{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6K6TYYGYPAQNU2TSAQ3G5IFID3","short_pith_number":"pith:6K6TYYGY","canonical_record":{"source":{"id":"2410.11114","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T21:48:14Z","cross_cats_sorted":[],"title_canon_sha256":"07fc3ceb9004e1a7b2c343d4fdccb8900294fdfdce8bff67aedb1ae7246289de","abstract_canon_sha256":"c9418af76c21bd5373901ed69dcd1cc94015a22194c63266c5db8cb12d925a14"},"schema_version":"1.0"},"canonical_sha256":"f2bd3c60d87820da6a7204366ea0a81ed479718505ab183c550eaee3c7a4d8ec","source":{"kind":"arxiv","id":"2410.11114","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11114","created_at":"2026-07-05T09:20:29Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11114v1","created_at":"2026-07-05T09:20:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11114","created_at":"2026-07-05T09:20:29Z"},{"alias_kind":"pith_short_12","alias_value":"6K6TYYGYPAQN","created_at":"2026-07-05T09:20:29Z"},{"alias_kind":"pith_short_16","alias_value":"6K6TYYGYPAQNU2TS","created_at":"2026-07-05T09:20:29Z"},{"alias_kind":"pith_short_8","alias_value":"6K6TYYGY","created_at":"2026-07-05T09:20:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6K6TYYGYPAQNU2TSAQ3G5IFID3","target":"record","payload":{"canonical_record":{"source":{"id":"2410.11114","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T21:48:14Z","cross_cats_sorted":[],"title_canon_sha256":"07fc3ceb9004e1a7b2c343d4fdccb8900294fdfdce8bff67aedb1ae7246289de","abstract_canon_sha256":"c9418af76c21bd5373901ed69dcd1cc94015a22194c63266c5db8cb12d925a14"},"schema_version":"1.0"},"canonical_sha256":"f2bd3c60d87820da6a7204366ea0a81ed479718505ab183c550eaee3c7a4d8ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:29.351452Z","signature_b64":"8Y+0P3I3zhvHZvKVq5oNNl0MjyV4HZLQ+dYJSIG8hKJg87id51dHt+ifdAqBs2YzW2AMYrJDpWBWzdWfb2jfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2bd3c60d87820da6a7204366ea0a81ed479718505ab183c550eaee3c7a4d8ec","last_reissued_at":"2026-07-05T09:20:29.350970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:29.350970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.11114","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:20:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X1ZdfRee4ouv+MK1SLsMuXcD++n49B/bMxlhfKqUePUw0bLRcORPhvThgvDKzxRe9of9Jk8IiQO0QH4QmVKUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:22:11.576974Z"},"content_sha256":"5bdc3936cdc15480cd319c8581a4e05f31f366832e474388207476328faf87c3","schema_version":"1.0","event_id":"sha256:5bdc3936cdc15480cd319c8581a4e05f31f366832e474388207476328faf87c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6K6TYYGYPAQNU2TSAQ3G5IFID3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Active Learning for Robust and Representative LLM Generation in Safety-Critical Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anthony Sicilia, Malihe Alikhani, Sabit Hassan","submitted_at":"2024-10-14T21:48:14Z","abstract_excerpt":"Ensuring robust safety measures across a wide range of scenarios is crucial for user-facing systems. While Large Language Models (LLMs) can generate valuable data for safety measures, they often exhibit distributional biases, focusing on common scenarios and neglecting rare but critical cases. This can undermine the effectiveness of safety protocols developed using such data. To address this, we propose a novel framework that integrates active learning with clustering to guide LLM generation, enhancing their representativeness and robustness in safety scenarios. We demonstrate the effectivenes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11114","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/2410.11114/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:20:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hKqQgkaW57ORuRnHd/Cw1heZgFqkhA1seL3eY59++zausS1BNHnOYRjzyhckm//bFwQkT3tC/CsIK3eRCv9GCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:22:11.577479Z"},"content_sha256":"d7ca10d69deff8d3fb3728a91a7525480453d373c865e9dd7858b4417f8d6854","schema_version":"1.0","event_id":"sha256:d7ca10d69deff8d3fb3728a91a7525480453d373c865e9dd7858b4417f8d6854"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6K6TYYGYPAQNU2TSAQ3G5IFID3/bundle.json","state_url":"https://pith.science/pith/6K6TYYGYPAQNU2TSAQ3G5IFID3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6K6TYYGYPAQNU2TSAQ3G5IFID3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T09:22:11Z","links":{"resolver":"https://pith.science/pith/6K6TYYGYPAQNU2TSAQ3G5IFID3","bundle":"https://pith.science/pith/6K6TYYGYPAQNU2TSAQ3G5IFID3/bundle.json","state":"https://pith.science/pith/6K6TYYGYPAQNU2TSAQ3G5IFID3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6K6TYYGYPAQNU2TSAQ3G5IFID3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6K6TYYGYPAQNU2TSAQ3G5IFID3","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":"c9418af76c21bd5373901ed69dcd1cc94015a22194c63266c5db8cb12d925a14","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T21:48:14Z","title_canon_sha256":"07fc3ceb9004e1a7b2c343d4fdccb8900294fdfdce8bff67aedb1ae7246289de"},"schema_version":"1.0","source":{"id":"2410.11114","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11114","created_at":"2026-07-05T09:20:29Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11114v1","created_at":"2026-07-05T09:20:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11114","created_at":"2026-07-05T09:20:29Z"},{"alias_kind":"pith_short_12","alias_value":"6K6TYYGYPAQN","created_at":"2026-07-05T09:20:29Z"},{"alias_kind":"pith_short_16","alias_value":"6K6TYYGYPAQNU2TS","created_at":"2026-07-05T09:20:29Z"},{"alias_kind":"pith_short_8","alias_value":"6K6TYYGY","created_at":"2026-07-05T09:20:29Z"}],"graph_snapshots":[{"event_id":"sha256:d7ca10d69deff8d3fb3728a91a7525480453d373c865e9dd7858b4417f8d6854","target":"graph","created_at":"2026-07-05T09:20:29Z","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/2410.11114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring robust safety measures across a wide range of scenarios is crucial for user-facing systems. While Large Language Models (LLMs) can generate valuable data for safety measures, they often exhibit distributional biases, focusing on common scenarios and neglecting rare but critical cases. This can undermine the effectiveness of safety protocols developed using such data. To address this, we propose a novel framework that integrates active learning with clustering to guide LLM generation, enhancing their representativeness and robustness in safety scenarios. We demonstrate the effectivenes","authors_text":"Anthony Sicilia, Malihe Alikhani, Sabit Hassan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T21:48:14Z","title":"Active Learning for Robust and Representative LLM Generation in Safety-Critical Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11114","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":"sha256:5bdc3936cdc15480cd319c8581a4e05f31f366832e474388207476328faf87c3","target":"record","created_at":"2026-07-05T09:20:29Z","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":"c9418af76c21bd5373901ed69dcd1cc94015a22194c63266c5db8cb12d925a14","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T21:48:14Z","title_canon_sha256":"07fc3ceb9004e1a7b2c343d4fdccb8900294fdfdce8bff67aedb1ae7246289de"},"schema_version":"1.0","source":{"id":"2410.11114","kind":"arxiv","version":1}},"canonical_sha256":"f2bd3c60d87820da6a7204366ea0a81ed479718505ab183c550eaee3c7a4d8ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2bd3c60d87820da6a7204366ea0a81ed479718505ab183c550eaee3c7a4d8ec","first_computed_at":"2026-07-05T09:20:29.350970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:29.350970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Y+0P3I3zhvHZvKVq5oNNl0MjyV4HZLQ+dYJSIG8hKJg87id51dHt+ifdAqBs2YzW2AMYrJDpWBWzdWfb2jfAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:29.351452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11114","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bdc3936cdc15480cd319c8581a4e05f31f366832e474388207476328faf87c3","sha256:d7ca10d69deff8d3fb3728a91a7525480453d373c865e9dd7858b4417f8d6854"],"state_sha256":"d9e271e4c25b298115890e8c0119e37ad0db7f6765cc3969fd7ddf77744c704f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJYlCh363ziqewitpXp78AIAMcDYlUaOIccG5pH5mDyVKIg3N36pKsmXXRZo6RDLaPyV2Pv1NMoKZSda57NWDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:22:11.580906Z","bundle_sha256":"6055512fda6e5bf2642ea441aa23ac9affcbb12c87558e1e9c3314ae39474976"}}