{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:S5TMPXHEHIFX6W75VKEZYC5VMN","short_pith_number":"pith:S5TMPXHE","canonical_record":{"source":{"id":"2501.17132","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-01-28T18:25:11Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c24e36ceb3be153bdf1830c9aab4ba8c79886e89d052b81b4644a22fee7104d5","abstract_canon_sha256":"af0599707523b84aa3c397406c522ed088ec09b8386cf09633fadb21e197842b"},"schema_version":"1.0"},"canonical_sha256":"9766c7dce43a0b7f5bfdaa899c0bb5634a328f7a756a89ae1bf5a0b458928a48","source":{"kind":"arxiv","id":"2501.17132","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17132","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17132v1","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17132","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"pith_short_12","alias_value":"S5TMPXHEHIFX","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"pith_short_16","alias_value":"S5TMPXHEHIFX6W75","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"pith_short_8","alias_value":"S5TMPXHE","created_at":"2026-07-05T10:06:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:S5TMPXHEHIFX6W75VKEZYC5VMN","target":"record","payload":{"canonical_record":{"source":{"id":"2501.17132","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-01-28T18:25:11Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c24e36ceb3be153bdf1830c9aab4ba8c79886e89d052b81b4644a22fee7104d5","abstract_canon_sha256":"af0599707523b84aa3c397406c522ed088ec09b8386cf09633fadb21e197842b"},"schema_version":"1.0"},"canonical_sha256":"9766c7dce43a0b7f5bfdaa899c0bb5634a328f7a756a89ae1bf5a0b458928a48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:34.808636Z","signature_b64":"KPT2wtZZJcGL53DC35mQAu8dHszgPgGWML6VxbvVdh7mFg1Q/Bf2OKALTA4rXHcHKDQHG6jRmRgJFrW1DBxTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9766c7dce43a0b7f5bfdaa899c0bb5634a328f7a756a89ae1bf5a0b458928a48","last_reissued_at":"2026-07-05T10:06:34.808082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:34.808082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.17132","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":"2026-07-05T10:06:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jdoL+AnhN2bW0J7qAuiAqtdq4QIdlTJ9MFOuStQlWpNK9ruCldaocV0xIn8qKqfOCz5lO4hSoyvK5wbQBgDABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:28:29.281783Z"},"content_sha256":"684d3dbbc3ce4b5d35cbe0d524245a897cc8bbe17a7c12de189fdd84a4083494","schema_version":"1.0","event_id":"sha256:684d3dbbc3ce4b5d35cbe0d524245a897cc8bbe17a7c12de189fdd84a4083494"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:S5TMPXHEHIFX6W75VKEZYC5VMN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ASTRAL: Automated Safety Testing of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Aitor Arrieta, Jos\\'e Antonio Parejo, Miriam Ugarte, Pablo Valle, Sergio Segura","submitted_at":"2025-01-28T18:25:11Z","abstract_excerpt":"Large Language Models (LLMs) have recently gained attention due to their ability to understand and generate sophisticated human-like content. However, ensuring their safety is paramount as they might provide harmful and unsafe responses. Existing LLM testing frameworks address various safety-related concerns (e.g., drugs, terrorism, animal abuse) but often face challenges due to unbalanced and obsolete datasets. In this paper, we present ASTRAL, a tool that automates the generation and execution of test cases (i.e., prompts) for testing the safety of LLMs. First, we introduce a novel black-box"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17132","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/2501.17132/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":"2026-07-05T10:06:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rBpx4DJhet1vYud5tg1rs92CYR4FF60sKHu8QSMOi4RceD6Y9kUNXK0ectxnlHJMTl/AekvW9j/O+V4tJfd/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:28:29.282697Z"},"content_sha256":"ff32747dc83e4cbddbfb37f11cfdde67151c19b336bf7db76a05f2ff4b821514","schema_version":"1.0","event_id":"sha256:ff32747dc83e4cbddbfb37f11cfdde67151c19b336bf7db76a05f2ff4b821514"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S5TMPXHEHIFX6W75VKEZYC5VMN/bundle.json","state_