{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XF2ZQH6QHRJOZGI3ZFXYXTPB3W","short_pith_number":"pith:XF2ZQH6Q","canonical_record":{"source":{"id":"2604.04202","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T17:55:23Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f703a61343c0d49bacaa84733f6b2eedd8ed5684a023db9a4f4893d69c9e29a6","abstract_canon_sha256":"859b410b9dd8781a6ef1023028a29ca7ace694ba5a2d242f19183c5b26751ca9"},"schema_version":"1.0"},"canonical_sha256":"b975981fd03c52ec991bc96f8bcde1dda4a36365f6c91d983d94a9974bed7e39","source":{"kind":"arxiv","id":"2604.04202","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.04202","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2604.04202v2","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.04202","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"XF2ZQH6QHRJO","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"XF2ZQH6QHRJOZGI3","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"XF2ZQH6Q","created_at":"2026-05-20T00:03:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XF2ZQH6QHRJOZGI3ZFXYXTPB3W","target":"record","payload":{"canonical_record":{"source":{"id":"2604.04202","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T17:55:23Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"f703a61343c0d49bacaa84733f6b2eedd8ed5684a023db9a4f4893d69c9e29a6","abstract_canon_sha256":"859b410b9dd8781a6ef1023028a29ca7ace694ba5a2d242f19183c5b26751ca9"},"schema_version":"1.0"},"canonical_sha256":"b975981fd03c52ec991bc96f8bcde1dda4a36365f6c91d983d94a9974bed7e39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:10.571081Z","signature_b64":"IuDWpIK4uqXQYj/12yb9DI1QpZ305Ge741pqJRsuwg4l8eKshSuIzWmWIAV7MM6KBBYGk7O/6IUPxy67jYnmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b975981fd03c52ec991bc96f8bcde1dda4a36365f6c91d983d94a9974bed7e39","last_reissued_at":"2026-05-20T00:03:10.570305Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:10.570305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.04202","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":"2026-05-20T00:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/LBMu3TQpEbIwsZ9JVzKiK/mqv9c6M1EqfAFxr7vPS2mhs7mxFnv0RAiit0KVWdF+zjAFUKsufgdMDgR1IMQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T20:23:07.148448Z"},"content_sha256":"80a8a8b2af807c5ab2dec6d9fb55fa41998b398748d82cba364ff3cfe1289bac","schema_version":"1.0","event_id":"sha256:80a8a8b2af807c5ab2dec6d9fb55fa41998b398748d82cba364ff3cfe1289bac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XF2ZQH6QHRJOZGI3ZFXYXTPB3W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ClawArena: Benchmarking AI Agents in Evolving Information Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bingzhou Li, Cihang Xie, Haonian Ji, Huaxiu Yao, Jiaqi Liu, Jinlong Li, Kaiwen Xiong, Peng Xia, Shi Qiu, Siwei Han, Yiyang Zhou, Zeyu Zheng","submitted_at":"2026-04-05T17:55:23Z","abstract_excerpt":"AI agents deployed as persistent assistants must maintain correct beliefs as their information environment evolves. In practice, evidence is scattered across heterogeneous sources that often contradict one another, new information can invalidate earlier conclusions, and user preferences surface through corrections rather than explicit instructions. Existing benchmarks largely assume static, single-authority settings and do not evaluate whether agents can keep up with this complexity. We introduce ClawArena, a benchmark for evaluating AI agents in evolving information environments. Each scenari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.04202","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/2604.04202/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":"2026-05-20T00:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JOIXK4mStPQXhYaUBX026TegLC32RqQd6UW4/IwsqL/SNoGl/ygtO+El+W2mrci9J/B8W5R45M+uT+w3wXoJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T20:23:07.149189Z"},"content_sha256":"01eb1f9e6f4f91aa11f81d9d712342d630b2b328efdd107537a21e7ff47683d6","schema_version":"1.0","event_id":"sha256:01eb1f9e6f4f91aa11f81d9d712342d630b2b328efdd107537a21e7ff47683d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XF2ZQH6QHRJOZGI3ZFXYXTPB3W/bundle.json","state_url":"https://pith.science/pith/