{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RQQAPKZPYYM34RS7HZEESY7NFI","short_pith_number":"pith:RQQAPKZP","canonical_record":{"source":{"id":"2607.26191","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-28T18:50:39Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SE"],"title_canon_sha256":"58cf312fe280a6ebf17c09dd52a27f70410f08a87721342de2a4d117e096157a","abstract_canon_sha256":"8a509c13fe842767406039897eeade9faa05907049bc0d0d40712f28d7e21ddb"},"schema_version":"1.0"},"canonical_sha256":"8c2007ab2fc619be465f3e484963ed2a0b62cf6ef9695b0fd78fa3f9b25d4238","source":{"kind":"arxiv","id":"2607.26191","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26191","created_at":"2026-07-30T00:08:40Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26191v1","created_at":"2026-07-30T00:08:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26191","created_at":"2026-07-30T00:08:40Z"},{"alias_kind":"pith_short_12","alias_value":"RQQAPKZPYYM3","created_at":"2026-07-30T00:08:40Z"},{"alias_kind":"pith_short_16","alias_value":"RQQAPKZPYYM34RS7","created_at":"2026-07-30T00:08:40Z"},{"alias_kind":"pith_short_8","alias_value":"RQQAPKZP","created_at":"2026-07-30T00:08:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RQQAPKZPYYM34RS7HZEESY7NFI","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26191","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-28T18:50:39Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SE"],"title_canon_sha256":"58cf312fe280a6ebf17c09dd52a27f70410f08a87721342de2a4d117e096157a","abstract_canon_sha256":"8a509c13fe842767406039897eeade9faa05907049bc0d0d40712f28d7e21ddb"},"schema_version":"1.0"},"canonical_sha256":"8c2007ab2fc619be465f3e484963ed2a0b62cf6ef9695b0fd78fa3f9b25d4238","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c2007ab2fc619be465f3e484963ed2a0b62cf6ef9695b0fd78fa3f9b25d4238","last_reissued_at":"2026-07-30T00:08:40.871945Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T00:08:40.871945Z"},"source_kind":"arxiv","source_id":"2607.26191","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":"2026-07-30T00:08:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DQDQTpTDFQiwtYMtMaUGpxe9COeKF8FfvPhYca4bG3K9aiclPirmsBKOhOq/De4B74w1XwpB9xN/RC9AaHYvBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:07:33.345623Z"},"content_sha256":"2ee74063782cd27caea9df595afba1d3ca91b7757d9960b90ac2059ec17a2782","schema_version":"1.0","event_id":"sha256:2ee74063782cd27caea9df595afba1d3ca91b7757d9960b90ac2059ec17a2782"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RQQAPKZPYYM34RS7HZEESY7NFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Position: Evaluation Scores Are Perishable Knowledge Claims","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Sankalp Gilda, Shlok Gilda","submitted_at":"2026-07-28T18:50:39Z","abstract_excerpt":"Evaluation methodologies for language models increasingly combine multiple signals, from automated metrics and LLM-as-judge ratings to human assessments and benchmark suite results. When these signals are aggregated via averaging, evaluation confidence can then substantially exceed the reliability of the weakest signal: a phenomenon we call trust inflation in evaluation. We argue that evaluation scores should be treated as epistemic claims with three properties: formality (human evaluation provides stronger evidence than an automated metric), scope (a benchmark result applies to the tested dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26191","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/2607.26191/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":"2026-07-30T00:08:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jPsercJBQgK5fySLjM/7XogcEwiwdGkHiAVUoeJfyCR4vA85TiejP5LCoDPeAYq5/ELyUhLQcq9NIRo+OwDXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:07:33.346130Z"},"content_sha256":"c08b52d7fe99d529ab72a474693be41b4a4c6dd7524f5383221ebc17cc3aa247","schema_version":"1.0","event_id":"sha256:c08b52d7fe99d529ab72a474693be41b4a4c6dd7524f5383221ebc17cc3aa247"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RQQAPKZPYYM34RS7HZEESY7NFI/bundle.json","state_url":"https://pith.science/pith/RQQAPKZPYYM34RS7HZEESY7NFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RQQAPKZPYYM34RS7HZEESY7NFI/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":"2026-08-06T12:07:33Z","links":{"resolver":"https://pith.science/pith/RQQAPKZPYYM34RS7HZEESY7NFI","bundle":"https://pith.science/pith/RQQAPKZPYYM34RS7HZEESY7NFI/bundle.json","state":"https://pith.science/pith/RQQAPKZPYYM34RS7HZEESY7NFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RQQAPKZPYYM34RS7HZEESY7NFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RQQAPKZPYYM34RS7HZEESY7NFI","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":"8a509c13fe842767406039897eeade9faa05907049bc0d0d40712f28d7e21ddb","cross_cats_sorted":["cs.CL","cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-28T18:50:39Z","title_canon_sha256":"58cf312fe280a6ebf17c09dd52a27f70410f08a87721342de2a4d117e096157a"},"schema_version":"1.0","source":{"id":"2607.26191","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26191","created_at":"2026-07-30T00:08:40Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26191v1","created_at":"2026-07-30T00:08:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26191","created_at":"2026-07-30T00:08:40Z"},{"alias_kind":"pith_short_12","alias_value":"RQQAPKZPYYM3","created_at":"2026-07-30T00:08:40Z"},{"alias_kind":"pith_short_16","alias_value":"RQQAPKZPYYM34RS7","created_at":"2026-07-30T00:08:40Z"},{"alias_kind":"pith_short_8","alias_value":"RQQAPKZP","created_at":"2026-07-30T00:08:40Z"}],"graph_snapshots":[{"event_id":"sha256:c08b52d7fe99d529ab72a474693be41b4a4c6dd7524f5383221ebc17cc3aa247","target":"graph","created_at":"2026-07-30T00:08:40Z","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/2607.26191/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluation methodologies for language models increasingly combine multiple signals, from automated metrics and LLM-as-judge ratings to human assessments and benchmark suite results. When these signals are aggregated via averaging, evaluation confidence can then substantially exceed the reliability of the weakest signal: a phenomenon we call trust inflation in evaluation. We argue that evaluation scores should be treated as epistemic claims with three properties: formality (human evaluation provides stronger evidence than an automated metric), scope (a benchmark result applies to the tested dis","authors_text":"Sankalp Gilda, Shlok Gilda","cross_cats":["cs.CL","cs.LG","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-28T18:50:39Z","title":"Position: Evaluation Scores Are Perishable Knowledge Claims"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26191","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":"sha256:2ee74063782cd27caea9df595afba1d3ca91b7757d9960b90ac2059ec17a2782","target":"record","created_at":"2026-07-30T00:08:40Z","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":"8a509c13fe842767406039897eeade9faa05907049bc0d0d40712f28d7e21ddb","cross_cats_sorted":["cs.CL","cs.LG","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-28T18:50:39Z","title_canon_sha256":"58cf312fe280a6ebf17c09dd52a27f70410f08a87721342de2a4d117e096157a"},"schema_version":"1.0","source":{"id":"2607.26191","kind":"arxiv","version":1}},"canonical_sha256":"8c2007ab2fc619be465f3e484963ed2a0b62cf6ef9695b0fd78fa3f9b25d4238","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c2007ab2fc619be465f3e484963ed2a0b62cf6ef9695b0fd78fa3f9b25d4238","first_computed_at":"2026-07-30T00:08:40.871945Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T00:08:40.871945Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26191","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ee74063782cd27caea9df595afba1d3ca91b7757d9960b90ac2059ec17a2782","sha256:c08b52d7fe99d529ab72a474693be41b4a4c6dd7524f5383221ebc17cc3aa247"],"state_sha256":"7bd2ac3826368537f88dec6c9cf83738a6e1feec34c5b67a6f8f189e4bf4d0cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nG42OEWHXoYxwQAO6X3tk9FDah7m1x/1ux4T1Lfr9aPMW1DDgyC9NxfF5C2irbqq7L0ewvi5HT2aSsvT7sR8AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T12:07:33.349750Z","bundle_sha256":"61e801093758b739155628b8eac229336a2ab7115cf6023e39c3f954e26e6e1c"}}