{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BOQEBQGIKZEGSK42Q27TDBRUQJ","short_pith_number":"pith:BOQEBQGI","canonical_record":{"source":{"id":"2605.29253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T02:15:52Z","cross_cats_sorted":[],"title_canon_sha256":"b0789495c4930e2b6c85876b998171f72f65fdf402f98a6138505f0af8850296","abstract_canon_sha256":"ab64ae667f608f614c508068474a737435421c267b5714046513bc32ab56137f"},"schema_version":"1.0"},"canonical_sha256":"0ba040c0c85648692b9a86bf318634826a161f28e1ab779358fc99ee885dd162","source":{"kind":"arxiv","id":"2605.29253","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29253","created_at":"2026-05-29T01:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29253v1","created_at":"2026-05-29T01:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29253","created_at":"2026-05-29T01:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"BOQEBQGIKZEG","created_at":"2026-05-29T01:05:27Z"},{"alias_kind":"pith_short_16","alias_value":"BOQEBQGIKZEGSK42","created_at":"2026-05-29T01:05:27Z"},{"alias_kind":"pith_short_8","alias_value":"BOQEBQGI","created_at":"2026-05-29T01:05:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BOQEBQGIKZEGSK42Q27TDBRUQJ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T02:15:52Z","cross_cats_sorted":[],"title_canon_sha256":"b0789495c4930e2b6c85876b998171f72f65fdf402f98a6138505f0af8850296","abstract_canon_sha256":"ab64ae667f608f614c508068474a737435421c267b5714046513bc32ab56137f"},"schema_version":"1.0"},"canonical_sha256":"0ba040c0c85648692b9a86bf318634826a161f28e1ab779358fc99ee885dd162","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:27.349422Z","signature_b64":"60t8ZzxubdpxUSOjtF/oyfm9cqhgsdLFPvv6QfmFezS7g8w8ffU0tvl9VM5k0oHzElXqecfjOe8jCH1ZoF5vDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ba040c0c85648692b9a86bf318634826a161f28e1ab779358fc99ee885dd162","last_reissued_at":"2026-05-29T01:05:27.348639Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:27.348639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29253","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":"2026-05-29T01:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uz3w8awSBuB4t2P0VQUvmGm2fMW79qY8Hzkm0uMFizVtkUfDIdzU/7NIXydflBgGV11pBnEIG8AMFYRVFlzfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:34:23.415288Z"},"content_sha256":"ba177d2419ba6e0018fe0bd4bd62b642e5661febdb290d9220535fe4885d95a0","schema_version":"1.0","event_id":"sha256:ba177d2419ba6e0018fe0bd4bd62b642e5661febdb290d9220535fe4885d95a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BOQEBQGIKZEGSK42Q27TDBRUQJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Wang, Chong Zhang, Hao Yin, Xiaolong Yin, Yangze Liu, Yibing Liu, Zhongyi Han","submitted_at":"2026-05-28T02:15:52Z","abstract_excerpt":"Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or capability-boundary overcommitment. We study this mismatch as the Outcome-Process Gap and introduce OpenClawBench, a large-scale dataset for measuring and supervising process-side anomalies in real agent execution processes. OpenClawBench is built from BFCL-driven OpenClaw sessions produced by 6 source models and contains 31,264 annotated trajectories. It aligns task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29253","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/2605.29253/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":"2026-05-29T01:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+vljCISswnlfMh/f4ClQyQnz4tN3Fv+RenGF1sKESIYfKQgbb2w4E4zU7X5QlSewPe9exAxU8UpMZW7fMwdPDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:34:23.415708Z"},"content_sha256":"74363a6eb5c7d51dd15129e5bc604609a9317841cc7467c8df8b35ee0b855a7e","schema_version":"1.0","event_id":"sha256:74363a6eb5c7d51dd15129e5bc604609a9317841cc7467c8df8b35ee0b855a7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BOQEBQGIKZEGSK42Q27TDBRUQJ/bundle.json","state_url":"https://pith.science/pith/BOQEBQGIKZEGSK42Q27TDBRUQJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BOQEBQGIKZEGSK42Q27TDBRUQJ/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":"2026-06-03T22:34:23Z","links":{"resolver":"https://pith.science/pith/BOQEBQGIKZEGSK42Q27TDBRUQJ","bundle":"https://pith.science/pith/BOQEBQGIKZEGSK42Q27TDBRUQJ/bundle.json","state":"https://pith.science/pith/BOQEBQGIKZEGSK42Q27TDBRUQJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BOQEBQGIKZEGSK42Q27TDBRUQJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BOQEBQGIKZEGSK42Q27TDBRUQJ","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":"ab64ae667f608f614c508068474a737435421c267b5714046513bc32ab56137f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T02:15:52Z","title_canon_sha256":"b0789495c4930e2b6c85876b998171f72f65fdf402f98a6138505f0af8850296"},"schema_version":"1.0","source":{"id":"2605.29253","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29253","created_at":"2026-05-29T01:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29253v1","created_at":"2026-05-29T01:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29253","created_at":"2026-05-29T01:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"BOQEBQGIKZEG","created_at":"2026-05-29T01:05:27Z"},{"alias_kind":"pith_short_16","alias_value":"BOQEBQGIKZEGSK42","created_at":"2026-05-29T01:05:27Z"},{"alias_kind":"pith_short_8","alias_value":"BOQEBQGI","created_at":"2026-05-29T01:05:27Z"}],"graph_snapshots":[{"event_id":"sha256:74363a6eb5c7d51dd15129e5bc604609a9317841cc7467c8df8b35ee0b855a7e","target":"graph","created_at":"2026-05-29T01:05:27Z","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/2605.29253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or capability-boundary overcommitment. We study this mismatch as the Outcome-Process Gap and introduce OpenClawBench, a large-scale dataset for measuring and supervising process-side anomalies in real agent execution processes. OpenClawBench is built from BFCL-driven OpenClaw sessions produced by 6 source models and contains 31,264 annotated trajectories. It aligns task","authors_text":"Bin Wang, Chong Zhang, Hao Yin, Xiaolong Yin, Yangze Liu, Yibing Liu, Zhongyi Han","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T02:15:52Z","title":"OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29253","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:ba177d2419ba6e0018fe0bd4bd62b642e5661febdb290d9220535fe4885d95a0","target":"record","created_at":"2026-05-29T01:05:27Z","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":"ab64ae667f608f614c508068474a737435421c267b5714046513bc32ab56137f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T02:15:52Z","title_canon_sha256":"b0789495c4930e2b6c85876b998171f72f65fdf402f98a6138505f0af8850296"},"schema_version":"1.0","source":{"id":"2605.29253","kind":"arxiv","version":1}},"canonical_sha256":"0ba040c0c85648692b9a86bf318634826a161f28e1ab779358fc99ee885dd162","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ba040c0c85648692b9a86bf318634826a161f28e1ab779358fc99ee885dd162","first_computed_at":"2026-05-29T01:05:27.348639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:27.348639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"60t8ZzxubdpxUSOjtF/oyfm9cqhgsdLFPvv6QfmFezS7g8w8ffU0tvl9VM5k0oHzElXqecfjOe8jCH1ZoF5vDQ==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:27.349422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29253","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba177d2419ba6e0018fe0bd4bd62b642e5661febdb290d9220535fe4885d95a0","sha256:74363a6eb5c7d51dd15129e5bc604609a9317841cc7467c8df8b35ee0b855a7e"],"state_sha256":"8740da24979258173d218bef70990e031110eafb33db41deea91e153c62db727"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lXUPOtsp7yoDpvWXNzdaXUagy8CXhw5E4OB5MyWa2aTsfQ0wNiXCn4aAHcmbo3qopPsgjhPKUrm3jDoz5F9oCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T22:34:23.417813Z","bundle_sha256":"23be9a88a1122bc01b1edf99114de80dc1a83007f0b14062c04b053c17b37994"}}