{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GQRJ4LZSNMMW27322EVZSQ7N3P","short_pith_number":"pith:GQRJ4LZS","canonical_record":{"source":{"id":"2607.14989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T13:38:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"562620fc276ca4d14b6ea3b50767829e07e3d6a9147cc1e0b93e763cdebc32db","abstract_canon_sha256":"fb4a858f4c8929322310cb791e6f5ff383208f0d098d8bd1478c7b58a4fca76d"},"schema_version":"1.0"},"canonical_sha256":"34229e2f326b196d7f7ad12b9943eddbd8e5cbc28c7de7d7f1abb0afc4b755f3","source":{"kind":"arxiv","id":"2607.14989","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14989","created_at":"2026-07-17T01:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14989v1","created_at":"2026-07-17T01:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14989","created_at":"2026-07-17T01:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"GQRJ4LZSNMMW","created_at":"2026-07-17T01:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"GQRJ4LZSNMMW2732","created_at":"2026-07-17T01:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"GQRJ4LZS","created_at":"2026-07-17T01:22:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GQRJ4LZSNMMW27322EVZSQ7N3P","target":"record","payload":{"canonical_record":{"source":{"id":"2607.14989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T13:38:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"562620fc276ca4d14b6ea3b50767829e07e3d6a9147cc1e0b93e763cdebc32db","abstract_canon_sha256":"fb4a858f4c8929322310cb791e6f5ff383208f0d098d8bd1478c7b58a4fca76d"},"schema_version":"1.0"},"canonical_sha256":"34229e2f326b196d7f7ad12b9943eddbd8e5cbc28c7de7d7f1abb0afc4b755f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:22:02.603402Z","signature_b64":"lF9GPiGtijQMawQM5oV/RDm/BUFLx0FMj0AQUsY93RfiZWTNOy985JUeRhxVyajsIDNUv/5rEOiyaYq/WuoABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34229e2f326b196d7f7ad12b9943eddbd8e5cbc28c7de7d7f1abb0afc4b755f3","last_reissued_at":"2026-07-17T01:22:02.602582Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:22:02.602582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.14989","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":"2026-07-17T01:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NUHHAHe3YzHduKYLo4epBSV8TAg04CnzqhGIDX8kzN/v6FUcU/4180jKppe3MNPbwbhnAPvNxfw04FQfE9sSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T12:46:21.433810Z"},"content_sha256":"45f1492a3ce200a7609c0f90b7610a14e8c8d78238379da1a424c7894c4aa837","schema_version":"1.0","event_id":"sha256:45f1492a3ce200a7609c0f90b7610a14e8c8d78238379da1a424c7894c4aa837"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GQRJ4LZSNMMW27322EVZSQ7N3P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengyu Shen, Chong Chen, Gangtao Xin, Guojie Zhu, Hao Jiang, Hao Liang, Hongcheng Gao, Jiawei Li, Meiyi Qiang, Runming He, Wenlong Fei, Wentao Zhang, Yanheng Hou, Yujie Fu, Zhao Cao, Zhen Hao Wong","submitted_at":"2026-07-16T13:38:07Z","abstract_excerpt":"Large language models are increasingly evolving from text generators into general agents capable of understanding user requests, invoking external tools, and completing complex tasks through interaction. However, existing agent benchmarks often focus on limited scenarios, tool ecosystems, or interaction formats, making it difficult to systematically characterize model capabilities across heterogeneous application settings. We introduce OmniaBench, a benchmark for evaluating general agents across diverse scenarios with explicit state spaces. We derive application-oriented scenario knowledge fro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14989","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/2607.14989/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":"2026-07-17T01:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zWAo2X12unVjAWRpbDtr/cPch16EDLR8AQXLlqZuJ0hAyyPPSJ4PVM2HhDH+0UTCZO1VvQ8G6dq7JdHnUIohBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T12:46:21.434099Z"},"content_sha256":"8f6d07f55eb3052a0a7e14b03ff5cf49a820fe5bd56c268a3edb1a44212a071a","schema_version":"1.0","event_id":"sha256:8f6d07f55eb3052a0a7e14b03ff5cf49a820fe5bd56c268a3edb1a44212a071a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GQRJ4LZSNMMW27322EVZSQ7N3P/bundle.json","state_url":"https