{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ORMECPGUQMJOI3LTMG4NZLQZUV","short_pith_number":"pith:ORMECPGU","canonical_record":{"source":{"id":"2607.02577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T21:10:42Z","cross_cats_sorted":[],"title_canon_sha256":"fc272cd869a03653f3ab86451039807092292f342f71d004daec572fbd5053f5","abstract_canon_sha256":"c9e33e433f2f76c1fd18230057db875f046c6513d4ee912b67852990c2e79233"},"schema_version":"1.0"},"canonical_sha256":"7458413cd48312e46d7361b8dcae19a566d6bde54d7204cf2478cf7bd209e2f5","source":{"kind":"arxiv","id":"2607.02577","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02577","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02577v1","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02577","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"pith_short_12","alias_value":"ORMECPGUQMJO","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"pith_short_16","alias_value":"ORMECPGUQMJOI3LT","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"pith_short_8","alias_value":"ORMECPGU","created_at":"2026-07-07T00:16:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ORMECPGUQMJOI3LTMG4NZLQZUV","target":"record","payload":{"canonical_record":{"source":{"id":"2607.02577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T21:10:42Z","cross_cats_sorted":[],"title_canon_sha256":"fc272cd869a03653f3ab86451039807092292f342f71d004daec572fbd5053f5","abstract_canon_sha256":"c9e33e433f2f76c1fd18230057db875f046c6513d4ee912b67852990c2e79233"},"schema_version":"1.0"},"canonical_sha256":"7458413cd48312e46d7361b8dcae19a566d6bde54d7204cf2478cf7bd209e2f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T00:16:01.312979Z","signature_b64":"pNMPU3oi4fVwMqa52n7KzYNNWnSGoTt7BUPIURdG5hur6Ggwm1JrDSlek8qVcKbBCjiiQjFfnGq8cYnCdwncAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7458413cd48312e46d7361b8dcae19a566d6bde54d7204cf2478cf7bd209e2f5","last_reissued_at":"2026-07-07T00:16:01.312371Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T00:16:01.312371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.02577","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":"2026-07-07T00:16:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bcIZ+usPKH0SihlAc2lcRT5BV8NRX6taptHNsi3FHSOzQHmQ/8rhEQU4rKhciZ44+Lrnp2dbeCAvsEIUzVGWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:37:16.223959Z"},"content_sha256":"114f7328a99fe319047543f15ab7db7b78f5384c2005cbf86c9dc448cae067c1","schema_version":"1.0","event_id":"sha256:114f7328a99fe319047543f15ab7db7b78f5384c2005cbf86c9dc448cae067c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ORMECPGUQMJOI3LTMG4NZLQZUV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking the Benchmarks: A Validity Audit of Tool-Calling Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Asad Aali, Jay Vaghasiya, Muhammad Ahmed Mohsin, Vishvesh Bhat","submitted_at":"2026-06-30T21:10:42Z","abstract_excerpt":"Tool-calling benchmarks are increasingly used to rank language-model agents, yet their scores are often treated as ground truth without validating the evaluators themselves. We present a systematic validity and reproducibility audit of four major tool-calling benchmark families: BFCL v4, {\\tau}2-Bench, LiveMCPBench, and MCP-Atlas. Across 496 expert-reviewed benchmark tasks, we find 92 evaluator-human disagreements, corresponding to an 18.5% misalignment rate. The failures are not isolated annotation mistakes: deterministic benchmarks exhibit brittle state matching, trajectory lock-in, incorrec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02577","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/2607.02577/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":"2026-07-07T00:16:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VZ2FzHfgWS3qLVdhXTE79LaRydm3zbJadNIedgilSPKscU/g97CXTotG9MzI6z+plQVKt7yV2Lk8HKL8XXVcBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:37:16.224475Z"},"content_sha256":"6f4839566364e73480f2d853fc306a66bd24d6bc195abe09dcc258f25fd80b66","schema_version":"1.0","event_id":"sha256:6f4839566364e73480f2d853fc306a66bd24d6bc195abe09dcc258f25fd80b66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ORMECPGUQMJOI3LTMG4NZLQZUV/bundle.json","state_url