{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7KAZAPC5RLPHSGPKTTHQPBT2RS","short_pith_number":"pith:7KAZAPC5","canonical_record":{"source":{"id":"2412.00765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-01T10:58:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"08382c623bc58b91343466f64acab386c21340fec7c9a74b460b5f1e3147be9d","abstract_canon_sha256":"896622e04cb15129a71c92d14629b837a7cbff676dfb187a16539e008c42f131"},"schema_version":"1.0"},"canonical_sha256":"fa81903c5d8ade7919ea9ccf07867a8c856858fb18eb501bb618261f11041af8","source":{"kind":"arxiv","id":"2412.00765","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00765","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00765v1","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00765","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"pith_short_12","alias_value":"7KAZAPC5RLPH","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"pith_short_16","alias_value":"7KAZAPC5RLPHSGPK","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"pith_short_8","alias_value":"7KAZAPC5","created_at":"2026-07-05T09:42:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7KAZAPC5RLPHSGPKTTHQPBT2RS","target":"record","payload":{"canonical_record":{"source":{"id":"2412.00765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-01T10:58:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"08382c623bc58b91343466f64acab386c21340fec7c9a74b460b5f1e3147be9d","abstract_canon_sha256":"896622e04cb15129a71c92d14629b837a7cbff676dfb187a16539e008c42f131"},"schema_version":"1.0"},"canonical_sha256":"fa81903c5d8ade7919ea9ccf07867a8c856858fb18eb501bb618261f11041af8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:47.211476Z","signature_b64":"k5PuU651zq7SXom3LfgSwiWgKbH1qy6WIDOP5mcprWkIgoJLnMipaNoZd1aVrUEYLNw0iVoOalfkJyWveNaIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa81903c5d8ade7919ea9ccf07867a8c856858fb18eb501bb618261f11041af8","last_reissued_at":"2026-07-05T09:42:47.211014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:47.211014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.00765","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":"2026-07-05T09:42:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vhiDx7stFOhMDtrnqS+pk4RK2sUkUZvs8QdSzxFjSet02MqaYgTmMaIZF3gTxzZUg3DD4j2PYPiSaI+c4MQJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:35:03.895011Z"},"content_sha256":"bd97c38544db9edba53c8c66659163840e461724d9eb715dfc4893d00d1f7137","schema_version":"1.0","event_id":"sha256:bd97c38544db9edba53c8c66659163840e461724d9eb715dfc4893d00d1f7137"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7KAZAPC5RLPHSGPKTTHQPBT2RS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SelfPrompt: Autonomously Evaluating LLM Robustness via Domain-Constrained Knowledge Guidelines and Refined Adversarial Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aihua Pei, Ju Jia, Ruoxi Cheng, Shunan Zhu, Zehua Yang","submitted_at":"2024-12-01T10:58:53Z","abstract_excerpt":"Traditional methods for evaluating the robustness of large language models (LLMs) often rely on standardized benchmarks, which can escalate costs and limit evaluations across varied domains. This paper introduces a novel framework designed to autonomously evaluate the robustness of LLMs by incorporating refined adversarial prompts and domain-constrained knowledge guidelines in the form of knowledge graphs. Our method systematically generates descriptive sentences from domain-constrained knowledge graph triplets to formulate adversarial prompts, enhancing the relevance and challenge of the eval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00765","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/2412.00765/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":"2026-07-05T09:42:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ebP+GmmG+pdwbDk0garFTV4Lmb8N6Y4D//Q68SHPoTWm4eydDzaXOw0a68r2BVdbd1FNFBipmstlDXV5DveuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:35:03.895512Z"},"content_sha256":"e70a0e10d874d8ac53dbdc5488f02b2a2db070e81cc8066acabe3645822bf2f6","schema_version":"1.0","event_id":"sha256:e70a0e10d874d8ac53dbdc5488f02b2a2db070e81cc8066acabe3645822bf2f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7KAZAPC5RLPHSGPKTTHQPBT2RS/bundle.json","state_url":"https