{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LRL2O57RSQZEOOXP5ZQMHQC35A","short_pith_number":"pith:LRL2O57R","canonical_record":{"source":{"id":"2607.05775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T03:05:13Z","cross_cats_sorted":[],"title_canon_sha256":"8de592424fbb0172a0546b9820695e3e9552e390a927752d991f2f634a8b768a","abstract_canon_sha256":"9b56efcf7995f65880ba1982e20713584b751b8dd28bbb95cabd4a1f7f05a495"},"schema_version":"1.0"},"canonical_sha256":"5c57a777f19432473aefee60c3c05be802c5e82eaf812595dc523000ad9ba05b","source":{"kind":"arxiv","id":"2607.05775","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05775","created_at":"2026-07-08T01:18:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05775v1","created_at":"2026-07-08T01:18:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05775","created_at":"2026-07-08T01:18:44Z"},{"alias_kind":"pith_short_12","alias_value":"LRL2O57RSQZE","created_at":"2026-07-08T01:18:44Z"},{"alias_kind":"pith_short_16","alias_value":"LRL2O57RSQZEOOXP","created_at":"2026-07-08T01:18:44Z"},{"alias_kind":"pith_short_8","alias_value":"LRL2O57R","created_at":"2026-07-08T01:18:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LRL2O57RSQZEOOXP5ZQMHQC35A","target":"record","payload":{"canonical_record":{"source":{"id":"2607.05775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T03:05:13Z","cross_cats_sorted":[],"title_canon_sha256":"8de592424fbb0172a0546b9820695e3e9552e390a927752d991f2f634a8b768a","abstract_canon_sha256":"9b56efcf7995f65880ba1982e20713584b751b8dd28bbb95cabd4a1f7f05a495"},"schema_version":"1.0"},"canonical_sha256":"5c57a777f19432473aefee60c3c05be802c5e82eaf812595dc523000ad9ba05b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:44.696943Z","signature_b64":"bbkoTm/hSU/BMvPLZgy0xrJc89Jdg63vuNwH3b1pTVvvTGTHKLkFBI4sIgIxRakwI1W2ZMnnM4Nu1SY+J/juDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c57a777f19432473aefee60c3c05be802c5e82eaf812595dc523000ad9ba05b","last_reissued_at":"2026-07-08T01:18:44.696525Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:44.696525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.05775","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":"2026-07-08T01:18:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z5Ibaq76rj3/P+6zp7fA51kOe93eBSwKjH6KpqZmFT1DMgV8UyRJ7FZhw+wQQ49b74YtL3xs8dFWmCm7Xj5yBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:20:39.196575Z"},"content_sha256":"0dac335700ce5d64cc98b4619f6f5975126b0ee9718bf6ebcb4fd7fe08e1fe88","schema_version":"1.0","event_id":"sha256:0dac335700ce5d64cc98b4619f6f5975126b0ee9718bf6ebcb4fd7fe08e1fe88"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LRL2O57RSQZEOOXP5ZQMHQC35A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ivan Flechais, Rui Zhao, Wael Albayaydh","submitted_at":"2026-07-07T03:05:13Z","abstract_excerpt":"Large language model (LLM) agents are increasingly evaluated on their ability to use tools, plan multi-step tasks, coordinate with other agents, and operate over extended horizons. Reported benchmark gains often obscure recurring failure modes documented across otherwise unrelated evaluation efforts. This paper synthesizes 27 benchmark, taxonomy, and audit papers (2023-2026), spanning 19 distinct benchmarks, into a cross-cutting taxonomy of agent limitations. To our knowledge, this is the first synthesis that integrates evidence across tool use, planning, long-horizon reasoning, multi-agent co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05775","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/2607.05775/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":"2026-07-08T01:18:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t84HUbYI3EZkY5aDCH8qbUjSNfKtg3q5u33m0nagq/oXmh3iknNSLUoXjD9K0PcVynk6hvYuNBUGhqv8pFgmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:20:39.197092Z"},"content_sha256":"7d8024ccecf6f5e3ffb2c0e799957929cba9ae2e97d363231721703c06c67c6a","schema_version":"1.0","event_id":"sha256:7d8024ccecf6f5e3ffb2c0e799957929cba9ae2e97d363231721703c06c67c6a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LRL2O57RSQZEOOXP5ZQMHQC35A/bundle.json","state_url":"https://pith.science/pith/LRL2O57RSQZEOOXP