{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2BN54A6D2I2BONFPIDYGJBKUFI","short_pith_number":"pith:2BN54A6D","canonical_record":{"source":{"id":"2307.03025","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-06T14:42:01Z","cross_cats_sorted":[],"title_canon_sha256":"969313b84bf49bebc4bb3e3304354340037da0c6620e2db2fee3bccc33e7fbc6","abstract_canon_sha256":"3305c8676fe0a73083ee1227aea2aae857d688f7fb004d8aadaaa92b5c0dab47"},"schema_version":"1.0"},"canonical_sha256":"d05bde03c3d2341734af40f06485542a16c621ec1b78b79742d4c102d5e3c501","source":{"kind":"arxiv","id":"2307.03025","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.03025","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"arxiv_version","alias_value":"2307.03025v3","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03025","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_12","alias_value":"2BN54A6D2I2B","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_16","alias_value":"2BN54A6D2I2BONFP","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_8","alias_value":"2BN54A6D","created_at":"2026-07-05T07:11:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2BN54A6D2I2BONFPIDYGJBKUFI","target":"record","payload":{"canonical_record":{"source":{"id":"2307.03025","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-06T14:42:01Z","cross_cats_sorted":[],"title_canon_sha256":"969313b84bf49bebc4bb3e3304354340037da0c6620e2db2fee3bccc33e7fbc6","abstract_canon_sha256":"3305c8676fe0a73083ee1227aea2aae857d688f7fb004d8aadaaa92b5c0dab47"},"schema_version":"1.0"},"canonical_sha256":"d05bde03c3d2341734af40f06485542a16c621ec1b78b79742d4c102d5e3c501","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:57.334880Z","signature_b64":"XVag9QIRR4yi6QukY/d0aBHac5Y/ouuVTz+scqkfAdVzc+rK1Y+X1WlxCZF1xncCOXNRfNKXQr9jeipVU9N7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d05bde03c3d2341734af40f06485542a16c621ec1b78b79742d4c102d5e3c501","last_reissued_at":"2026-07-05T07:11:57.334387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:57.334387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.03025","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:11:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YYNEUQXoRHdU7nfzfFZcR1xol0uh9eHcPaF9oDimYohiXY1Ifuo2cgYQ9WTygLR0/i3cNpzk3IL7v0UcLgfmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:55:33.834173Z"},"content_sha256":"569254cb2a79da20a6beab9368e5eb0c9231fe953851aef484fda1d09bae9b0f","schema_version":"1.0","event_id":"sha256:569254cb2a79da20a6beab9368e5eb0c9231fe953851aef484fda1d09bae9b0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2BN54A6D2I2BONFPIDYGJBKUFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Style Over Substance: Evaluation Biases for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alham Fikri Aji, Minghao Wu","submitted_at":"2023-07-06T14:42:01Z","abstract_excerpt":"As large language models (LLMs) continue to advance, accurately and comprehensively evaluating their performance becomes increasingly challenging. Ranking the relative performance of LLMs based on Elo ratings, according to human judgment, is gaining more popularity. However, the extent to which humans and LLMs are capable evaluators remains uncertain. This study investigates the behavior of crowd-sourced and expert annotators, as well as LLMs, when comparing outputs from different models. To achieve this, we curate a dataset of intentionally flawed machine-generated answers. Our findings revea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03025","kind":"arxiv","version":3},"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/2307.03025/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":"2026-07-05T07:11:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yi4bD9QiLbsguWwMSAUS1kaj3vnwgMEL6108AoZX8evxezpxKNnC1cgAOPLypIRkLQ9+UDT8xrk55Tk2Oh79Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:55:33.834662Z"},"content_sha256":"2bceeea4b44f55be2913cb9861d6e10cc3749cc905d4f86167b7c0be9e9dc6ef","schema_version":"1.0","event_id":"sha256:2bceeea4b44f55be2913cb9861d6e10cc3749cc905d4f86167b7c0be9e9dc6ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2BN54A6D2I2BONFPIDYGJBKUFI/bundle.json","state_url":"https://