{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GDJNTIANT4W5J2X7ZCFGDWNS3W","short_pith_number":"pith:GDJNTIAN","canonical_record":{"source":{"id":"2607.01239","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-01T18:57:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7a28fa75967e4e261e41815896ca68a37f7ca8e0398dd089f778f104d3172143","abstract_canon_sha256":"895c7d6b8b3e682c312a3fa5564e3d343d58a23083f016414240c4689b61f77b"},"schema_version":"1.0"},"canonical_sha256":"30d2d9a00d9f2dd4eaffc88a61d9b2dda292c1432493409a00552ee7ec59f5e4","source":{"kind":"arxiv","id":"2607.01239","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01239","created_at":"2026-07-03T00:16:55Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01239v1","created_at":"2026-07-03T00:16:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01239","created_at":"2026-07-03T00:16:55Z"},{"alias_kind":"pith_short_12","alias_value":"GDJNTIANT4W5","created_at":"2026-07-03T00:16:55Z"},{"alias_kind":"pith_short_16","alias_value":"GDJNTIANT4W5J2X7","created_at":"2026-07-03T00:16:55Z"},{"alias_kind":"pith_short_8","alias_value":"GDJNTIAN","created_at":"2026-07-03T00:16:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GDJNTIANT4W5J2X7ZCFGDWNS3W","target":"record","payload":{"canonical_record":{"source":{"id":"2607.01239","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-01T18:57:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7a28fa75967e4e261e41815896ca68a37f7ca8e0398dd089f778f104d3172143","abstract_canon_sha256":"895c7d6b8b3e682c312a3fa5564e3d343d58a23083f016414240c4689b61f77b"},"schema_version":"1.0"},"canonical_sha256":"30d2d9a00d9f2dd4eaffc88a61d9b2dda292c1432493409a00552ee7ec59f5e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T00:16:55.053799Z","signature_b64":"4cRFzSNaYMrRmzRQOIqxzVuj3BSHChwKorMnMKD+O0qX+sc3z7xAIZX/G+VsjNwpUpL85QmdfDT9UtDBm8P6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30d2d9a00d9f2dd4eaffc88a61d9b2dda292c1432493409a00552ee7ec59f5e4","last_reissued_at":"2026-07-03T00:16:55.053377Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T00:16:55.053377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.01239","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":"2026-07-03T00:16:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3k+Oj26wJHdNhqAWn1P5gS5G+Ymi6l3v+Zb5X7R5ihAeSxbCbvxIaOgwJxbsDPF+qQOcpKPMgOUNfm4Knh60Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T11:23:21.868772Z"},"content_sha256":"800bf9559d0f821813868cc893f929c1fc2a5237df38f03f032815d54d860468","schema_version":"1.0","event_id":"sha256:800bf9559d0f821813868cc893f929c1fc2a5237df38f03f032815d54d860468"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GDJNTIANT4W5J2X7ZCFGDWNS3W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongliang Liu, Tung-Ling Li, Yuhao Wu","submitted_at":"2026-05-01T18:57:03Z","abstract_excerpt":"Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable. We identify and test a central structural mechanism: BPE tokenization fragments safety-critical words into sub-word pieces, and the three public alignment datasets we surveyed contain no intentionally fragmented inputs. The mechanism is a chain, tested end-to-end on five model families (Qwen-3-4B, Qwen-2.5-7B, Gemma-3-4B, Llama-3.1-8B, Mistral-7B). An optimization targeting safety-token fragmentation flips the first-token refusal trigger on 80-100% of refused HarmBench prompts, with 48%"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01239","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/2607.01239/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":"2026-07-03T00:16:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ibPyUzxUzGKSKboreEMwg63SZmr/1I9uD5AMNSRUfosW5C6a+VhqeDdyS2P111/fo6JtUHDsA3eAjdVwS7UAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T11:23:21.869141Z"},"content_sha256":"2b3f3d7f461e5bfc2dca06dce6a9d5c9d0c86ca599c0166e1a109d98c8fa9d6b","schema_version":"1.0","event_id":"sha256:2b3f3d7f461e5bfc2dca06dce6a9d5c9d0c86ca599c0166e1a109d98c8fa9d6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDJNTIANT4W5J2X7ZCFGDWNS3W/bundle.json","state_url":"https://pith