://pith.science/pith/GQRJ4LZSNMMW27322EVZSQ7N3P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GQRJ4LZSNMMW27322EVZSQ7N3P/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":"2026-08-01T12:46:21Z","links":{"resolver":"https://pith.science/pith/GQRJ4LZSNMMW27322EVZSQ7N3P","bundle":"https://pith.science/pith/GQRJ4LZSNMMW27322EVZSQ7N3P/bundle.json","state":"https://pith.science/pith/GQRJ4LZSNMMW27322EVZSQ7N3P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GQRJ4LZSNMMW27322EVZSQ7N3P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GQRJ4LZSNMMW27322EVZSQ7N3P","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":"fb4a858f4c8929322310cb791e6f5ff383208f0d098d8bd1478c7b58a4fca76d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T13:38:07Z","title_canon_sha256":"562620fc276ca4d14b6ea3b50767829e07e3d6a9147cc1e0b93e763cdebc32db"},"schema_version":"1.0","source":{"id":"2607.14989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14989","created_at":"2026-07-17T01:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14989v1","created_at":"2026-07-17T01:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14989","created_at":"2026-07-17T01:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"GQRJ4LZSNMMW","created_at":"2026-07-17T01:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"GQRJ4LZSNMMW2732","created_at":"2026-07-17T01:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"GQRJ4LZS","created_at":"2026-07-17T01:22:02Z"}],"graph_snapshots":[{"event_id":"sha256:8f6d07f55eb3052a0a7e14b03ff5cf49a820fe5bd56c268a3edb1a44212a071a","target":"graph","created_at":"2026-07-17T01:22:02Z","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/2607.14989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are increasingly evolving from text generators into general agents capable of understanding user requests, invoking external tools, and completing complex tasks through interaction. However, existing agent benchmarks often focus on limited scenarios, tool ecosystems, or interaction formats, making it difficult to systematically characterize model capabilities across heterogeneous application settings. We introduce OmniaBench, a benchmark for evaluating general agents across diverse scenarios with explicit state spaces. We derive application-oriented scenario knowledge fro","authors_text":"Chengyu Shen, Chong Chen, Gangtao Xin, Guojie Zhu, Hao Jiang, Hao Liang, Hongcheng Gao, Jiawei Li, Meiyi Qiang, Runming He, Wenlong Fei, Wentao Zhang, Yanheng Hou, Yujie Fu, Zhao Cao, Zhen Hao Wong","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T13:38:07Z","title":"OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14989","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":"sha256:45f1492a3ce200a7609c0f90b7610a14e8c8d78238379da1a424c7894c4aa837","target":"record","created_at":"2026-07-17T01:22:02Z","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":"fb4a858f4c8929322310cb791e6f5ff383208f0d098d8bd1478c7b58a4fca76d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T13:38:07Z","title_canon_sha256":"562620fc276ca4d14b6ea3b50767829e07e3d6a9147cc1e0b93e763cdebc32db"},"schema_version":"1.0","source":{"id":"2607.14989","kind":"arxiv","version":1}},"canonical_sha256":"34229e2f326b196d7f7ad12b9943eddbd8e5cbc28c7de7d7f1abb0afc4b755f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34229e2f326b196d7f7ad12b9943eddbd8e5cbc28c7de7d7f1abb0afc4b755f3","first_computed_at":"2026-07-17T01:22:02.602582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:22:02.602582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lF9GPiGtijQMawQM5oV/RDm/BUFLx0FMj0AQUsY93RfiZWTNOy985JUeRhxVyajsIDNUv/5rEOiyaYq/WuoABA==","signature_status":"signed_v1","signed_at":"2026-07-17T01:22:02.603402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45f1492a3ce200a7609c0f90b7610a14e8c8d78238379da1a424c7894c4aa837","sha256:8f6d07f55eb3052a0a7e14b03ff5cf49a820fe5bd56c268a3edb1a44212a071a"],"state_sha256":"8d02796c7ea39d65cdfe5d9d04fcc7bec58dbb5ed02807843bc55c53d9e2ba37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xELc4bAg4qC1fIO4zHeK6MQz2qx3NvT3YBVbKy5op2U+l604bPfYXxZ0GsdsKoBMsoorYuUehDg7TzGxLeonAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T12:46:21.437924Z","bundle_sha256":"9506126f594a15ec3f8fe5fc84c6d50d29681bddfcca7570cf60d70907f4376b"}}