{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MKHN3JTBNS2ZZIKJEJO4WASR6V","short_pith_number":"pith:MKHN3JTB","canonical_record":{"source":{"id":"2505.08054","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T20:45:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed53dda8feec3ed56d44a51e9890bf5adb81f942e6eb3592ed2424e09b0f40d7","abstract_canon_sha256":"5a967d4502d20b1ea12aaccc86bba1d2970363b6f1e3f1cfdd736b6ac1f42147"},"schema_version":"1.0"},"canonical_sha256":"628edda6616cb59ca149225dcb0251f566d9e43dcd6646f516f3f7b6a8f9dbf9","source":{"kind":"arxiv","id":"2505.08054","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08054","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08054v2","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08054","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_12","alias_value":"MKHN3JTBNS2Z","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_16","alias_value":"MKHN3JTBNS2ZZIKJ","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_8","alias_value":"MKHN3JTB","created_at":"2026-07-05T11:37:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MKHN3JTBNS2ZZIKJEJO4WASR6V","target":"record","payload":{"canonical_record":{"source":{"id":"2505.08054","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T20:45:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed53dda8feec3ed56d44a51e9890bf5adb81f942e6eb3592ed2424e09b0f40d7","abstract_canon_sha256":"5a967d4502d20b1ea12aaccc86bba1d2970363b6f1e3f1cfdd736b6ac1f42147"},"schema_version":"1.0"},"canonical_sha256":"628edda6616cb59ca149225dcb0251f566d9e43dcd6646f516f3f7b6a8f9dbf9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:19.988948Z","signature_b64":"Wozo1VMhR1zmZXbrJ8GxeCav1ke+OEM9Xi+QbyMXaagCfbppqnfhnpxHFRE3qkFQQ0w7zA+T+JFH4qwKxd7tBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"628edda6616cb59ca149225dcb0251f566d9e43dcd6646f516f3f7b6a8f9dbf9","last_reissued_at":"2026-07-05T11:37:19.988450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:19.988450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.08054","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:37:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+vQsRgPwoPU4E97zn4dhBXKZMNk7P5Sw/uMqZFXC6CuFQfFKvux4L541HjpVye0PjMyu5kd6USN6iVpQVPl0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:28:10.617069Z"},"content_sha256":"9e10d5be12462a9c072e2e5a83c2a04dd457a7d92ad4a3469be370622daac264","schema_version":"1.0","event_id":"sha256:9e10d5be12462a9c072e2e5a83c2a04dd457a7d92ad4a3469be370622daac264"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MKHN3JTBNS2ZZIKJEJO4WASR6V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chandan K. Reddy, Fanyou Wu, Weijie Xu, Zhehao Zhang","submitted_at":"2025-05-12T20:45:25Z","abstract_excerpt":"Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a comprehensive resource containing 16k seemingly toxic queries accompanied by structured responses across 44 safety-related categories. We propose a graph-informed adversarial multi-agent interaction framework to generate diverse and complex prompts, while structuring responses with explicit reasoning to aid models in accurately distinguishing safe from unsafe contexts."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08054","kind":"arxiv","version":2},"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/2505.08054/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":"2026-07-05T11:37:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hxEs0B0ViuTcd/4Hv2KBd9SDGH1jifm9TnP/VOJp2QxAf70TnTNwOAUb20FG0wIZLurMe+o1uSsNthBsRHrQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:28:10.618077Z"},"content_sha256":"e8c899073d851f97cdc68723e5f9cabd43fe5160df36b0212439c0140213d305","schema_version":"1.0","event_id":"sha256:e8c899073d851f97cdc68723e5f9cabd43fe5160df36b0212439c0140213d305"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MKHN3JTBNS2ZZIKJEJO4WASR6V/bundle.json","state_url":"https://pith.science/pith/MKHN3JTBNS2ZZIKJEJO4WASR6V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MKHN3JTBNS2ZZIKJEJO4WASR6V/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":"2026-08-22T03:28:10Z","links":{"resolver":"https://pith.science/pith/MKHN3JTBNS2ZZIKJEJO4WASR6V","bundle":"https://pith.science/pith/MKHN3JTBNS2ZZIKJEJO4WASR6V/bundle.json","state":"https://pith.science/pith/MKHN3JTBNS2ZZIKJEJO4WASR6V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MKHN3JTBNS2ZZIKJEJO4WASR6V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MKHN3JTBNS2ZZIKJEJO4WASR6V","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":"5a967d4502d20b1ea12aaccc86bba1d2970363b6f1e3f1cfdd736b6ac1f42147","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T20:45:25Z","title_canon_sha256":"ed53dda8feec3ed56d44a51e9890bf5adb81f942e6eb3592ed2424e09b0f40d7"},"schema_version":"1.0","source":{"id":"2505.08054","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08054","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08054v2","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08054","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_12","alias_value":"MKHN3JTBNS2Z","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_16","alias_value":"MKHN3JTBNS2ZZIKJ","created_at":"2026-07-05T11:37:19Z"},{"alias_kind":"pith_short_8","alias_value":"MKHN3JTB","created_at":"2026-07-05T11:37:19Z"}],"graph_snapshots":[{"event_id":"sha256:e8c899073d851f97cdc68723e5f9cabd43fe5160df36b0212439c0140213d305","target":"graph","created_at":"2026-07-05T11:37:19Z","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/2505.08054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a comprehensive resource containing 16k seemingly toxic queries accompanied by structured responses across 44 safety-related categories. We propose a graph-informed adversarial multi-agent interaction framework to generate diverse and complex prompts, while structuring responses with explicit reasoning to aid models in accurately distinguishing safe from unsafe contexts.","authors_text":"Chandan K. Reddy, Fanyou Wu, Weijie Xu, Zhehao Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T20:45:25Z","title":"FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08054","kind":"arxiv","version":2},"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":"sha256:9e10d5be12462a9c072e2e5a83c2a04dd457a7d92ad4a3469be370622daac264","target":"record","created_at":"2026-07-05T11:37:19Z","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":"5a967d4502d20b1ea12aaccc86bba1d2970363b6f1e3f1cfdd736b6ac1f42147","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T20:45:25Z","title_canon_sha256":"ed53dda8feec3ed56d44a51e9890bf5adb81f942e6eb3592ed2424e09b0f40d7"},"schema_version":"1.0","source":{"id":"2505.08054","kind":"arxiv","version":2}},"canonical_sha256":"628edda6616cb59ca149225dcb0251f566d9e43dcd6646f516f3f7b6a8f9dbf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"628edda6616cb59ca149225dcb0251f566d9e43dcd6646f516f3f7b6a8f9dbf9","first_computed_at":"2026-07-05T11:37:19.988450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:19.988450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wozo1VMhR1zmZXbrJ8GxeCav1ke+OEM9Xi+QbyMXaagCfbppqnfhnpxHFRE3qkFQQ0w7zA+T+JFH4qwKxd7tBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:19.988948Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08054","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e10d5be12462a9c072e2e5a83c2a04dd457a7d92ad4a3469be370622daac264","sha256:e8c899073d851f97cdc68723e5f9cabd43fe5160df36b0212439c0140213d305"],"state_sha256":"d8fbb84d2193d224df92d2658e510f9af10a78389816e0f1b2d0c107824aafa6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e/1eS6a3yGMzfTbSEol2UtGQzaQW3uLE20A5yDND1VkiHaq2rx20eEVGb7eh/Tu786v0rDksFN5duRFZgpACBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T03:28:10.623773Z","bundle_sha256":"a14bf45dadd1d6dfd58c04bebf7ac547514439e7e6c38914ce4c10c6b6335c06"}}