{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YLPYTJW4E7UTIOWV4SORV2VZNI","short_pith_number":"pith:YLPYTJW4","canonical_record":{"source":{"id":"2503.01865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T07:47:41Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"c0de976a2fc0b4ae56a5d9e11c79699496f6c018d39883ee6361162f6c45c12d","abstract_canon_sha256":"048157ef6568b09c4f01ce7ade1ca36e517c109057bfd7820f69c9027faa7457"},"schema_version":"1.0"},"canonical_sha256":"c2df89a6dc27e9343ad5e49d1aeab96a2874daa1b9903edc3bfce00dafacb102","source":{"kind":"arxiv","id":"2503.01865","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01865","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01865v1","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01865","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"pith_short_12","alias_value":"YLPYTJW4E7UT","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"pith_short_16","alias_value":"YLPYTJW4E7UTIOWV","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"pith_short_8","alias_value":"YLPYTJW4","created_at":"2026-07-05T10:23:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YLPYTJW4E7UTIOWV4SORV2VZNI","target":"record","payload":{"canonical_record":{"source":{"id":"2503.01865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T07:47:41Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"c0de976a2fc0b4ae56a5d9e11c79699496f6c018d39883ee6361162f6c45c12d","abstract_canon_sha256":"048157ef6568b09c4f01ce7ade1ca36e517c109057bfd7820f69c9027faa7457"},"schema_version":"1.0"},"canonical_sha256":"c2df89a6dc27e9343ad5e49d1aeab96a2874daa1b9903edc3bfce00dafacb102","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:31.470391Z","signature_b64":"NwfqcfjadgdDUa3B4w6uGw+xHX1ADOoSy54xYAwUqtc/hBpAqMPmZzjyvJRpS+NjVJvqA+Yh8Bx8XIdwR6WXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2df89a6dc27e9343ad5e49d1aeab96a2874daa1b9903edc3bfce00dafacb102","last_reissued_at":"2026-07-05T10:23:31.469736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:31.469736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.01865","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":"2026-07-05T10:23:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/snP8PWFoH5oGQLjwrVmsAEnVKf+BmqbkhM8brng9V0iBjrPBRM5/AoCkOFJ2fjLvndvHMRklz/PdlD7I2b4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:39:43.059643Z"},"content_sha256":"79c29968825d17bb2882a96716a0d6922bd090589be89b3c258109340867936a","schema_version":"1.0","event_id":"sha256:79c29968825d17bb2882a96716a0d6922bd090589be89b3c258109340867936a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YLPYTJW4E7UTIOWV4SORV2VZNI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Hongning Wang, Junxiao Yang, Minlie Huang, Shiyao Cui, Zhexin Zhang","submitted_at":"2025-02-25T07:47:41Z","abstract_excerpt":"Jailbreaking attacks can effectively induce unsafe behaviors in Large Language Models (LLMs); however, the transferability of these attacks across different models remains limited. This study aims to understand and enhance the transferability of gradient-based jailbreaking methods, which are among the standard approaches for attacking white-box models. Through a detailed analysis of the optimization process, we introduce a novel conceptual framework to elucidate transferability and identify superfluous constraints-specifically, the response pattern constraint and the token tail constraint-as s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01865","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/2503.01865/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":"2026-07-05T10:23:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/AhmJ2YPgVQPhpTtZunW3YIO3Iz+XjhcGbKyppwwq1Uz/xUOFQYRV4Z+mgis7CFVVmp2okodvg7kISV9JxFFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:39:43.060133Z"},"content_sha256":"fef81d7a43aeb555fad2e14d2945fd5f992167baccfe6cdc4fbcb3e8e2f5fa1f","schema_version":"1.0","event_id":"sha256:fef81d7a43aeb555fad2e14d2945fd5f992167baccfe6cdc4fbcb3e8e2f5fa1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YLPYTJW4E7UTIOWV4SORV2VZNI/bundle.json","state_url":"https://pith.science/pith/YLPYTJW4E7UTIOWV4SORV2VZNI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YLPYTJW4E7UTIOWV4SORV2VZNI/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":"2026-08-09T02:39:43Z","links":{"resolver":"https://pith.science/pith/YLPYTJW4E7UTIOWV4SORV2VZNI","bundle":"https://pith.science/pith/YLPYTJW4E7UTIOWV4SORV2VZNI/bundle.json","state":"https://pith.science/pith/YLPYTJW4E7UTIOWV4SORV2VZNI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YLPYTJW4E7UTIOWV4SORV2VZNI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YLPYTJW4E7UTIOWV4SORV2VZNI","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":"048157ef6568b09c4f01ce7ade1ca36e517c109057bfd7820f69c9027faa7457","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T07:47:41Z","title_canon_sha256":"c0de976a2fc0b4ae56a5d9e11c79699496f6c018d39883ee6361162f6c45c12d"},"schema_version":"1.0","source":{"id":"2503.01865","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01865","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01865v1","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01865","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"pith_short_12","alias_value":"YLPYTJW4E7UT","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"pith_short_16","alias_value":"YLPYTJW4E7UTIOWV","created_at":"2026-07-05T10:23:31Z"},{"alias_kind":"pith_short_8","alias_value":"YLPYTJW4","created_at":"2026-07-05T10:23:31Z"}],"graph_snapshots":[{"event_id":"sha256:fef81d7a43aeb555fad2e14d2945fd5f992167baccfe6cdc4fbcb3e8e2f5fa1f","target":"graph","created_at":"2026-07-05T10:23:31Z","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/2503.01865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Jailbreaking attacks can effectively induce unsafe behaviors in Large Language Models (LLMs); however, the transferability of these attacks across different models remains limited. This study aims to understand and enhance the transferability of gradient-based jailbreaking methods, which are among the standard approaches for attacking white-box models. Through a detailed analysis of the optimization process, we introduce a novel conceptual framework to elucidate transferability and identify superfluous constraints-specifically, the response pattern constraint and the token tail constraint-as s","authors_text":"Hongning Wang, Junxiao Yang, Minlie Huang, Shiyao Cui, Zhexin Zhang","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T07:47:41Z","title":"Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01865","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":"sha256:79c29968825d17bb2882a96716a0d6922bd090589be89b3c258109340867936a","target":"record","created_at":"2026-07-05T10:23:31Z","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":"048157ef6568b09c4f01ce7ade1ca36e517c109057bfd7820f69c9027faa7457","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T07:47:41Z","title_canon_sha256":"c0de976a2fc0b4ae56a5d9e11c79699496f6c018d39883ee6361162f6c45c12d"},"schema_version":"1.0","source":{"id":"2503.01865","kind":"arxiv","version":1}},"canonical_sha256":"c2df89a6dc27e9343ad5e49d1aeab96a2874daa1b9903edc3bfce00dafacb102","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2df89a6dc27e9343ad5e49d1aeab96a2874daa1b9903edc3bfce00dafacb102","first_computed_at":"2026-07-05T10:23:31.469736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:31.469736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NwfqcfjadgdDUa3B4w6uGw+xHX1ADOoSy54xYAwUqtc/hBpAqMPmZzjyvJRpS+NjVJvqA+Yh8Bx8XIdwR6WXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:31.470391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01865","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79c29968825d17bb2882a96716a0d6922bd090589be89b3c258109340867936a","sha256:fef81d7a43aeb555fad2e14d2945fd5f992167baccfe6cdc4fbcb3e8e2f5fa1f"],"state_sha256":"e4bbdf9d17354b91800fd4f8522dce349b75f60a7a8834396247255f332de4d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w0v9EQx0vsjEdmCEFu1KT050cpvQMyVCnDk5iaKc+azBEDdF+4Ncw/Hm8Gx71gnVoa4OigsrHK64ZHNHfwVcBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:39:43.063618Z","bundle_sha256":"c91349c5f3b778e931462928995d72652843cf519f32873801659da0309097e0"}}