{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OVKLI6OA6K2QBKY74CJEOLXOL5","short_pith_number":"pith:OVKLI6OA","canonical_record":{"source":{"id":"2606.11166","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.OT","submitted_at":"2026-06-09T17:46:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d9c494b2af3f4ae3f3f1dac1f54fd9bab078fcad07dd424c88c0513ca9e58f59","abstract_canon_sha256":"c7013c1fc2fe6075708d178c9010e34fafc9e892b782ba38254f94ad4f9e21db"},"schema_version":"1.0"},"canonical_sha256":"7554b479c0f2b500ab1fe092472eee5f504c6fbb7e6c6ef402dcacb159b8580d","source":{"kind":"arxiv","id":"2606.11166","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11166","created_at":"2026-06-10T01:11:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11166v1","created_at":"2026-06-10T01:11:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11166","created_at":"2026-06-10T01:11:14Z"},{"alias_kind":"pith_short_12","alias_value":"OVKLI6OA6K2Q","created_at":"2026-06-10T01:11:14Z"},{"alias_kind":"pith_short_16","alias_value":"OVKLI6OA6K2QBKY7","created_at":"2026-06-10T01:11:14Z"},{"alias_kind":"pith_short_8","alias_value":"OVKLI6OA","created_at":"2026-06-10T01:11:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OVKLI6OA6K2QBKY74CJEOLXOL5","target":"record","payload":{"canonical_record":{"source":{"id":"2606.11166","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.OT","submitted_at":"2026-06-09T17:46:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d9c494b2af3f4ae3f3f1dac1f54fd9bab078fcad07dd424c88c0513ca9e58f59","abstract_canon_sha256":"c7013c1fc2fe6075708d178c9010e34fafc9e892b782ba38254f94ad4f9e21db"},"schema_version":"1.0"},"canonical_sha256":"7554b479c0f2b500ab1fe092472eee5f504c6fbb7e6c6ef402dcacb159b8580d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:11:14.879109Z","signature_b64":"zhk9MzPpILtAfxq8XGgwKn4YHVN/ZE6tnnx97vsslYKmz5Wpl5GC8P/9qMrS5yqeZXxo/d8DTbRMZGEZO0GEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7554b479c0f2b500ab1fe092472eee5f504c6fbb7e6c6ef402dcacb159b8580d","last_reissued_at":"2026-06-10T01:11:14.878376Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:11:14.878376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.11166","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":"2026-06-10T01:11:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fMlOR9/cn98lnGSu2FP1ou0H+4jhY7ZE8mVsKRJ2oLC41NAhM/Im8/++RiACHv2nfyjMKtaxfTFqvWq1hQkIDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T17:15:26.363269Z"},"content_sha256":"123cedb5f81d94318c1b9c70386b6a4a1f2509b2778554297393b6f8325c507f","schema_version":"1.0","event_id":"sha256:123cedb5f81d94318c1b9c70386b6a4a1f2509b2778554297393b6f8325c507f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OVKLI6OA6K2QBKY74CJEOLXOL5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flaws in the LLM Automation Narrative","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"stat.OT","authors_text":"George Perrett, Javae Elliott, Jennifer Hill, Marc Scott","submitted_at":"2026-06-09T17:46:10Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly described as performing at the level of human experts on knowledge economy tasks. These claims are primarily based on how LLMs perform on benchmarking tasks that measure average performance across standardized datasets. Primary limitations of many benchmarking tasks are that they often measure performance based on content directly included in LLM training data, and they frequently do not assess the reliability of LLM performance or the magnitude of LLM errors. However, in high stakes contexts, these qualities are critically important. Through a nov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11166","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/2606.11166/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":"2026-06-10T01:11:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ih5Bp9sKYFGONBac4POvUlp/ipty4E/DexuEJlNAnJ+E+QDHHGahkz0bLZudhQVnWkBLS9M3b/W32WInuGZBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T17:15:26.363661Z"},"content_sha256":"50fbb6237e84780db06d64f60bc2481042d1e1cfcaca4b2c6e201e92f644699b","schema_version":"1.0","event_id":"sha256:50fbb6237e84780db06d64f60bc2481042d1e1cfcaca4b2c6e201e92f644699b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OVKLI6OA6K2QBKY74CJEOLXOL5/bundle.json","state_url":"https://pith