{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NJ7AB4636BYGSFGLWT4G7PNTDG","short_pith_number":"pith:NJ7AB463","canonical_record":{"source":{"id":"2508.07139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-08-10T01:59:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3420a988721643ee11598581ee8d044fb7b17fdb62eda4397dccd24fcf656aff","abstract_canon_sha256":"d33e3f631fb82960230e7eac73edf3b3f09640144b70e2067b63014f42030511"},"schema_version":"1.0"},"canonical_sha256":"6a7e00f3dbf0706914cbb4f86fbdb319a7d73ae68f96606743d4c6a60f139c6e","source":{"kind":"arxiv","id":"2508.07139","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07139","created_at":"2026-07-05T11:51:41Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07139v1","created_at":"2026-07-05T11:51:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07139","created_at":"2026-07-05T11:51:41Z"},{"alias_kind":"pith_short_12","alias_value":"NJ7AB4636BYG","created_at":"2026-07-05T11:51:41Z"},{"alias_kind":"pith_short_16","alias_value":"NJ7AB4636BYGSFGL","created_at":"2026-07-05T11:51:41Z"},{"alias_kind":"pith_short_8","alias_value":"NJ7AB463","created_at":"2026-07-05T11:51:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NJ7AB4636BYGSFGLWT4G7PNTDG","target":"record","payload":{"canonical_record":{"source":{"id":"2508.07139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-08-10T01:59:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3420a988721643ee11598581ee8d044fb7b17fdb62eda4397dccd24fcf656aff","abstract_canon_sha256":"d33e3f631fb82960230e7eac73edf3b3f09640144b70e2067b63014f42030511"},"schema_version":"1.0"},"canonical_sha256":"6a7e00f3dbf0706914cbb4f86fbdb319a7d73ae68f96606743d4c6a60f139c6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:41.502089Z","signature_b64":"gOdiSZMBud7GBou29tRw4yg36uIghlvK7lb/hQzq7lYCtxMQUhJ1VBHhLvqFDMecH8E6Prs1298r1xAry+PsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a7e00f3dbf0706914cbb4f86fbdb319a7d73ae68f96606743d4c6a60f139c6e","last_reissued_at":"2026-07-05T11:51:41.501628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:41.501628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.07139","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":"2026-07-05T11:51:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CnkPi+CLlCe0VvJ5v28np1mAEmHN4Iff61W0v8OT2qP9vPOgXDqfMPeadgj0h3t6lD3/Jk97B8Ian737ep+/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:44:47.334170Z"},"content_sha256":"5977eef50fea82b96500997a6bb7fac7a81158bdce329a350705ba336ea3d320","schema_version":"1.0","event_id":"sha256:5977eef50fea82b96500997a6bb7fac7a81158bdce329a350705ba336ea3d320"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NJ7AB4636BYGSFGLWT4G7PNTDG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Ivan Zhang","submitted_at":"2025-08-10T01:59:07Z","abstract_excerpt":"Ensuring LLM alignment is critical to information security as AI models become increasingly widespread and integrated in society. Unfortunately, many defenses against adversarial attacks and jailbreaking on LLMs cannot adapt quickly to new attacks, degrade model responses to benign prompts, or introduce significant barriers to scalable implementation. To mitigate these challenges, we introduce a real-time, self-tuning (RTST) moderator framework to defend against adversarial attacks while maintaining a lightweight training footprint. We empirically evaluate its effectiveness using Google's Gemi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07139","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/2508.07139/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":"2026-07-05T11:51:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fEijE+geuoJGkzGsqdSidJhILRjDqFoVANFN8F7Con28FMAsPcoTpuwL+f1Hs+mtJcymHkkDhsJaFT3J6QsvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:44:47.334681Z"},"content_sha256":"9e7f7da09ac29fc64ac723e643947ec8375139693982b9d253c8cd5eb173fd4a","schema_version":"1.0","event_id":"sha256:9e7f7da09ac29fc64ac723e643947ec8375139693982b9d253c8cd5eb173fd4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJ7AB4636BYGSFGLWT4G7PNTDG/bundle.json","state_url":"https://pith.science/pith/NJ7AB4636BYGSFGLWT4G7PNTDG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJ7AB4636BYGSFGLWT4G7PNTDG/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":"2026-08-06T06:44:47Z","links":{"resolver":"https://pith.science/pith/NJ7AB4636BYGSFGLWT4G7PNTDG","bundle":"https://pith.science/pith/NJ7AB4636BYGSFGLWT4G7PNTDG/bundle.json","state":"https://pith.science/pith/NJ7AB4636BYGSFGLWT4G7PNTDG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJ7AB4636BYGSFGLWT4G7PNTDG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NJ7AB4636BYGSFGLWT4G7PNTDG","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":"d33e3f631fb82960230e7eac73edf3b3f09640144b70e2067b63014f42030511","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-08-10T01:59:07Z","title_canon_sha256":"3420a988721643ee11598581ee8d044fb7b17fdb62eda4397dccd24fcf656aff"},"schema_version":"1.0","source":{"id":"2508.07139","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07139","created_at":"2026-07-05T11:51:41Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07139v1","created_at":"2026-07-05T11:51:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07139","created_at":"2026-07-05T11:51:41Z"},{"alias_kind":"pith_short_12","alias_value":"NJ7AB4636BYG","created_at":"2026-07-05T11:51:41Z"},{"alias_kind":"pith_short_16","alias_value":"NJ7AB4636BYGSFGL","created_at":"2026-07-05T11:51:41Z"},{"alias_kind":"pith_short_8","alias_value":"NJ7AB463","created_at":"2026-07-05T11:51:41Z"}],"graph_snapshots":[{"event_id":"sha256:9e7f7da09ac29fc64ac723e643947ec8375139693982b9d253c8cd5eb173fd4a","target":"graph","created_at":"2026-07-05T11:51:41Z","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/2508.07139/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring LLM alignment is critical to information security as AI models become increasingly widespread and integrated in society. Unfortunately, many defenses against adversarial attacks and jailbreaking on LLMs cannot adapt quickly to new attacks, degrade model responses to benign prompts, or introduce significant barriers to scalable implementation. To mitigate these challenges, we introduce a real-time, self-tuning (RTST) moderator framework to defend against adversarial attacks while maintaining a lightweight training footprint. We empirically evaluate its effectiveness using Google's Gemi","authors_text":"Ivan Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-08-10T01:59:07Z","title":"A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07139","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":"sha256:5977eef50fea82b96500997a6bb7fac7a81158bdce329a350705ba336ea3d320","target":"record","created_at":"2026-07-05T11:51:41Z","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":"d33e3f631fb82960230e7eac73edf3b3f09640144b70e2067b63014f42030511","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-08-10T01:59:07Z","title_canon_sha256":"3420a988721643ee11598581ee8d044fb7b17fdb62eda4397dccd24fcf656aff"},"schema_version":"1.0","source":{"id":"2508.07139","kind":"arxiv","version":1}},"canonical_sha256":"6a7e00f3dbf0706914cbb4f86fbdb319a7d73ae68f96606743d4c6a60f139c6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a7e00f3dbf0706914cbb4f86fbdb319a7d73ae68f96606743d4c6a60f139c6e","first_computed_at":"2026-07-05T11:51:41.501628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:41.501628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gOdiSZMBud7GBou29tRw4yg36uIghlvK7lb/hQzq7lYCtxMQUhJ1VBHhLvqFDMecH8E6Prs1298r1xAry+PsDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:41.502089Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07139","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5977eef50fea82b96500997a6bb7fac7a81158bdce329a350705ba336ea3d320","sha256:9e7f7da09ac29fc64ac723e643947ec8375139693982b9d253c8cd5eb173fd4a"],"state_sha256":"29022ab52dce2f7ac83af9df3847bb2e023871f5d0bf0b5034dc4b0502b386c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+OPToH3EgD3cR4zu14e6jE1RS/TXzZ9VBBWTxNbTHuzF4RYt7RmPRz3ns5fBAgbCExJ1lE22NW8i6QR5G2Y+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:44:47.349236Z","bundle_sha256":"02074e8793222c3d248202fe297ff653a393a0aeff45d15cc535a2ca76435ede"}}