url":"https://pith.science/pith/S5TMPXHEHIFX6W75VKEZYC5VMN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S5TMPXHEHIFX6W75VKEZYC5VMN/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":"2026-08-05T14:28:29Z","links":{"resolver":"https://pith.science/pith/S5TMPXHEHIFX6W75VKEZYC5VMN","bundle":"https://pith.science/pith/S5TMPXHEHIFX6W75VKEZYC5VMN/bundle.json","state":"https://pith.science/pith/S5TMPXHEHIFX6W75VKEZYC5VMN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S5TMPXHEHIFX6W75VKEZYC5VMN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:S5TMPXHEHIFX6W75VKEZYC5VMN","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":"af0599707523b84aa3c397406c522ed088ec09b8386cf09633fadb21e197842b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-01-28T18:25:11Z","title_canon_sha256":"c24e36ceb3be153bdf1830c9aab4ba8c79886e89d052b81b4644a22fee7104d5"},"schema_version":"1.0","source":{"id":"2501.17132","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17132","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17132v1","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17132","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"pith_short_12","alias_value":"S5TMPXHEHIFX","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"pith_short_16","alias_value":"S5TMPXHEHIFX6W75","created_at":"2026-07-05T10:06:34Z"},{"alias_kind":"pith_short_8","alias_value":"S5TMPXHE","created_at":"2026-07-05T10:06:34Z"}],"graph_snapshots":[{"event_id":"sha256:ff32747dc83e4cbddbfb37f11cfdde67151c19b336bf7db76a05f2ff4b821514","target":"graph","created_at":"2026-07-05T10:06:34Z","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/2501.17132/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have recently gained attention due to their ability to understand and generate sophisticated human-like content. However, ensuring their safety is paramount as they might provide harmful and unsafe responses. Existing LLM testing frameworks address various safety-related concerns (e.g., drugs, terrorism, animal abuse) but often face challenges due to unbalanced and obsolete datasets. In this paper, we present ASTRAL, a tool that automates the generation and execution of test cases (i.e., prompts) for testing the safety of LLMs. First, we introduce a novel black-box","authors_text":"Aitor Arrieta, Jos\\'e Antonio Parejo, Miriam Ugarte, Pablo Valle, Sergio Segura","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-01-28T18:25:11Z","title":"ASTRAL: Automated Safety Testing of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17132","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":"sha256:684d3dbbc3ce4b5d35cbe0d524245a897cc8bbe17a7c12de189fdd84a4083494","target":"record","created_at":"2026-07-05T10:06:34Z","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":"af0599707523b84aa3c397406c522ed088ec09b8386cf09633fadb21e197842b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-01-28T18:25:11Z","title_canon_sha256":"c24e36ceb3be153bdf1830c9aab4ba8c79886e89d052b81b4644a22fee7104d5"},"schema_version":"1.0","source":{"id":"2501.17132","kind":"arxiv","version":1}},"canonical_sha256":"9766c7dce43a0b7f5bfdaa899c0bb5634a328f7a756a89ae1bf5a0b458928a48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9766c7dce43a0b7f5bfdaa899c0bb5634a328f7a756a89ae1bf5a0b458928a48","first_computed_at":"2026-07-05T10:06:34.808082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:34.808082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KPT2wtZZJcGL53DC35mQAu8dHszgPgGWML6VxbvVdh7mFg1Q/Bf2OKALTA4rXHcHKDQHG6jRmRgJFrW1DBxTDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:34.808636Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.17132","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:684d3dbbc3ce4b5d35cbe0d524245a897cc8bbe17a7c12de189fdd84a4083494","sha256:ff32747dc83e4cbddbfb37f11cfdde67151c19b336bf7db76a05f2ff4b821514"],"state_sha256":"339bffdfdc6f3d5033e5d4af672ca12bdae6ae5a3c9320f56c10898dfb516ef0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UX1lWSQ3tw8LyRGNpK56vTo9P2uTKFDqmuMl9LQP8urb7/pxhWtIueFW43r4SZSQh4bu0hnOd64HXs3J4NS+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:28:29.310467Z","bundle_sha256":"4db97b67f90b0b9b78f5eddf04f53ebebf8c4c98846d52a45f463aa7ee3b43f4"}}