XF2ZQH6QHRJOZGI3ZFXYXTPB3W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XF2ZQH6QHRJOZGI3ZFXYXTPB3W/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":"2026-05-23T20:23:07Z","links":{"resolver":"https://pith.science/pith/XF2ZQH6QHRJOZGI3ZFXYXTPB3W","bundle":"https://pith.science/pith/XF2ZQH6QHRJOZGI3ZFXYXTPB3W/bundle.json","state":"https://pith.science/pith/XF2ZQH6QHRJOZGI3ZFXYXTPB3W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XF2ZQH6QHRJOZGI3ZFXYXTPB3W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XF2ZQH6QHRJOZGI3ZFXYXTPB3W","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":"859b410b9dd8781a6ef1023028a29ca7ace694ba5a2d242f19183c5b26751ca9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T17:55:23Z","title_canon_sha256":"f703a61343c0d49bacaa84733f6b2eedd8ed5684a023db9a4f4893d69c9e29a6"},"schema_version":"1.0","source":{"id":"2604.04202","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.04202","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2604.04202v2","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.04202","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"XF2ZQH6QHRJO","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"XF2ZQH6QHRJOZGI3","created_at":"2026-05-20T00:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"XF2ZQH6Q","created_at":"2026-05-20T00:03:10Z"}],"graph_snapshots":[{"event_id":"sha256:01eb1f9e6f4f91aa11f81d9d712342d630b2b328efdd107537a21e7ff47683d6","target":"graph","created_at":"2026-05-20T00:03:10Z","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/2604.04202/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"AI agents deployed as persistent assistants must maintain correct beliefs as their information environment evolves. In practice, evidence is scattered across heterogeneous sources that often contradict one another, new information can invalidate earlier conclusions, and user preferences surface through corrections rather than explicit instructions. Existing benchmarks largely assume static, single-authority settings and do not evaluate whether agents can keep up with this complexity. We introduce ClawArena, a benchmark for evaluating AI agents in evolving information environments. Each scenari","authors_text":"Bingzhou Li, Cihang Xie, Haonian Ji, Huaxiu Yao, Jiaqi Liu, Jinlong Li, Kaiwen Xiong, Peng Xia, Shi Qiu, Siwei Han, Yiyang Zhou, Zeyu Zheng","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T17:55:23Z","title":"ClawArena: Benchmarking AI Agents in Evolving Information Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.04202","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":"sha256:80a8a8b2af807c5ab2dec6d9fb55fa41998b398748d82cba364ff3cfe1289bac","target":"record","created_at":"2026-05-20T00:03:10Z","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":"859b410b9dd8781a6ef1023028a29ca7ace694ba5a2d242f19183c5b26751ca9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-05T17:55:23Z","title_canon_sha256":"f703a61343c0d49bacaa84733f6b2eedd8ed5684a023db9a4f4893d69c9e29a6"},"schema_version":"1.0","source":{"id":"2604.04202","kind":"arxiv","version":2}},"canonical_sha256":"b975981fd03c52ec991bc96f8bcde1dda4a36365f6c91d983d94a9974bed7e39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b975981fd03c52ec991bc96f8bcde1dda4a36365f6c91d983d94a9974bed7e39","first_computed_at":"2026-05-20T00:03:10.570305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:10.570305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IuDWpIK4uqXQYj/12yb9DI1QpZ305Ge741pqJRsuwg4l8eKshSuIzWmWIAV7MM6KBBYGk7O/6IUPxy67jYnmAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:10.571081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.04202","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80a8a8b2af807c5ab2dec6d9fb55fa41998b398748d82cba364ff3cfe1289bac","sha256:01eb1f9e6f4f91aa11f81d9d712342d630b2b328efdd107537a21e7ff47683d6"],"state_sha256":"b8c6db1b8afc6d29e0207987c077271216f031782d73c0afedcd963dae11dc4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NL4++j0JXk/fRJQz4ITtqR7nROn368m2qqStlNmjF6kcS6j8VS5QKz6thBHtZc6OKst446llHG41lEWbDzPFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T20:23:07.153068Z","bundle_sha256":"68ef3235a2bcbdea768f72acac2dc18d5477638784b8c02634a53bb6ef3c239e"}}