{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UWESIHK4I25GV45TFY2YFXSCKB","short_pith_number":"pith:UWESIHK4","canonical_record":{"source":{"id":"2602.03238","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-03T08:18:37Z","cross_cats_sorted":[],"title_canon_sha256":"6b9f6601b758fd4989528a6a76f4f467bebaa4a6f4002c1ba99af3653f25512f","abstract_canon_sha256":"e60bbfee8e9d7f3e90735638d357be2d4155f0c0c46fa90e8f460e59b2ff5e54"},"schema_version":"1.0"},"canonical_sha256":"a589241d5c46ba6af3b32e3582de425075ae1c86143fd80279f29bb60dfbbfac","source":{"kind":"arxiv","id":"2602.03238","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.03238","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2602.03238v2","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03238","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"UWESIHK4I25G","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"UWESIHK4I25GV45T","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"UWESIHK4","created_at":"2026-05-27T01:05:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UWESIHK4I25GV45TFY2YFXSCKB","target":"record","payload":{"canonical_record":{"source":{"id":"2602.03238","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-03T08:18:37Z","cross_cats_sorted":[],"title_canon_sha256":"6b9f6601b758fd4989528a6a76f4f467bebaa4a6f4002c1ba99af3653f25512f","abstract_canon_sha256":"e60bbfee8e9d7f3e90735638d357be2d4155f0c0c46fa90e8f460e59b2ff5e54"},"schema_version":"1.0"},"canonical_sha256":"a589241d5c46ba6af3b32e3582de425075ae1c86143fd80279f29bb60dfbbfac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:43.835417Z","signature_b64":"fPcx8fO9Mb0y0YkiD1/N1tdH8ZWQkxZ/qcm/0GoZTYQMYsQuDEWAc095MkRud6DO6D6I4f1FP0cIYChpEdaHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a589241d5c46ba6af3b32e3582de425075ae1c86143fd80279f29bb60dfbbfac","last_reissued_at":"2026-05-27T01:05:43.834687Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:43.834687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.03238","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":"2026-05-27T01:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+6pwM9/jAxiQVZmvp7RsqkzdrSzXgmAw6aFcR05WMnBo/KTHjRgWo6B3tPrQ4wMc89IvVUkcXoQLcPnAX9rPAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:24:44.616948Z"},"content_sha256":"cd845f9d40899b51ceb5d45cfe15df88d1d6ecb52626cf821a6f21e505829c9f","schema_version":"1.0","event_id":"sha256:cd845f9d40899b51ceb5d45cfe15df88d1d6ecb52626cf821a6f21e505829c9f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UWESIHK4I25GV45TFY2YFXSCKB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Necessity of a Unified Framework for LLM-Based Agent Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Li Sun, Pengyu Zhu, Philip S. Yu, Sen Su","submitted_at":"2026-02-03T08:18:37Z","abstract_excerpt":"With the advent of Large Language Models (LLMs), general-purpose agents have seen fundamental advancements. However, evaluating these agents presents unique challenges that distinguish them from static QA benchmarks. We observe that current agent benchmarks are heavily confounded by extraneous factors, including system prompts, toolset configurations, and environmental dynamics. Existing evaluations often rely on fragmented, researcher-specific frameworks where the prompt engineering for reasoning and tool usage varies significantly, making it difficult to attribute performance gains to the mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03238","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/2602.03238/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":"2026-05-27T01:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sel7dN5GKW/j9mW8ilFiymJuDdD/gie0oa+aM9IvAqUtAVOQ+/+VDBlz7vdFLwS1fCgnkb/pCuI0cYcxuIc8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:24:44.617545Z"},"content_sha256":"cc44fd80424bb996845384182485632b58ad5d165f762f7861aaaac8287a68f1","schema_version":"1.0","event_id":"sha256:cc44fd80424bb996845384182485632b58ad5d165f762f7861aaaac8287a68f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB/bundle.json","state_url":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UWESIHK4I25GV45TFY2YFXSCKB/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":"2026-05-30T09:24:44Z","links":{"resolver":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB","bundle":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB/bundle.json","state":"https://pith.science/pith/UWESIHK4I25GV45TFY2YFXSCKB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UWESIHK4I25GV45TFY2YFXSCKB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UWESIHK4I25GV45TFY2YFXSCKB","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":"e60bbfee8e9d7f3e90735638d357be2d4155f0c0c46fa90e8f460e59b2ff5e54","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-03T08:18:37Z","title_canon_sha256":"6b9f6601b758fd4989528a6a76f4f467bebaa4a6f4002c1ba99af3653f25512f"},"schema_version":"1.0","source":{"id":"2602.03238","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.03238","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2602.03238v2","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03238","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"UWESIHK4I25G","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"UWESIHK4I25GV45T","created_at":"2026-05-27T01:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"UWESIHK4","created_at":"2026-05-27T01:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:cc44fd80424bb996845384182485632b58ad5d165f762f7861aaaac8287a68f1","target":"graph","created_at":"2026-05-27T01:05:43Z","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/2602.03238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the advent of Large Language Models (LLMs), general-purpose agents have seen fundamental advancements. However, evaluating these agents presents unique challenges that distinguish them from static QA benchmarks. We observe that current agent benchmarks are heavily confounded by extraneous factors, including system prompts, toolset configurations, and environmental dynamics. Existing evaluations often rely on fragmented, researcher-specific frameworks where the prompt engineering for reasoning and tool usage varies significantly, making it difficult to attribute performance gains to the mo","authors_text":"Li Sun, Pengyu Zhu, Philip S. Yu, Sen Su","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-03T08:18:37Z","title":"The Necessity of a Unified Framework for LLM-Based Agent Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03238","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:cd845f9d40899b51ceb5d45cfe15df88d1d6ecb52626cf821a6f21e505829c9f","target":"record","created_at":"2026-05-27T01:05:43Z","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":"e60bbfee8e9d7f3e90735638d357be2d4155f0c0c46fa90e8f460e59b2ff5e54","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-03T08:18:37Z","title_canon_sha256":"6b9f6601b758fd4989528a6a76f4f467bebaa4a6f4002c1ba99af3653f25512f"},"schema_version":"1.0","source":{"id":"2602.03238","kind":"arxiv","version":2}},"canonical_sha256":"a589241d5c46ba6af3b32e3582de425075ae1c86143fd80279f29bb60dfbbfac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a589241d5c46ba6af3b32e3582de425075ae1c86143fd80279f29bb60dfbbfac","first_computed_at":"2026-05-27T01:05:43.834687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:43.834687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fPcx8fO9Mb0y0YkiD1/N1tdH8ZWQkxZ/qcm/0GoZTYQMYsQuDEWAc095MkRud6DO6D6I4f1FP0cIYChpEdaHDg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:43.835417Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.03238","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd845f9d40899b51ceb5d45cfe15df88d1d6ecb52626cf821a6f21e505829c9f","sha256:cc44fd80424bb996845384182485632b58ad5d165f762f7861aaaac8287a68f1"],"state_sha256":"095001f5b4d7b4d37bec130011419b6248f530ceab672b1c85abcc0393fa0b8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sdr+u0kv84Qe0txy/x38lqqrvYYxm26VIX637jBx2yISLbCxnN4gxR83fHvdst6uvsbimkHPpmOJEDHMQIm8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T09:24:44.620838Z","bundle_sha256":"274595f449145861bb2f943eadb1637dcdc25d1acf85d6dba59c363d97a98c42"}}