{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TDKRLCS3GBXHC47TJAZV7XFZBH","short_pith_number":"pith:TDKRLCS3","canonical_record":{"source":{"id":"2508.00324","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-01T05:14:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"57b30f2181da1c11469e861ca1b629ea5b766341fbfc694b8e9209ad218796a6","abstract_canon_sha256":"02c2be4d429af946ee4461acc801ad9fd4c6a918c5af7881aa548bb41ec0bc85"},"schema_version":"1.0"},"canonical_sha256":"98d5158a5b306e7173f348335fdcb909cab5d4807873308e42f755d1212c5510","source":{"kind":"arxiv","id":"2508.00324","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00324","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00324v1","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00324","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"pith_short_12","alias_value":"TDKRLCS3GBXH","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"pith_short_16","alias_value":"TDKRLCS3GBXHC47T","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"pith_short_8","alias_value":"TDKRLCS3","created_at":"2026-07-05T11:46:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TDKRLCS3GBXHC47TJAZV7XFZBH","target":"record","payload":{"canonical_record":{"source":{"id":"2508.00324","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-01T05:14:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"57b30f2181da1c11469e861ca1b629ea5b766341fbfc694b8e9209ad218796a6","abstract_canon_sha256":"02c2be4d429af946ee4461acc801ad9fd4c6a918c5af7881aa548bb41ec0bc85"},"schema_version":"1.0"},"canonical_sha256":"98d5158a5b306e7173f348335fdcb909cab5d4807873308e42f755d1212c5510","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:53.440909Z","signature_b64":"zv7m4Exi/TfvqPxpdVmmaO2gwOAQQ7j9kMSGFflTXwVDMPFUz3Pa4oaUJw3AJ2Nxn6U+cN5VSRtPkB64JAe/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98d5158a5b306e7173f348335fdcb909cab5d4807873308e42f755d1212c5510","last_reissued_at":"2026-07-05T11:46:53.440399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:53.440399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.00324","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":"2026-07-05T11:46:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YUzc0zQQEuUwRqQjpLvvya4Otecxdlku+g5We6FtrrTlw68U5tyMXZP4nwVTTDTtzHOd1Oz/LKP/SeFT/VXPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T04:02:38.032197Z"},"content_sha256":"1aa5aca07aa382e8fe58fc3a5c93036c53f18f2621551c0d06deb6649db64645","schema_version":"1.0","event_id":"sha256:1aa5aca07aa382e8fe58fc3a5c93036c53f18f2621551c0d06deb6649db64645"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TDKRLCS3GBXHC47TJAZV7XFZBH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chanyoung Park, Sangwu Park, Wonjoong Kim, Yeonjun In","submitted_at":"2025-08-01T05:14:13Z","abstract_excerpt":"Although large reasoning models (LRMs) have demonstrated impressive capabilities on complex tasks, recent studies reveal that these models frequently fulfill harmful user instructions, raising significant safety concerns. In this paper, we investigate the underlying cause of LRM safety risks and find that models already possess sufficient safety knowledge but fail to activate it during reasoning. Based on this insight, we propose R1-Act, a simple and efficient post-training method that explicitly triggers safety knowledge through a structured reasoning process. R1-Act achieves strong safety im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00324","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/2508.00324/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":"2026-07-05T11:46:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TnM2/h554nkv51J6VDkCMt6EgkV0ShmM5RcEUIurtTgLLXMk7CMNuxxSYLL0A9YCgqNVcHacRWrCuItIms1gCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T04:02:38.032713Z"},"content_sha256":"f59f665de06d621f838d5e61b33916502ed9c2abbc2e8454b5df4258006f122f","schema_version":"1.0","event_id":"sha256:f59f665de06d621f838d5e61b33916502ed9c2abbc2e8454b5df4258006f122f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TDKRLCS3GBXHC47TJAZV7XFZBH/bundle.json","state_url":"https://pith.science/pith/TDKRLCS3GBXHC47TJAZV7XFZBH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TDKRLCS3GBXHC47TJAZV7XFZBH/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":"2026-08-12T04:02:38Z","links":{"resolver":"https://pith.science/pith/TDKRLCS3GBXHC47TJAZV7XFZBH","bundle":"https://pith.science/pith/TDKRLCS3GBXHC47TJAZV7XFZBH/bundle.json","state":"https://pith.science/pith/TDKRLCS3GBXHC47TJAZV7XFZBH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TDKRLCS3GBXHC47TJAZV7XFZBH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TDKRLCS3GBXHC47TJAZV7XFZBH","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":"02c2be4d429af946ee4461acc801ad9fd4c6a918c5af7881aa548bb41ec0bc85","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-01T05:14:13Z","title_canon_sha256":"57b30f2181da1c11469e861ca1b629ea5b766341fbfc694b8e9209ad218796a6"},"schema_version":"1.0","source":{"id":"2508.00324","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00324","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00324v1","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00324","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"pith_short_12","alias_value":"TDKRLCS3GBXH","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"pith_short_16","alias_value":"TDKRLCS3GBXHC47T","created_at":"2026-07-05T11:46:53Z"},{"alias_kind":"pith_short_8","alias_value":"TDKRLCS3","created_at":"2026-07-05T11:46:53Z"}],"graph_snapshots":[{"event_id":"sha256:f59f665de06d621f838d5e61b33916502ed9c2abbc2e8454b5df4258006f122f","target":"graph","created_at":"2026-07-05T11:46:53Z","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/2508.00324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although large reasoning models (LRMs) have demonstrated impressive capabilities on complex tasks, recent studies reveal that these models frequently fulfill harmful user instructions, raising significant safety concerns. In this paper, we investigate the underlying cause of LRM safety risks and find that models already possess sufficient safety knowledge but fail to activate it during reasoning. Based on this insight, we propose R1-Act, a simple and efficient post-training method that explicitly triggers safety knowledge through a structured reasoning process. R1-Act achieves strong safety im","authors_text":"Chanyoung Park, Sangwu Park, Wonjoong Kim, Yeonjun In","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-01T05:14:13Z","title":"R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00324","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":"sha256:1aa5aca07aa382e8fe58fc3a5c93036c53f18f2621551c0d06deb6649db64645","target":"record","created_at":"2026-07-05T11:46:53Z","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":"02c2be4d429af946ee4461acc801ad9fd4c6a918c5af7881aa548bb41ec0bc85","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-01T05:14:13Z","title_canon_sha256":"57b30f2181da1c11469e861ca1b629ea5b766341fbfc694b8e9209ad218796a6"},"schema_version":"1.0","source":{"id":"2508.00324","kind":"arxiv","version":1}},"canonical_sha256":"98d5158a5b306e7173f348335fdcb909cab5d4807873308e42f755d1212c5510","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98d5158a5b306e7173f348335fdcb909cab5d4807873308e42f755d1212c5510","first_computed_at":"2026-07-05T11:46:53.440399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:53.440399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zv7m4Exi/TfvqPxpdVmmaO2gwOAQQ7j9kMSGFflTXwVDMPFUz3Pa4oaUJw3AJ2Nxn6U+cN5VSRtPkB64JAe/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:53.440909Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.00324","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1aa5aca07aa382e8fe58fc3a5c93036c53f18f2621551c0d06deb6649db64645","sha256:f59f665de06d621f838d5e61b33916502ed9c2abbc2e8454b5df4258006f122f"],"state_sha256":"5cfd442ab41832462491fbd74e868005a7666851d62d8af6f0adc6414669486c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lWHYzzTNjfkhGuJkmDf/S9y/OI1qPdddsD8tJRx0ahbAEHvpItpd0oFWJJgj2xb+DiHiu8Xn9wFR65tVKV25Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T04:02:38.036703Z","bundle_sha256":"2db1ded06948ea83d50c5877ce27e27db8b99f01a4fdf876c17d20a3effae59a"}}