{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4U5ZKBBE235HGM5AUQV3A2NM3B","short_pith_number":"pith:4U5ZKBBE","canonical_record":{"source":{"id":"2503.04957","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-06T20:43:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"936858ab191e8e88b8653e757813a3e8e23af10ac645a628c8a3395a242d0894","abstract_canon_sha256":"503dd286dde0b38709d991ebef4e7718d907eed294f54918d76aa14153d8de4c"},"schema_version":"1.0"},"canonical_sha256":"e53b950424d6fa7333a0a42bb069acd8712760cb3bb8429a2e424e37fb284ac9","source":{"kind":"arxiv","id":"2503.04957","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04957","created_at":"2026-07-05T10:26:17Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04957v1","created_at":"2026-07-05T10:26:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04957","created_at":"2026-07-05T10:26:17Z"},{"alias_kind":"pith_short_12","alias_value":"4U5ZKBBE235H","created_at":"2026-07-05T10:26:17Z"},{"alias_kind":"pith_short_16","alias_value":"4U5ZKBBE235HGM5A","created_at":"2026-07-05T10:26:17Z"},{"alias_kind":"pith_short_8","alias_value":"4U5ZKBBE","created_at":"2026-07-05T10:26:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4U5ZKBBE235HGM5AUQV3A2NM3B","target":"record","payload":{"canonical_record":{"source":{"id":"2503.04957","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-06T20:43:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"936858ab191e8e88b8653e757813a3e8e23af10ac645a628c8a3395a242d0894","abstract_canon_sha256":"503dd286dde0b38709d991ebef4e7718d907eed294f54918d76aa14153d8de4c"},"schema_version":"1.0"},"canonical_sha256":"e53b950424d6fa7333a0a42bb069acd8712760cb3bb8429a2e424e37fb284ac9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:17.320746Z","signature_b64":"Rvnob3ZvUlZdtlkH7Llj/5VJofRUX3GgRTMorf+Y2W5Z62yVQYrtUxk69bxg+xzRKnR0aRVRkhQOQe0gE+v4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e53b950424d6fa7333a0a42bb069acd8712760cb3bb8429a2e424e37fb284ac9","last_reissued_at":"2026-07-05T10:26:17.320259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:17.320259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.04957","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":"2026-07-05T10:26:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2qsjh9TZecMtgAsQFpVq140TZJEuBHRwDyUYZK2FOzIjf5144yVCBvgAAuQz2QHeQab1mTgjMsPvrINPh5D3Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:57:59.151959Z"},"content_sha256":"6ce48a9a7932e767fb14d73f8672fa62d659540aec21324177d1a46fbbb83296","schema_version":"1.0","event_id":"sha256:6ce48a9a7932e767fb14d73f8672fa62d659540aec21324177d1a46fbbb83296"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4U5ZKBBE235HGM5AUQV3A2NM3B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SafeArena: Evaluating the Safety of Autonomous Web Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Ada Defne Tur, Alejandra Zambrano, Arkil Patel, Esin Durmus, Karolina Sta\\'nczak, Nicholas Meade, Siva Reddy, Spandana Gella, Xing Han L\\`u","submitted_at":"2025-03-06T20:43:14Z","abstract_excerpt":"LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinformation in an online forum or selling illicit substances on a website. To evaluate these risks, we propose SafeArena, the first benchmark to focus on the deliberate misuse of web agents. SafeArena comprises 250 safe and 250 harmful tasks across four websites. We classify the harmful tasks into five harm categories -- misinformation, illegal activity, harassment, cybercrime, and social bias, designed to assess realis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04957","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/2503.04957/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":"2026-07-05T10:26:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DF1xkbYIMTML/uA+WLuiH9Z43NRfmt4sgWW9AS28CpOA29HRq2kp2hXXRpdB1dLFiQg5l1RIqz9TaShsX/jkAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:57:59.153772Z"},"content_sha256":"d382566f76c11ad8d910a1ba3696631a04c45f59b0238cca692b7f6bff9d6e36","schema_version":"1.0","event_id":"sha256:d382566f76c11ad8d910a1ba3696631a04c45f59b0238cca692b7f6bff9d6e36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4U5ZKBBE235HGM5AUQV3A2NM3B/bundle.json