{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EBPIF5GWHULM3XLGBHISLWTKYI","short_pith_number":"pith:EBPIF5GW","canonical_record":{"source":{"id":"2404.13752","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-21T19:24:15Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CR","math.OC"],"title_canon_sha256":"e96576335f83ba0079af00db0a1d22850b1024da1825e5a6d82441c0cf938c03","abstract_canon_sha256":"70a93e51643a3d57e1291043f6cfb219b192d043cd3c087deb35b64c3be0bdc2"},"schema_version":"1.0"},"canonical_sha256":"205e82f4d63d16cddd6609d125da6ac201512a8a1e5e25c5ee2e2ea630016793","source":{"kind":"arxiv","id":"2404.13752","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13752","created_at":"2026-07-05T09:29:28Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13752v3","created_at":"2026-07-05T09:29:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13752","created_at":"2026-07-05T09:29:28Z"},{"alias_kind":"pith_short_12","alias_value":"EBPIF5GWHULM","created_at":"2026-07-05T09:29:28Z"},{"alias_kind":"pith_short_16","alias_value":"EBPIF5GWHULM3XLG","created_at":"2026-07-05T09:29:28Z"},{"alias_kind":"pith_short_8","alias_value":"EBPIF5GW","created_at":"2026-07-05T09:29:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EBPIF5GWHULM3XLGBHISLWTKYI","target":"record","payload":{"canonical_record":{"source":{"id":"2404.13752","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-21T19:24:15Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CR","math.OC"],"title_canon_sha256":"e96576335f83ba0079af00db0a1d22850b1024da1825e5a6d82441c0cf938c03","abstract_canon_sha256":"70a93e51643a3d57e1291043f6cfb219b192d043cd3c087deb35b64c3be0bdc2"},"schema_version":"1.0"},"canonical_sha256":"205e82f4d63d16cddd6609d125da6ac201512a8a1e5e25c5ee2e2ea630016793","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:28.013657Z","signature_b64":"p6DirbMpJ2b1brapcaR23rXwv5B+RMhdMb9FA1GmEE03nAMahOPGnezsJRcfyUIAH1TP4TUKEuP4SWRxkRwICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"205e82f4d63d16cddd6609d125da6ac201512a8a1e5e25c5ee2e2ea630016793","last_reissued_at":"2026-07-05T09:29:28.013124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:28.013124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.13752","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:29:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yPPG8izdH3I+6gObPx4/+uPqTGlx/8nG+F5OXfHn0JJqQdosGg76C+LuOOQR7LMEEKN5F5FXHUmDB1xuVP8XBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:04:02.081448Z"},"content_sha256":"9b5a747a147e5bf19e3a33997872836eb3d7eab10d0b2e18eb29060b257d2a81","schema_version":"1.0","event_id":"sha256:9b5a747a147e5bf19e3a33997872836eb3d7eab10d0b2e18eb29060b257d2a81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EBPIF5GWHULM3XLGBHISLWTKYI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CR","math.OC"],"primary_cat":"cs.LG","authors_text":"Jun Sun, Meng Sun, Yihao Zhang, Zeming Wei","submitted_at":"2024-04-21T19:24:15Z","abstract_excerpt":"Since the rapid development of Large Language Models (LLMs) has achieved remarkable success, understanding and rectifying their internal complex mechanisms has become an urgent issue. Recent research has attempted to interpret their behaviors through the lens of inner representation. However, developing practical and efficient methods for applying these representations for general and flexible model editing remains challenging. In this work, we explore how to leverage insights from representation engineering to guide the editing of LLMs by deploying a representation sensor as an editing oracle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13752","kind":"arxiv","version":3},"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/2404.13752/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":"2026-07-05T09:29:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iIsSgZokRWHt296z8l1awXO7Q3dk0JJp74vGGvRRkJkHP/V7Cib1NXMxeUWvyJSIuZ7UnaHV9//VteUuSXjxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:04:02.081958Z"},"content_sha256":"a78d5505c13a992857bdb109cb127e47a0ecb97f065b68db6b778e7ed9f4635b","schema_version":"1.0","event_id":"sha256:a78d5505c13a992857bdb109cb127e47a0ecb97f065b68db6b778e7ed9f4635b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EBPIF5GWHULM3XLGBHISLWTKYI/bundle.json","state_url":"https://pith.science/pith/EBPIF5GWHULM3XLGBHISLWTKYI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EBPIF5GWHULM3XLGBHISLWTKYI/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":"2026-08-19T02:04:02Z","links":{"resolver":"https://pith.science/pith/EBPIF5GWHULM3XLGBHISLWTKYI","bundle":"https://pith.science/pith/EBPIF5GWHULM3XLGBHISLWTKYI/bundle.json","state":"https://pith.science/pith/EBPIF5GWHULM3XLGBHISLWTKYI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EBPIF5GWHULM3XLGBHISLWTKYI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EBPIF5GWHULM3XLGBHISLWTKYI","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":"70a93e51643a3d57e1291043f6cfb219b192d043cd3c087deb35b64c3be0bdc2","cross_cats_sorted":["cs.AI","cs.CL","cs.CR","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-21T19:24:15Z","title_canon_sha256":"e96576335f83ba0079af00db0a1d22850b1024da1825e5a6d82441c0cf938c03"},"schema_version":"1.0","source":{"id":"2404.13752","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13752","created_at":"2026-07-05T09:29:28Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13752v3","created_at":"2026-07-05T09:29:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13752","created_at":"2026-07-05T09:29:28Z"},{"alias_kind":"pith_short_12","alias_value":"EBPIF5GWHULM","created_at":"2026-07-05T09:29:28Z"},{"alias_kind":"pith_short_16","alias_value":"EBPIF5GWHULM3XLG","created_at":"2026-07-05T09:29:28Z"},{"alias_kind":"pith_short_8","alias_value":"EBPIF5GW","created_at":"2026-07-05T09:29:28Z"}],"graph_snapshots":[{"event_id":"sha256:a78d5505c13a992857bdb109cb127e47a0ecb97f065b68db6b778e7ed9f4635b","target":"graph","created_at":"2026-07-05T09:29:28Z","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/2404.13752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Since the rapid development of Large Language Models (LLMs) has achieved remarkable success, understanding and rectifying their internal complex mechanisms has become an urgent issue. Recent research has attempted to interpret their behaviors through the lens of inner representation. However, developing practical and efficient methods for applying these representations for general and flexible model editing remains challenging. In this work, we explore how to leverage insights from representation engineering to guide the editing of LLMs by deploying a representation sensor as an editing oracle","authors_text":"Jun Sun, Meng Sun, Yihao Zhang, Zeming Wei","cross_cats":["cs.AI","cs.CL","cs.CR","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-21T19:24:15Z","title":"Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13752","kind":"arxiv","version":3},"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":"sha256:9b5a747a147e5bf19e3a33997872836eb3d7eab10d0b2e18eb29060b257d2a81","target":"record","created_at":"2026-07-05T09:29:28Z","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":"70a93e51643a3d57e1291043f6cfb219b192d043cd3c087deb35b64c3be0bdc2","cross_cats_sorted":["cs.AI","cs.CL","cs.CR","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-21T19:24:15Z","title_canon_sha256":"e96576335f83ba0079af00db0a1d22850b1024da1825e5a6d82441c0cf938c03"},"schema_version":"1.0","source":{"id":"2404.13752","kind":"arxiv","version":3}},"canonical_sha256":"205e82f4d63d16cddd6609d125da6ac201512a8a1e5e25c5ee2e2ea630016793","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"205e82f4d63d16cddd6609d125da6ac201512a8a1e5e25c5ee2e2ea630016793","first_computed_at":"2026-07-05T09:29:28.013124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:28.013124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p6DirbMpJ2b1brapcaR23rXwv5B+RMhdMb9FA1GmEE03nAMahOPGnezsJRcfyUIAH1TP4TUKEuP4SWRxkRwICQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:28.013657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.13752","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b5a747a147e5bf19e3a33997872836eb3d7eab10d0b2e18eb29060b257d2a81","sha256:a78d5505c13a992857bdb109cb127e47a0ecb97f065b68db6b778e7ed9f4635b"],"state_sha256":"cbe52497fcc9c404bf019304e4bf7a3f9a50bfe55db00dae321b3abc8011caf4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N6XBz9id4r77vvLShBdvDzZAaM0r/7SJaOKFDUXh3x3W0yBwLooeBKR0FYU3nWdPrCvrgQP+Fos8Vi6vRsNKBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T02:04:02.087239Z","bundle_sha256":"767467bf591f4f19c89fde1c460907749655f0c4aae00bf377cf4d149c8580e7"}}