{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TLLOITWX3CXXQLX4AWA3HMQHFS","short_pith_number":"pith:TLLOITWX","canonical_record":{"source":{"id":"2505.23848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T20:25:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6a9d9c5dd93fa8c34196ceca5b22fa5b709b7dc490e777bbe6406b6fd513cf5a","abstract_canon_sha256":"d823429fcb20d7d01f0cec7b7bd309a54ae0bd43a8b686e398bb7746627e6051"},"schema_version":"1.0"},"canonical_sha256":"9ad6e44ed7d8af782efc0581b3b2072c9b8dd564c970dc347fff19388f731de5","source":{"kind":"arxiv","id":"2505.23848","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23848","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23848v1","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23848","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_12","alias_value":"TLLOITWX3CXX","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_16","alias_value":"TLLOITWX3CXXQLX4","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_8","alias_value":"TLLOITWX","created_at":"2026-07-05T11:12:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TLLOITWX3CXXQLX4AWA3HMQHFS","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T20:25:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6a9d9c5dd93fa8c34196ceca5b22fa5b709b7dc490e777bbe6406b6fd513cf5a","abstract_canon_sha256":"d823429fcb20d7d01f0cec7b7bd309a54ae0bd43a8b686e398bb7746627e6051"},"schema_version":"1.0"},"canonical_sha256":"9ad6e44ed7d8af782efc0581b3b2072c9b8dd564c970dc347fff19388f731de5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:36.668121Z","signature_b64":"YnjjNz1tVwYLVw/BcScpPexDuByQ2X9ExZ0hTN3rCGr2doUF6NhoN6GibWiCiLwGb9/rC+wnb6cRpJxqnSewAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ad6e44ed7d8af782efc0581b3b2072c9b8dd564c970dc347fff19388f731de5","last_reissued_at":"2026-07-05T11:12:36.666771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:36.666771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23848","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":"2026-07-05T11:12:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZKNnDOcIP0sbA9j66no03DQ/fzGNiDBGYQEU3YNC/K3AAePN0vdOhIxZb+78VY2OWGx2nU4Wj/sVpqfWSFUgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:34:28.725504Z"},"content_sha256":"beba993d8e6235db0328dc8eca1c5f217c5875e713f96d07daf7c007be7717ea","schema_version":"1.0","event_id":"sha256:beba993d8e6235db0328dc8eca1c5f217c5875e713f96d07daf7c007be7717ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TLLOITWX3CXXQLX4AWA3HMQHFS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ganesh Gopalakrishnan, Harvey Dam, Jonas Knochelmann, Vinu Joseph","submitted_at":"2025-05-28T20:25:24Z","abstract_excerpt":"We introduce a method to reduce refusal rates of large language models (LLMs) on sensitive content without modifying model weights or prompts. Motivated by the observation that refusals in certain models were often preceded by the specific token sequence of a token marking the beginning of the chain-of-thought (CoT) block (<think>) followed by a double newline token (\\n\\n), we investigate the impact of two simple formatting adjustments during generation: suppressing \\n\\n after <think> and suppressing the end-of-sequence token after the end of the CoT block (</think>). Our method requires no da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23848","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/2505.23848/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":"2026-07-05T11:12:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8y8lCohMHko6hlfkJgEdWNG07DuWRE/D/uQPI9HHZEOdZKvJAc3kM5T/pruN+eqpoMv81O+L0ZqC1KQKqLt9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:34:28.726499Z"},"content_sha256":"9c2ebccbdcf3eefdad42a2b8f3b2a3158dda5654d2d7bbc99f5d5700340b2cff","schema_version":"1.0","event_id":"sha256:9c2ebccbdcf3eefdad42a2b8f3b2a3158dda5654d2d7bbc99f5d5700340b2cff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TLLOITWX3CXXQLX4AWA3HMQHFS/bundle.json","state_url":"https://pith.science/pith/TLLOITWX3CXXQLX4AWA3HMQHFS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TLLOITWX3CXXQLX4AWA3HMQHFS/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":"2026-08-08T08:34:28Z","links":{"resolver":"https://pith.science/pith/TLLOITWX3CXXQLX4AWA3HMQHFS","bundle":"https://pith.science/pith/TLLOITWX3CXXQLX4AWA3HMQHFS/bundle.json","state":"https://pith.science/pith/TLLOITWX3CXXQLX4AWA3HMQHFS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TLLOITWX3CXXQLX4AWA3HMQHFS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TLLOITWX3CXXQLX4AWA3HMQHFS","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":"d823429fcb20d7d01f0cec7b7bd309a54ae0bd43a8b686e398bb7746627e6051","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T20:25:24Z","title_canon_sha256":"6a9d9c5dd93fa8c34196ceca5b22fa5b709b7dc490e777bbe6406b6fd513cf5a"},"schema_version":"1.0","source":{"id":"2505.23848","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23848","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23848v1","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23848","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_12","alias_value":"TLLOITWX3CXX","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_16","alias_value":"TLLOITWX3CXXQLX4","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_8","alias_value":"TLLOITWX","created_at":"2026-07-05T11:12:36Z"}],"graph_snapshots":[{"event_id":"sha256:9c2ebccbdcf3eefdad42a2b8f3b2a3158dda5654d2d7bbc99f5d5700340b2cff","target":"graph","created_at":"2026-07-05T11:12:36Z","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/2505.23848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a method to reduce refusal rates of large language models (LLMs) on sensitive content without modifying model weights or prompts. Motivated by the observation that refusals in certain models were often preceded by the specific token sequence of a token marking the beginning of the chain-of-thought (CoT) block (<think>) followed by a double newline token (\\n\\n), we investigate the impact of two simple formatting adjustments during generation: suppressing \\n\\n after <think> and suppressing the end-of-sequence token after the end of the CoT block (</think>). Our method requires no da","authors_text":"Ganesh Gopalakrishnan, Harvey Dam, Jonas Knochelmann, Vinu Joseph","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T20:25:24Z","title":"Derailing Non-Answers via Logit Suppression at Output Subspace Boundaries in RLHF-Aligned Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23848","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:beba993d8e6235db0328dc8eca1c5f217c5875e713f96d07daf7c007be7717ea","target":"record","created_at":"2026-07-05T11:12:36Z","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":"d823429fcb20d7d01f0cec7b7bd309a54ae0bd43a8b686e398bb7746627e6051","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T20:25:24Z","title_canon_sha256":"6a9d9c5dd93fa8c34196ceca5b22fa5b709b7dc490e777bbe6406b6fd513cf5a"},"schema_version":"1.0","source":{"id":"2505.23848","kind":"arxiv","version":1}},"canonical_sha256":"9ad6e44ed7d8af782efc0581b3b2072c9b8dd564c970dc347fff19388f731de5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ad6e44ed7d8af782efc0581b3b2072c9b8dd564c970dc347fff19388f731de5","first_computed_at":"2026-07-05T11:12:36.666771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:36.666771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YnjjNz1tVwYLVw/BcScpPexDuByQ2X9ExZ0hTN3rCGr2doUF6NhoN6GibWiCiLwGb9/rC+wnb6cRpJxqnSewAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:36.668121Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23848","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:beba993d8e6235db0328dc8eca1c5f217c5875e713f96d07daf7c007be7717ea","sha256:9c2ebccbdcf3eefdad42a2b8f3b2a3158dda5654d2d7bbc99f5d5700340b2cff"],"state_sha256":"85c2eb1729acf6405c4ea3c069b92b99fbb0cdb6aa00602099c63e7620e3c310"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rKKdGfA5zOJ+KE9OVPDQ/wtvJZllec5tOxr2LIb+s8h4yxBB4iwaoDjSaAd7OkuPwlo8BXPr1l6Dm6Vb9Zo4Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:34:28.731563Z","bundle_sha256":"ec0b5081ef2c6747a1d1a1d690ccf30a525236b8725dd5b57a2aa674824be5f5"}}