{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BQYWADLAXM7G7P2UMH7KRU2ZRS","short_pith_number":"pith:BQYWADLA","canonical_record":{"source":{"id":"2407.18961","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-18T00:58:41Z","cross_cats_sorted":[],"title_canon_sha256":"45c4fc040da50448d0e0cfcf52bae78f49cb672e9f5f3f361d0132472a8e776b","abstract_canon_sha256":"3af895dbdb15e38340b3a68187424bc39c19749cecc63e58095ec5d884be3076"},"schema_version":"1.0"},"canonical_sha256":"0c31600d60bb3e6fbf5461fea8d3598cb75344bb79d8519543a5b1b8fe29e77f","source":{"kind":"arxiv","id":"2407.18961","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18961","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18961v3","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18961","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"pith_short_12","alias_value":"BQYWADLAXM7G","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"pith_short_16","alias_value":"BQYWADLAXM7G7P2U","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"pith_short_8","alias_value":"BQYWADLA","created_at":"2026-07-05T08:55:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BQYWADLAXM7G7P2UMH7KRU2ZRS","target":"record","payload":{"canonical_record":{"source":{"id":"2407.18961","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-18T00:58:41Z","cross_cats_sorted":[],"title_canon_sha256":"45c4fc040da50448d0e0cfcf52bae78f49cb672e9f5f3f361d0132472a8e776b","abstract_canon_sha256":"3af895dbdb15e38340b3a68187424bc39c19749cecc63e58095ec5d884be3076"},"schema_version":"1.0"},"canonical_sha256":"0c31600d60bb3e6fbf5461fea8d3598cb75344bb79d8519543a5b1b8fe29e77f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:51.519716Z","signature_b64":"Bkz5Aw+QNMmY0jVnjEsoBVURNdEmXq8TZBnn4GSWbh4auN8gBf9cE+QYzP7+chKBGOJxhdNWHs+pa0R+Bbr2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c31600d60bb3e6fbf5461fea8d3598cb75344bb79d8519543a5b1b8fe29e77f","last_reissued_at":"2026-07-05T08:55:51.519163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:51.519163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.18961","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:55:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lB18/ZEUL/5ubTJ05x9apsFyHjhMeRZ527FkcXErBCHrwbf2JS3DBRAzsJD2+wlAl5NCXyvzXlVvGoMHbolrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:24:17.891419Z"},"content_sha256":"23ebe688b864524d5d50e7c506c05e954c0c11ce77c755fce9ec9943bf7897ac","schema_version":"1.0","event_id":"sha256:23ebe688b864524d5d50e7c506c05e954c0c11ce77c755fce9ec9943bf7897ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BQYWADLAXM7G7P2UMH7KRU2ZRS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aonan Zhang, Dian Ang Yap, Dominic Walsh, Feng Nan, Guoli Yin, Haoping Bai, Jiarui Lu, Jiulong Shan, Juergen Wiest, Karsten Ahnert, Mathias Berglund, Meng Cao, Ruoming Pang, Shen Ma, Shuang Ma, Tobias Gindele, Vik Kamath, Xiang Kong, Xiaoming Wang, Yanchao Sun, Yizhe Zhang, Zhaoyang Xu, Zhengfeng Lai, Zirui Wang","submitted_at":"2024-07-18T00:58:41Z","abstract_excerpt":"Recent advances in large language models (LLMs) have increased the demand for comprehensive benchmarks to evaluate their capabilities as human-like agents. Existing benchmarks, while useful, often focus on specific application scenarios, emphasizing task completion but failing to dissect the underlying skills that drive these outcomes. This lack of granularity makes it difficult to deeply discern where failures stem from. Additionally, setting up these environments requires considerable effort, and issues of unreliability and reproducibility sometimes arise, especially in interactive tasks. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18961","kind":"arxiv","version":3},"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/2407.18961/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":"2026-07-05T08:55:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+6AXYKi8yNM3VNO39VO6jvaJ+IXB2AVPs+xaFvqgbv0/VJQWl9rvRmzOMQMuvGabd1CUbbmcWbbf3wkk3SvPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:24:17.892125Z"},"content_sha256":"bb16c180647041fdd622dd961019dd28a9add251bd9bf4ef6e40bcc49ce79724","schema_version":"1.0","event_id":"sha256:bb16c180647041fdd622dd961019dd28a9add251bd9bf4ef6e40bcc49ce79724"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BQYWADLAXM7G7P2UMH7KRU2ZRS/bundle.json","state_url":"https://pith.science/pith/