://pith.science/pith/7KAZAPC5RLPHSGPKTTHQPBT2RS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7KAZAPC5RLPHSGPKTTHQPBT2RS/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":"2026-08-08T06:35:03Z","links":{"resolver":"https://pith.science/pith/7KAZAPC5RLPHSGPKTTHQPBT2RS","bundle":"https://pith.science/pith/7KAZAPC5RLPHSGPKTTHQPBT2RS/bundle.json","state":"https://pith.science/pith/7KAZAPC5RLPHSGPKTTHQPBT2RS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7KAZAPC5RLPHSGPKTTHQPBT2RS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7KAZAPC5RLPHSGPKTTHQPBT2RS","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":"896622e04cb15129a71c92d14629b837a7cbff676dfb187a16539e008c42f131","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-01T10:58:53Z","title_canon_sha256":"08382c623bc58b91343466f64acab386c21340fec7c9a74b460b5f1e3147be9d"},"schema_version":"1.0","source":{"id":"2412.00765","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00765","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00765v1","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00765","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"pith_short_12","alias_value":"7KAZAPC5RLPH","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"pith_short_16","alias_value":"7KAZAPC5RLPHSGPK","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"pith_short_8","alias_value":"7KAZAPC5","created_at":"2026-07-05T09:42:47Z"}],"graph_snapshots":[{"event_id":"sha256:e70a0e10d874d8ac53dbdc5488f02b2a2db070e81cc8066acabe3645822bf2f6","target":"graph","created_at":"2026-07-05T09:42:47Z","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/2412.00765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional methods for evaluating the robustness of large language models (LLMs) often rely on standardized benchmarks, which can escalate costs and limit evaluations across varied domains. This paper introduces a novel framework designed to autonomously evaluate the robustness of LLMs by incorporating refined adversarial prompts and domain-constrained knowledge guidelines in the form of knowledge graphs. Our method systematically generates descriptive sentences from domain-constrained knowledge graph triplets to formulate adversarial prompts, enhancing the relevance and challenge of the eval","authors_text":"Aihua Pei, Ju Jia, Ruoxi Cheng, Shunan Zhu, Zehua Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-01T10:58:53Z","title":"SelfPrompt: Autonomously Evaluating LLM Robustness via Domain-Constrained Knowledge Guidelines and Refined Adversarial Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00765","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:bd97c38544db9edba53c8c66659163840e461724d9eb715dfc4893d00d1f7137","target":"record","created_at":"2026-07-05T09:42:47Z","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":"896622e04cb15129a71c92d14629b837a7cbff676dfb187a16539e008c42f131","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-01T10:58:53Z","title_canon_sha256":"08382c623bc58b91343466f64acab386c21340fec7c9a74b460b5f1e3147be9d"},"schema_version":"1.0","source":{"id":"2412.00765","kind":"arxiv","version":1}},"canonical_sha256":"fa81903c5d8ade7919ea9ccf07867a8c856858fb18eb501bb618261f11041af8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa81903c5d8ade7919ea9ccf07867a8c856858fb18eb501bb618261f11041af8","first_computed_at":"2026-07-05T09:42:47.211014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:47.211014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k5PuU651zq7SXom3LfgSwiWgKbH1qy6WIDOP5mcprWkIgoJLnMipaNoZd1aVrUEYLNw0iVoOalfkJyWveNaIBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:47.211476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00765","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd97c38544db9edba53c8c66659163840e461724d9eb715dfc4893d00d1f7137","sha256:e70a0e10d874d8ac53dbdc5488f02b2a2db070e81cc8066acabe3645822bf2f6"],"state_sha256":"d3d05db82b3dde3507a5e83d819f36dfe53afe396107b74c5f8f416f3c44c0ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cZDtKLaodiE6SXd8uGImv+qplD0KO5lbEu3P4eC0P9DDgD/FO/SjvRBuHEyAbmj5OLJIDKfGaK8iey8PNkS5Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:35:03.900859Z","bundle_sha256":"2257e6ee631da9949957d432c7221f128fa12bf1fd376ceedac7affe36f4354e"}}