Z"},{"alias_kind":"pith_short_8","alias_value":"RLOFPROP","created_at":"2026-07-05T09:47:38Z"}],"graph_snapshots":[{"event_id":"sha256:e71da9ec12cfed2d7c1bf7e97c3629029c6fbe6318868b50c0f9e30e85af0dc5","target":"graph","created_at":"2026-07-05T09:47:38Z","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/2412.06843/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) generating unsafe responses to toxic prompts is a significant issue in their applications. While various efforts aim to address this safety concern, previous approaches often demand substantial human data collection or rely on the less dependable option of using another LLM to generate corrective data. In this paper, we aim to take this problem and overcome limitations of requiring significant high-quality human data. Our method requires only a small set of unsafe responses to toxic prompts, easily obtained from the unsafe LLM itself. By employing a semantic cost c","authors_text":"Arunesh Sinha, Pradeep Varakantham, Yuxiao Lu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-07T16:35:14Z","title":"Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06843","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:b8ccd350851b708e2e978924936186c20b8e1e2421dace2c085c842416c93439","target":"record","created_at":"2026-07-05T09:47:38Z","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":"be3bfd02519136b434ea5768acc4fa73da5bddcb26fd7cca16afe8695f81fe80","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-07T16:35:14Z","title_canon_sha256":"a28a9052e42abca3810a9b2de474ed3c475bd651857eb7ddcfca275e1d1dc9c0"},"schema_version":"1.0","source":{"id":"2412.06843","kind":"arxiv","version":2}},"canonical_sha256":"8adc57c5cff601821aa7566653be40fc7ab4672f97203f230297d8a09992e559","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8adc57c5cff601821aa7566653be40fc7ab4672f97203f230297d8a09992e559","first_computed_at":"2026-07-05T09:47:38.403046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:38.403046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kzQ2rj23DunjAOUmyQI2Xa5xRAOw8AeCytxLSye4JZISVh9hRVSL0m/ANLr6A0LeA/YUC1XuDAQ6Rj9hH+sQDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:38.403541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06843","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8ccd350851b708e2e978924936186c20b8e1e2421dace2c085c842416c93439","sha256:e71da9ec12cfed2d7c1bf7e97c3629029c6fbe6318868b50c0f9e30e85af0dc5"],"state_sha256":"e7a45364e3d097fb450cd7093abec13a8ff784107bead345b83097f14dd02e80"}