{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2BBQWXPK6NILUWCMEAA2MBBRYM","short_pith_number":"pith:2BBQWXPK","canonical_record":{"source":{"id":"2607.00572","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-01T07:58:16Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"499568636d7b4418244d77a5cceac3cbf73cfd01b522df4e33e729a063560810","abstract_canon_sha256":"5cae3601018f79fe93491badfa25ebd8547546b12e798ee9db60fc93b6edce5f"},"schema_version":"1.0"},"canonical_sha256":"d0430b5deaf350ba584c2001a60431c30a1cb1a13eeb1658268ca39d69519ae1","source":{"kind":"arxiv","id":"2607.00572","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00572","created_at":"2026-07-02T01:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00572v1","created_at":"2026-07-02T01:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00572","created_at":"2026-07-02T01:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"2BBQWXPK6NIL","created_at":"2026-07-02T01:17:47Z"},{"alias_kind":"pith_short_16","alias_value":"2BBQWXPK6NILUWCM","created_at":"2026-07-02T01:17:47Z"},{"alias_kind":"pith_short_8","alias_value":"2BBQWXPK","created_at":"2026-07-02T01:17:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2BBQWXPK6NILUWCMEAA2MBBRYM","target":"record","payload":{"canonical_record":{"source":{"id":"2607.00572","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-01T07:58:16Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"499568636d7b4418244d77a5cceac3cbf73cfd01b522df4e33e729a063560810","abstract_canon_sha256":"5cae3601018f79fe93491badfa25ebd8547546b12e798ee9db60fc93b6edce5f"},"schema_version":"1.0"},"canonical_sha256":"d0430b5deaf350ba584c2001a60431c30a1cb1a13eeb1658268ca39d69519ae1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:47.957413Z","signature_b64":"xTGllPkbbCckV9kvzp+XJMMCU5ZeFRsJEXTkgI+Isl68N01Y8eO1ZCVjfsLEkkTMfUQxtmc5n22J2QbLzhupCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0430b5deaf350ba584c2001a60431c30a1cb1a13eeb1658268ca39d69519ae1","last_reissued_at":"2026-07-02T01:17:47.957032Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:47.957032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.00572","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":"2026-07-02T01:17:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZelqyYwIGpNqdyJIAAW1hicUar1/MZrB4UMue2nD3gLb1gBOF3qQ8dPaNKsl+aKrv93IwtI3GhJE62M+Ii1DDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T21:25:59.207118Z"},"content_sha256":"1549b1485c2ed22a7c5812d0b1e56e56e5bda1ab4e4e33eaeaad6b76a428a920","schema_version":"1.0","event_id":"sha256:1549b1485c2ed22a7c5812d0b1e56e56e5bda1ab4e4e33eaeaad6b76a428a920"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2BBQWXPK6NILUWCMEAA2MBBRYM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.AI","authors_text":"Fangzhao Wu, Shei Pern Chua","submitted_at":"2026-07-01T07:58:16Z","abstract_excerpt":"Understanding how aligned LLMs internally represent safety is critical for diagnosing alignment vulnerabilities, as it explains why jailbreaks succeed and informs the design of robust alignment strategies. Prior work shows that aligned LLMs encode harmfulness and refusal as separable directions in the residual stream at prompt-side token positions. We show that jailbreaks succeed at prompt encoding by suppressing either the refusal or harmfulness direction before any token is generated, with distinct attack classes occupying separable regions of the harmfulness-refusal plane. Extending the ana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00572","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/2607.00572/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":"2026-07-02T01:17:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CuPfzsHA61flBVU21EGXoD6dVUkGtf6ULhptVBqOjQ1s2YKDCEYNRgTb0h4TvGduQje5YPxzkSL0RkZdIS6WBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T21:25:59.207500Z"},"content_sha256":"d8f933c30a0d739064732d93a180317fb589f8f6fdb45d7dde0399e16ba14522","schema_version":"1.0","event_id":"sha256:d8f933c30a0d739064732d93a180317fb589f8f6fdb45d7dde0399e16ba14522"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2BBQWXPK6NILUWCMEAA2MBBRYM/bundle.json","state_url":"https://pith.science/pith/2BBQWXPK6NILUWCMEAA2MBBRYM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2BBQWXPK6NILUWCMEAA2MBBRYM/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":"2026-07-02T21:25:59Z","links":{"resolver":"https://pith.science/pith/2BBQWXPK6NILUWCMEAA2MBBRYM","bundle":"https://pith.science/pith/2BBQWXPK6NILUWCMEAA2MBBRYM/bundle.json","state":"https://pith.science/pith/2BBQWXPK6NILUWCMEAA2MBBRYM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2BBQWXPK6NILUWCMEAA2MBBRYM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2BBQWXPK6NILUWCMEAA2MBBRYM","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":"5cae3601018f79fe93491badfa25ebd8547546b12e798ee9db60fc93b6edce5f","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-01T07:58:16Z","title_canon_sha256":"499568636d7b4418244d77a5cceac3cbf73cfd01b522df4e33e729a063560810"},"schema_version":"1.0","source":{"id":"2607.00572","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00572","created_at":"2026-07-02T01:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00572v1","created_at":"2026-07-02T01:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00572","created_at":"2026-07-02T01:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"2BBQWXPK6NIL","created_at":"2026-07-02T01:17:47Z"},{"alias_kind":"pith_short_16","alias_value":"2BBQWXPK6NILUWCM","created_at":"2026-07-02T01:17:47Z"},{"alias_kind":"pith_short_8","alias_value":"2BBQWXPK","created_at":"2026-07-02T01:17:47Z"}],"graph_snapshots":[{"event_id":"sha256:d8f933c30a0d739064732d93a180317fb589f8f6fdb45d7dde0399e16ba14522","target":"graph","created_at":"2026-07-02T01:17:47Z","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/2607.00572/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding how aligned LLMs internally represent safety is critical for diagnosing alignment vulnerabilities, as it explains why jailbreaks succeed and informs the design of robust alignment strategies. Prior work shows that aligned LLMs encode harmfulness and refusal as separable directions in the residual stream at prompt-side token positions. We show that jailbreaks succeed at prompt encoding by suppressing either the refusal or harmfulness direction before any token is generated, with distinct attack classes occupying separable regions of the harmfulness-refusal plane. Extending the ana","authors_text":"Fangzhao Wu, Shei Pern Chua","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-01T07:58:16Z","title":"HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00572","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":"sha256:1549b1485c2ed22a7c5812d0b1e56e56e5bda1ab4e4e33eaeaad6b76a428a920","target":"record","created_at":"2026-07-02T01:17:47Z","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":"5cae3601018f79fe93491badfa25ebd8547546b12e798ee9db60fc93b6edce5f","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-01T07:58:16Z","title_canon_sha256":"499568636d7b4418244d77a5cceac3cbf73cfd01b522df4e33e729a063560810"},"schema_version":"1.0","source":{"id":"2607.00572","kind":"arxiv","version":1}},"canonical_sha256":"d0430b5deaf350ba584c2001a60431c30a1cb1a13eeb1658268ca39d69519ae1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0430b5deaf350ba584c2001a60431c30a1cb1a13eeb1658268ca39d69519ae1","first_computed_at":"2026-07-02T01:17:47.957032Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:17:47.957032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xTGllPkbbCckV9kvzp+XJMMCU5ZeFRsJEXTkgI+Isl68N01Y8eO1ZCVjfsLEkkTMfUQxtmc5n22J2QbLzhupCw==","signature_status":"signed_v1","signed_at":"2026-07-02T01:17:47.957413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00572","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1549b1485c2ed22a7c5812d0b1e56e56e5bda1ab4e4e33eaeaad6b76a428a920","sha256:d8f933c30a0d739064732d93a180317fb589f8f6fdb45d7dde0399e16ba14522"],"state_sha256":"3624aa150dfcf0d1dcbb391d16dfcbd8760799e0c8580d2d01a30cb78f8aee7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0LEOYk3QNcNitbEXNMMCfqb0vPDOa3lkgeulspVHwT8HPjyMNmj8OVlXMqjfAVV0vkckKkIJhuYMEfWypK6hAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T21:25:59.209453Z","bundle_sha256":"39a281c34214386ff7956b0069ca1d6f5a1ab86b06f3ce7de892b0d92a01aba5"}}