":"https://pith.science/pith/ORMECPGUQMJOI3LTMG4NZLQZUV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ORMECPGUQMJOI3LTMG4NZLQZUV/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":"2026-08-19T08:37:16Z","links":{"resolver":"https://pith.science/pith/ORMECPGUQMJOI3LTMG4NZLQZUV","bundle":"https://pith.science/pith/ORMECPGUQMJOI3LTMG4NZLQZUV/bundle.json","state":"https://pith.science/pith/ORMECPGUQMJOI3LTMG4NZLQZUV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ORMECPGUQMJOI3LTMG4NZLQZUV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ORMECPGUQMJOI3LTMG4NZLQZUV","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":"c9e33e433f2f76c1fd18230057db875f046c6513d4ee912b67852990c2e79233","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T21:10:42Z","title_canon_sha256":"fc272cd869a03653f3ab86451039807092292f342f71d004daec572fbd5053f5"},"schema_version":"1.0","source":{"id":"2607.02577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02577","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02577v1","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02577","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"pith_short_12","alias_value":"ORMECPGUQMJO","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"pith_short_16","alias_value":"ORMECPGUQMJOI3LT","created_at":"2026-07-07T00:16:01Z"},{"alias_kind":"pith_short_8","alias_value":"ORMECPGU","created_at":"2026-07-07T00:16:01Z"}],"graph_snapshots":[{"event_id":"sha256:6f4839566364e73480f2d853fc306a66bd24d6bc195abe09dcc258f25fd80b66","target":"graph","created_at":"2026-07-07T00:16:01Z","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/2607.02577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tool-calling benchmarks are increasingly used to rank language-model agents, yet their scores are often treated as ground truth without validating the evaluators themselves. We present a systematic validity and reproducibility audit of four major tool-calling benchmark families: BFCL v4, {\\tau}2-Bench, LiveMCPBench, and MCP-Atlas. Across 496 expert-reviewed benchmark tasks, we find 92 evaluator-human disagreements, corresponding to an 18.5% misalignment rate. The failures are not isolated annotation mistakes: deterministic benchmarks exhibit brittle state matching, trajectory lock-in, incorrec","authors_text":"Asad Aali, Jay Vaghasiya, Muhammad Ahmed Mohsin, Vishvesh Bhat","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T21:10:42Z","title":"Benchmarking the Benchmarks: A Validity Audit of Tool-Calling Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02577","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":"sha256:114f7328a99fe319047543f15ab7db7b78f5384c2005cbf86c9dc448cae067c1","target":"record","created_at":"2026-07-07T00:16:01Z","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":"c9e33e433f2f76c1fd18230057db875f046c6513d4ee912b67852990c2e79233","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T21:10:42Z","title_canon_sha256":"fc272cd869a03653f3ab86451039807092292f342f71d004daec572fbd5053f5"},"schema_version":"1.0","source":{"id":"2607.02577","kind":"arxiv","version":1}},"canonical_sha256":"7458413cd48312e46d7361b8dcae19a566d6bde54d7204cf2478cf7bd209e2f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7458413cd48312e46d7361b8dcae19a566d6bde54d7204cf2478cf7bd209e2f5","first_computed_at":"2026-07-07T00:16:01.312371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T00:16:01.312371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pNMPU3oi4fVwMqa52n7KzYNNWnSGoTt7BUPIURdG5hur6Ggwm1JrDSlek8qVcKbBCjiiQjFfnGq8cYnCdwncAQ==","signature_status":"signed_v1","signed_at":"2026-07-07T00:16:01.312979Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:114f7328a99fe319047543f15ab7db7b78f5384c2005cbf86c9dc448cae067c1","sha256:6f4839566364e73480f2d853fc306a66bd24d6bc195abe09dcc258f25fd80b66"],"state_sha256":"e5615ca5c9837653f8144a4e1d92076075656711d1b78770de0a162556ef9aaa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cnbT16FriiZ1NSrv4R5cqmZjRGf3/yNXl2GEOnvxnXeUbSM/0cVymUewQy0orsCN/jOjo/1LB5Uxm++JnFrFCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T08:37:16.229565Z","bundle_sha256":"713231f98c0190c9b7a86a4c982432098074db8dcc408690a37fed1abb0051f1"}}