BQYWADLAXM7G7P2UMH7KRU2ZRS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BQYWADLAXM7G7P2UMH7KRU2ZRS/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":"2026-08-11T08:24:17Z","links":{"resolver":"https://pith.science/pith/BQYWADLAXM7G7P2UMH7KRU2ZRS","bundle":"https://pith.science/pith/BQYWADLAXM7G7P2UMH7KRU2ZRS/bundle.json","state":"https://pith.science/pith/BQYWADLAXM7G7P2UMH7KRU2ZRS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BQYWADLAXM7G7P2UMH7KRU2ZRS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BQYWADLAXM7G7P2UMH7KRU2ZRS","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":"3af895dbdb15e38340b3a68187424bc39c19749cecc63e58095ec5d884be3076","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-18T00:58:41Z","title_canon_sha256":"45c4fc040da50448d0e0cfcf52bae78f49cb672e9f5f3f361d0132472a8e776b"},"schema_version":"1.0","source":{"id":"2407.18961","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18961","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18961v3","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18961","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"pith_short_12","alias_value":"BQYWADLAXM7G","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"pith_short_16","alias_value":"BQYWADLAXM7G7P2U","created_at":"2026-07-05T08:55:51Z"},{"alias_kind":"pith_short_8","alias_value":"BQYWADLA","created_at":"2026-07-05T08:55:51Z"}],"graph_snapshots":[{"event_id":"sha256:bb16c180647041fdd622dd961019dd28a9add251bd9bf4ef6e40bcc49ce79724","target":"graph","created_at":"2026-07-05T08:55:51Z","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/2407.18961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have increased the demand for comprehensive benchmarks to evaluate their capabilities as human-like agents. Existing benchmarks, while useful, often focus on specific application scenarios, emphasizing task completion but failing to dissect the underlying skills that drive these outcomes. This lack of granularity makes it difficult to deeply discern where failures stem from. Additionally, setting up these environments requires considerable effort, and issues of unreliability and reproducibility sometimes arise, especially in interactive tasks. To","authors_text":"Aonan Zhang, Dian Ang Yap, Dominic Walsh, Feng Nan, Guoli Yin, Haoping Bai, Jiarui Lu, Jiulong Shan, Juergen Wiest, Karsten Ahnert, Mathias Berglund, Meng Cao, Ruoming Pang, Shen Ma, Shuang Ma, Tobias Gindele, Vik Kamath, Xiang Kong, Xiaoming Wang, Yanchao Sun, Yizhe Zhang, Zhaoyang Xu, Zhengfeng Lai, Zirui Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-18T00:58:41Z","title":"MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18961","kind":"arxiv","version":3},"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":"sha256:23ebe688b864524d5d50e7c506c05e954c0c11ce77c755fce9ec9943bf7897ac","target":"record","created_at":"2026-07-05T08:55:51Z","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":"3af895dbdb15e38340b3a68187424bc39c19749cecc63e58095ec5d884be3076","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-18T00:58:41Z","title_canon_sha256":"45c4fc040da50448d0e0cfcf52bae78f49cb672e9f5f3f361d0132472a8e776b"},"schema_version":"1.0","source":{"id":"2407.18961","kind":"arxiv","version":3}},"canonical_sha256":"0c31600d60bb3e6fbf5461fea8d3598cb75344bb79d8519543a5b1b8fe29e77f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c31600d60bb3e6fbf5461fea8d3598cb75344bb79d8519543a5b1b8fe29e77f","first_computed_at":"2026-07-05T08:55:51.519163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:51.519163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bkz5Aw+QNMmY0jVnjEsoBVURNdEmXq8TZBnn4GSWbh4auN8gBf9cE+QYzP7+chKBGOJxhdNWHs+pa0R+Bbr2Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:51.519716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.18961","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23ebe688b864524d5d50e7c506c05e954c0c11ce77c755fce9ec9943bf7897ac","sha256:bb16c180647041fdd622dd961019dd28a9add251bd9bf4ef6e40bcc49ce79724"],"state_sha256":"c519b63129de46dc0cd98033e1da6346e6559aa0f869fddad8bd5ecf24b0c77e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e1I/uPFsQil0iB6hlAJdefRMzY+07oWZXFMb7iT06uz/VXEFUZiy4fXwh92AtKizVhLvwXv59qUJ92zWenwnCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:24:17.897470Z","bundle_sha256":"eb5631fe04d7f76d3d2070122e94f3cc2341717690eb37ef105577b691ec9da6"}}