.science/pith/OVKLI6OA6K2QBKY74CJEOLXOL5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OVKLI6OA6K2QBKY74CJEOLXOL5/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":"2026-07-03T17:15:26Z","links":{"resolver":"https://pith.science/pith/OVKLI6OA6K2QBKY74CJEOLXOL5","bundle":"https://pith.science/pith/OVKLI6OA6K2QBKY74CJEOLXOL5/bundle.json","state":"https://pith.science/pith/OVKLI6OA6K2QBKY74CJEOLXOL5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OVKLI6OA6K2QBKY74CJEOLXOL5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OVKLI6OA6K2QBKY74CJEOLXOL5","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":"c7013c1fc2fe6075708d178c9010e34fafc9e892b782ba38254f94ad4f9e21db","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.OT","submitted_at":"2026-06-09T17:46:10Z","title_canon_sha256":"d9c494b2af3f4ae3f3f1dac1f54fd9bab078fcad07dd424c88c0513ca9e58f59"},"schema_version":"1.0","source":{"id":"2606.11166","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11166","created_at":"2026-06-10T01:11:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11166v1","created_at":"2026-06-10T01:11:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11166","created_at":"2026-06-10T01:11:14Z"},{"alias_kind":"pith_short_12","alias_value":"OVKLI6OA6K2Q","created_at":"2026-06-10T01:11:14Z"},{"alias_kind":"pith_short_16","alias_value":"OVKLI6OA6K2QBKY7","created_at":"2026-06-10T01:11:14Z"},{"alias_kind":"pith_short_8","alias_value":"OVKLI6OA","created_at":"2026-06-10T01:11:14Z"}],"graph_snapshots":[{"event_id":"sha256:50fbb6237e84780db06d64f60bc2481042d1e1cfcaca4b2c6e201e92f644699b","target":"graph","created_at":"2026-06-10T01:11:14Z","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/2606.11166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are increasingly described as performing at the level of human experts on knowledge economy tasks. These claims are primarily based on how LLMs perform on benchmarking tasks that measure average performance across standardized datasets. Primary limitations of many benchmarking tasks are that they often measure performance based on content directly included in LLM training data, and they frequently do not assess the reliability of LLM performance or the magnitude of LLM errors. However, in high stakes contexts, these qualities are critically important. Through a nov","authors_text":"George Perrett, Javae Elliott, Jennifer Hill, Marc Scott","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.OT","submitted_at":"2026-06-09T17:46:10Z","title":"Flaws in the LLM Automation Narrative"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11166","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":"sha256:123cedb5f81d94318c1b9c70386b6a4a1f2509b2778554297393b6f8325c507f","target":"record","created_at":"2026-06-10T01:11:14Z","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":"c7013c1fc2fe6075708d178c9010e34fafc9e892b782ba38254f94ad4f9e21db","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.OT","submitted_at":"2026-06-09T17:46:10Z","title_canon_sha256":"d9c494b2af3f4ae3f3f1dac1f54fd9bab078fcad07dd424c88c0513ca9e58f59"},"schema_version":"1.0","source":{"id":"2606.11166","kind":"arxiv","version":1}},"canonical_sha256":"7554b479c0f2b500ab1fe092472eee5f504c6fbb7e6c6ef402dcacb159b8580d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7554b479c0f2b500ab1fe092472eee5f504c6fbb7e6c6ef402dcacb159b8580d","first_computed_at":"2026-06-10T01:11:14.878376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:11:14.878376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zhk9MzPpILtAfxq8XGgwKn4YHVN/ZE6tnnx97vsslYKmz5Wpl5GC8P/9qMrS5yqeZXxo/d8DTbRMZGEZO0GEBw==","signature_status":"signed_v1","signed_at":"2026-06-10T01:11:14.879109Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11166","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:123cedb5f81d94318c1b9c70386b6a4a1f2509b2778554297393b6f8325c507f","sha256:50fbb6237e84780db06d64f60bc2481042d1e1cfcaca4b2c6e201e92f644699b"],"state_sha256":"ea8b76b4c6dd9e3ce1715cd25bd0730550af16b37c9824534554796daaea35d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ICyo8QD4GERlxahnww0SW6J1dWOUcYCSRSl5pfDjtc6UP5/3rCJoEeVcdfTtV1RW4F33YNx3WJTOBPcyCobgAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T17:15:26.365634Z","bundle_sha256":"455295acfdf5a11aca64108a59248adf8978772069782d1ec1d4c3af32b27fd1"}}