5ZQMHQC35A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LRL2O57RSQZEOOXP5ZQMHQC35A/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":"2026-08-03T20:20:39Z","links":{"resolver":"https://pith.science/pith/LRL2O57RSQZEOOXP5ZQMHQC35A","bundle":"https://pith.science/pith/LRL2O57RSQZEOOXP5ZQMHQC35A/bundle.json","state":"https://pith.science/pith/LRL2O57RSQZEOOXP5ZQMHQC35A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LRL2O57RSQZEOOXP5ZQMHQC35A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LRL2O57RSQZEOOXP5ZQMHQC35A","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":"9b56efcf7995f65880ba1982e20713584b751b8dd28bbb95cabd4a1f7f05a495","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T03:05:13Z","title_canon_sha256":"8de592424fbb0172a0546b9820695e3e9552e390a927752d991f2f634a8b768a"},"schema_version":"1.0","source":{"id":"2607.05775","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05775","created_at":"2026-07-08T01:18:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05775v1","created_at":"2026-07-08T01:18:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05775","created_at":"2026-07-08T01:18:44Z"},{"alias_kind":"pith_short_12","alias_value":"LRL2O57RSQZE","created_at":"2026-07-08T01:18:44Z"},{"alias_kind":"pith_short_16","alias_value":"LRL2O57RSQZEOOXP","created_at":"2026-07-08T01:18:44Z"},{"alias_kind":"pith_short_8","alias_value":"LRL2O57R","created_at":"2026-07-08T01:18:44Z"}],"graph_snapshots":[{"event_id":"sha256:7d8024ccecf6f5e3ffb2c0e799957929cba9ae2e97d363231721703c06c67c6a","target":"graph","created_at":"2026-07-08T01:18:44Z","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/2607.05775/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) agents are increasingly evaluated on their ability to use tools, plan multi-step tasks, coordinate with other agents, and operate over extended horizons. Reported benchmark gains often obscure recurring failure modes documented across otherwise unrelated evaluation efforts. This paper synthesizes 27 benchmark, taxonomy, and audit papers (2023-2026), spanning 19 distinct benchmarks, into a cross-cutting taxonomy of agent limitations. To our knowledge, this is the first synthesis that integrates evidence across tool use, planning, long-horizon reasoning, multi-agent co","authors_text":"Ivan Flechais, Rui Zhao, Wael Albayaydh","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T03:05:13Z","title":"Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05775","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":"sha256:0dac335700ce5d64cc98b4619f6f5975126b0ee9718bf6ebcb4fd7fe08e1fe88","target":"record","created_at":"2026-07-08T01:18:44Z","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":"9b56efcf7995f65880ba1982e20713584b751b8dd28bbb95cabd4a1f7f05a495","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-07T03:05:13Z","title_canon_sha256":"8de592424fbb0172a0546b9820695e3e9552e390a927752d991f2f634a8b768a"},"schema_version":"1.0","source":{"id":"2607.05775","kind":"arxiv","version":1}},"canonical_sha256":"5c57a777f19432473aefee60c3c05be802c5e82eaf812595dc523000ad9ba05b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c57a777f19432473aefee60c3c05be802c5e82eaf812595dc523000ad9ba05b","first_computed_at":"2026-07-08T01:18:44.696525Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:18:44.696525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bbkoTm/hSU/BMvPLZgy0xrJc89Jdg63vuNwH3b1pTVvvTGTHKLkFBI4sIgIxRakwI1W2ZMnnM4Nu1SY+J/juDA==","signature_status":"signed_v1","signed_at":"2026-07-08T01:18:44.696943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.05775","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0dac335700ce5d64cc98b4619f6f5975126b0ee9718bf6ebcb4fd7fe08e1fe88","sha256:7d8024ccecf6f5e3ffb2c0e799957929cba9ae2e97d363231721703c06c67c6a"],"state_sha256":"3a274b4973465313b73631cd969e592e091abb3d811e8978bb13b4015f801a0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lbvmMJW6jW+XEmsazdS8yVw0WtX+eeTFXB5VFskTA1FTmrbb3fDIhIDoE5e/iOXzs4kzMin/LwQovTGR+DCWBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:20:39.202458Z","bundle_sha256":"230a18242d34c6a4c9200dae5e8fb16c5ab087cd8ca8ddff1cfcf5bb0711d4aa"}}