pith.science/pith/2BN54A6D2I2BONFPIDYGJBKUFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2BN54A6D2I2BONFPIDYGJBKUFI/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":"2026-08-08T12:55:33Z","links":{"resolver":"https://pith.science/pith/2BN54A6D2I2BONFPIDYGJBKUFI","bundle":"https://pith.science/pith/2BN54A6D2I2BONFPIDYGJBKUFI/bundle.json","state":"https://pith.science/pith/2BN54A6D2I2BONFPIDYGJBKUFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2BN54A6D2I2BONFPIDYGJBKUFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2BN54A6D2I2BONFPIDYGJBKUFI","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":"3305c8676fe0a73083ee1227aea2aae857d688f7fb004d8aadaaa92b5c0dab47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-06T14:42:01Z","title_canon_sha256":"969313b84bf49bebc4bb3e3304354340037da0c6620e2db2fee3bccc33e7fbc6"},"schema_version":"1.0","source":{"id":"2307.03025","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.03025","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"arxiv_version","alias_value":"2307.03025v3","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03025","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_12","alias_value":"2BN54A6D2I2B","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_16","alias_value":"2BN54A6D2I2BONFP","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_8","alias_value":"2BN54A6D","created_at":"2026-07-05T07:11:57Z"}],"graph_snapshots":[{"event_id":"sha256:2bceeea4b44f55be2913cb9861d6e10cc3749cc905d4f86167b7c0be9e9dc6ef","target":"graph","created_at":"2026-07-05T07:11:57Z","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/2307.03025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) continue to advance, accurately and comprehensively evaluating their performance becomes increasingly challenging. Ranking the relative performance of LLMs based on Elo ratings, according to human judgment, is gaining more popularity. However, the extent to which humans and LLMs are capable evaluators remains uncertain. This study investigates the behavior of crowd-sourced and expert annotators, as well as LLMs, when comparing outputs from different models. To achieve this, we curate a dataset of intentionally flawed machine-generated answers. Our findings revea","authors_text":"Alham Fikri Aji, Minghao Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-06T14:42:01Z","title":"Style Over Substance: Evaluation Biases for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03025","kind":"arxiv","version":3},"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":"sha256:569254cb2a79da20a6beab9368e5eb0c9231fe953851aef484fda1d09bae9b0f","target":"record","created_at":"2026-07-05T07:11:57Z","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":"3305c8676fe0a73083ee1227aea2aae857d688f7fb004d8aadaaa92b5c0dab47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-06T14:42:01Z","title_canon_sha256":"969313b84bf49bebc4bb3e3304354340037da0c6620e2db2fee3bccc33e7fbc6"},"schema_version":"1.0","source":{"id":"2307.03025","kind":"arxiv","version":3}},"canonical_sha256":"d05bde03c3d2341734af40f06485542a16c621ec1b78b79742d4c102d5e3c501","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d05bde03c3d2341734af40f06485542a16c621ec1b78b79742d4c102d5e3c501","first_computed_at":"2026-07-05T07:11:57.334387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:57.334387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XVag9QIRR4yi6QukY/d0aBHac5Y/ouuVTz+scqkfAdVzc+rK1Y+X1WlxCZF1xncCOXNRfNKXQr9jeipVU9N7Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:57.334880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.03025","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:569254cb2a79da20a6beab9368e5eb0c9231fe953851aef484fda1d09bae9b0f","sha256:2bceeea4b44f55be2913cb9861d6e10cc3749cc905d4f86167b7c0be9e9dc6ef"],"state_sha256":"26e75bfd4485b4f169589ee1398a57ce35806fff8d5232ae9eb6d3ea468c173c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EtgUPjjaPBXO/PhBwAAODhByF++GkWSoFR7L3bpemUFpWPKk+OMMLviYPQq7szhsCtc8uZ9J4+je/tRN4hGgCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:55:33.838350Z","bundle_sha256":"7654911f89048728fe745da9d361ec948fd7d46d7b62baf4078f00ba49ac3432"}}