.science/pith/GDJNTIANT4W5J2X7ZCFGDWNS3W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDJNTIANT4W5J2X7ZCFGDWNS3W/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":"2026-07-04T11:23:21Z","links":{"resolver":"https://pith.science/pith/GDJNTIANT4W5J2X7ZCFGDWNS3W","bundle":"https://pith.science/pith/GDJNTIANT4W5J2X7ZCFGDWNS3W/bundle.json","state":"https://pith.science/pith/GDJNTIANT4W5J2X7ZCFGDWNS3W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDJNTIANT4W5J2X7ZCFGDWNS3W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GDJNTIANT4W5J2X7ZCFGDWNS3W","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":"895c7d6b8b3e682c312a3fa5564e3d343d58a23083f016414240c4689b61f77b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-01T18:57:03Z","title_canon_sha256":"7a28fa75967e4e261e41815896ca68a37f7ca8e0398dd089f778f104d3172143"},"schema_version":"1.0","source":{"id":"2607.01239","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01239","created_at":"2026-07-03T00:16:55Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01239v1","created_at":"2026-07-03T00:16:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01239","created_at":"2026-07-03T00:16:55Z"},{"alias_kind":"pith_short_12","alias_value":"GDJNTIANT4W5","created_at":"2026-07-03T00:16:55Z"},{"alias_kind":"pith_short_16","alias_value":"GDJNTIANT4W5J2X7","created_at":"2026-07-03T00:16:55Z"},{"alias_kind":"pith_short_8","alias_value":"GDJNTIAN","created_at":"2026-07-03T00:16:55Z"}],"graph_snapshots":[{"event_id":"sha256:2b3f3d7f461e5bfc2dca06dce6a9d5c9d0c86ca599c0166e1a109d98c8fa9d6b","target":"graph","created_at":"2026-07-03T00:16:55Z","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/2607.01239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable. We identify and test a central structural mechanism: BPE tokenization fragments safety-critical words into sub-word pieces, and the three public alignment datasets we surveyed contain no intentionally fragmented inputs. The mechanism is a chain, tested end-to-end on five model families (Qwen-3-4B, Qwen-2.5-7B, Gemma-3-4B, Llama-3.1-8B, Mistral-7B). An optimization targeting safety-token fragmentation flips the first-token refusal trigger on 80-100% of refused HarmBench prompts, with 48%","authors_text":"Hongliang Liu, Tung-Ling Li, Yuhao Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-01T18:57:03Z","title":"Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01239","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":"sha256:800bf9559d0f821813868cc893f929c1fc2a5237df38f03f032815d54d860468","target":"record","created_at":"2026-07-03T00:16:55Z","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":"895c7d6b8b3e682c312a3fa5564e3d343d58a23083f016414240c4689b61f77b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-01T18:57:03Z","title_canon_sha256":"7a28fa75967e4e261e41815896ca68a37f7ca8e0398dd089f778f104d3172143"},"schema_version":"1.0","source":{"id":"2607.01239","kind":"arxiv","version":1}},"canonical_sha256":"30d2d9a00d9f2dd4eaffc88a61d9b2dda292c1432493409a00552ee7ec59f5e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30d2d9a00d9f2dd4eaffc88a61d9b2dda292c1432493409a00552ee7ec59f5e4","first_computed_at":"2026-07-03T00:16:55.053377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T00:16:55.053377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4cRFzSNaYMrRmzRQOIqxzVuj3BSHChwKorMnMKD+O0qX+sc3z7xAIZX/G+VsjNwpUpL85QmdfDT9UtDBm8P6CA==","signature_status":"signed_v1","signed_at":"2026-07-03T00:16:55.053799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01239","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:800bf9559d0f821813868cc893f929c1fc2a5237df38f03f032815d54d860468","sha256:2b3f3d7f461e5bfc2dca06dce6a9d5c9d0c86ca599c0166e1a109d98c8fa9d6b"],"state_sha256":"d18b93ac1801aae42343a0b30e68fcb15ea42ce1adc6ad86053754b050516c20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Ia8UBDGV0i4+UDAeHkUDhTZe31Gi5AKGMbiCUAnJ6aDfU0ajVMa7QDqDsU5UTizVe7GC1UyCBC9CxiDNHnlBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T11:23:21.871046Z","bundle_sha256":"dcc22f78c7a440f1f62d627c9253b63479cc01d6bcde5c3e1f12f288486918af"}}