","state_url":"https://pith.science/pith/4U5ZKBBE235HGM5AUQV3A2NM3B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4U5ZKBBE235HGM5AUQV3A2NM3B/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":"2026-08-14T15:57:59Z","links":{"resolver":"https://pith.science/pith/4U5ZKBBE235HGM5AUQV3A2NM3B","bundle":"https://pith.science/pith/4U5ZKBBE235HGM5AUQV3A2NM3B/bundle.json","state":"https://pith.science/pith/4U5ZKBBE235HGM5AUQV3A2NM3B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4U5ZKBBE235HGM5AUQV3A2NM3B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4U5ZKBBE235HGM5AUQV3A2NM3B","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":"503dd286dde0b38709d991ebef4e7718d907eed294f54918d76aa14153d8de4c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-06T20:43:14Z","title_canon_sha256":"936858ab191e8e88b8653e757813a3e8e23af10ac645a628c8a3395a242d0894"},"schema_version":"1.0","source":{"id":"2503.04957","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04957","created_at":"2026-07-05T10:26:17Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04957v1","created_at":"2026-07-05T10:26:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04957","created_at":"2026-07-05T10:26:17Z"},{"alias_kind":"pith_short_12","alias_value":"4U5ZKBBE235H","created_at":"2026-07-05T10:26:17Z"},{"alias_kind":"pith_short_16","alias_value":"4U5ZKBBE235HGM5A","created_at":"2026-07-05T10:26:17Z"},{"alias_kind":"pith_short_8","alias_value":"4U5ZKBBE","created_at":"2026-07-05T10:26:17Z"}],"graph_snapshots":[{"event_id":"sha256:d382566f76c11ad8d910a1ba3696631a04c45f59b0238cca692b7f6bff9d6e36","target":"graph","created_at":"2026-07-05T10:26:17Z","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/2503.04957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinformation in an online forum or selling illicit substances on a website. To evaluate these risks, we propose SafeArena, the first benchmark to focus on the deliberate misuse of web agents. SafeArena comprises 250 safe and 250 harmful tasks across four websites. We classify the harmful tasks into five harm categories -- misinformation, illegal activity, harassment, cybercrime, and social bias, designed to assess realis","authors_text":"Ada Defne Tur, Alejandra Zambrano, Arkil Patel, Esin Durmus, Karolina Sta\\'nczak, Nicholas Meade, Siva Reddy, Spandana Gella, Xing Han L\\`u","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-06T20:43:14Z","title":"SafeArena: Evaluating the Safety of Autonomous Web Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04957","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":"sha256:6ce48a9a7932e767fb14d73f8672fa62d659540aec21324177d1a46fbbb83296","target":"record","created_at":"2026-07-05T10:26:17Z","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":"503dd286dde0b38709d991ebef4e7718d907eed294f54918d76aa14153d8de4c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-06T20:43:14Z","title_canon_sha256":"936858ab191e8e88b8653e757813a3e8e23af10ac645a628c8a3395a242d0894"},"schema_version":"1.0","source":{"id":"2503.04957","kind":"arxiv","version":1}},"canonical_sha256":"e53b950424d6fa7333a0a42bb069acd8712760cb3bb8429a2e424e37fb284ac9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e53b950424d6fa7333a0a42bb069acd8712760cb3bb8429a2e424e37fb284ac9","first_computed_at":"2026-07-05T10:26:17.320259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:17.320259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rvnob3ZvUlZdtlkH7Llj/5VJofRUX3GgRTMorf+Y2W5Z62yVQYrtUxk69bxg+xzRKnR0aRVRkhQOQe0gE+v4Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:17.320746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04957","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ce48a9a7932e767fb14d73f8672fa62d659540aec21324177d1a46fbbb83296","sha256:d382566f76c11ad8d910a1ba3696631a04c45f59b0238cca692b7f6bff9d6e36"],"state_sha256":"88218ceae2466fac1b82fc8075b842b44f7975923704a2f9457dfe8e16eab9ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"biFWgtfsjvk90po7YGnzK5v/aNlwCoIqPuieWsBNvinDHUxNRxzfFJ5NS3la0CIdXoDL9ohAB1m9sdlWr67LAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T15:57:59.163223Z","bundle_sha256":"e5734f866e00a733f2782d62e0e37b02c688dbcbfc6ffe078a58d36d580d4c9c"}}