{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CZ2QDCDIAXLMBORS4GFFRFYOFE","short_pith_number":"pith:CZ2QDCDI","canonical_record":{"source":{"id":"2412.04363","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-12-05T17:22:04Z","cross_cats_sorted":[],"title_canon_sha256":"214e131de5a46dba8baaeb857b900e50c3bad3d782f53ba06c1f9c89f6514238","abstract_canon_sha256":"b28bf1d88601dfbd2d41b4de11072545e7be128d4afa860d9c679370315bb4d6"},"schema_version":"1.0"},"canonical_sha256":"167501886805d6c0ba32e18a58970e290880b8fd1fd34a9e0a8fa89f9123d020","source":{"kind":"arxiv","id":"2412.04363","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04363","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04363v1","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04363","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_12","alias_value":"CZ2QDCDIAXLM","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_16","alias_value":"CZ2QDCDIAXLMBORS","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_8","alias_value":"CZ2QDCDI","created_at":"2026-07-05T09:45:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CZ2QDCDIAXLMBORS4GFFRFYOFE","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04363","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-12-05T17:22:04Z","cross_cats_sorted":[],"title_canon_sha256":"214e131de5a46dba8baaeb857b900e50c3bad3d782f53ba06c1f9c89f6514238","abstract_canon_sha256":"b28bf1d88601dfbd2d41b4de11072545e7be128d4afa860d9c679370315bb4d6"},"schema_version":"1.0"},"canonical_sha256":"167501886805d6c0ba32e18a58970e290880b8fd1fd34a9e0a8fa89f9123d020","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:02.871369Z","signature_b64":"CKbb1Q6/5+SlrXYjZAN09JVLmlpOfvcEz9kTPhcT5/2I8VGl6cWKfIg6sJ5qFwkKxgJ6UK9hT/CGy3m7rUp7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"167501886805d6c0ba32e18a58970e290880b8fd1fd34a9e0a8fa89f9123d020","last_reissued_at":"2026-07-05T09:45:02.870883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:02.870883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04363","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":"2026-07-05T09:45:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3PNYJBK3Uwu65y8Eq+Z9Z5R6uK1hZQSoMlr3x0zyhKDCxeJ/3ygnqFSDT28GLVDwSRumcwTtn/ueaGVUZyWuBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:27:10.267852Z"},"content_sha256":"19bfe6cb50a749defcbfa0aef77bcb36c1e1b1b6816a37f9c6f81c5ebf640f40","schema_version":"1.0","event_id":"sha256:19bfe6cb50a749defcbfa0aef77bcb36c1e1b1b6816a37f9c6f81c5ebf640f40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CZ2QDCDIAXLMBORS4GFFRFYOFE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Challenges in Trustworthy Human Evaluation of Chatbots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Alexander M. Rush, Tanya Goyal, Wenting Zhao","submitted_at":"2024-12-05T17:22:04Z","abstract_excerpt":"Open community-driven platforms like Chatbot Arena that collect user preference data from site visitors have gained a reputation as one of the most trustworthy publicly available benchmarks for LLM performance. While now standard, it is tricky to implement effective guardrails to collect high-quality annotations from humans. In this paper, we demonstrate that three sources of bad annotations, both malicious and otherwise, can corrupt the reliability of open leaderboard rankings. In particular, we show that only 10\\% of poor quality votes by apathetic (site visitors not appropriately incentiviz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04363","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/2412.04363/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":"2026-07-05T09:45:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"urbjwn/lvygINC+3vUyn4QNyVI/BeL7stg/XeH08LBtYskpi9mvRvFtJ5D+6EytaiwFydmoYnJWpornZct7+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:27:10.268391Z"},"content_sha256":"59ee62bde7de780e0985abdebb803283be8fdee5d677346a7affdd61098f9ee7","schema_version":"1.0","event_id":"sha256:59ee62bde7de780e0985abdebb803283be8fdee5d677346a7affdd61098f9ee7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZ2QDCDIAXLMBORS4GFFRFYOFE/bundle.json","state_url":"https://pith.science/pith/CZ2QDCDIAXLMBORS4GFFRFYOFE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZ2QDCDIAXLMBORS4GFFRFYOFE/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":"2026-08-08T04:27:10Z","links":{"resolver":"https://pith.science/pith/CZ2QDCDIAXLMBORS4GFFRFYOFE","bundle":"https://pith.science/pith/CZ2QDCDIAXLMBORS4GFFRFYOFE/bundle.json","state":"https://pith.science/pith/CZ2QDCDIAXLMBORS4GFFRFYOFE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZ2QDCDIAXLMBORS4GFFRFYOFE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CZ2QDCDIAXLMBORS4GFFRFYOFE","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":"b28bf1d88601dfbd2d41b4de11072545e7be128d4afa860d9c679370315bb4d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-12-05T17:22:04Z","title_canon_sha256":"214e131de5a46dba8baaeb857b900e50c3bad3d782f53ba06c1f9c89f6514238"},"schema_version":"1.0","source":{"id":"2412.04363","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04363","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04363v1","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04363","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_12","alias_value":"CZ2QDCDIAXLM","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_16","alias_value":"CZ2QDCDIAXLMBORS","created_at":"2026-07-05T09:45:02Z"},{"alias_kind":"pith_short_8","alias_value":"CZ2QDCDI","created_at":"2026-07-05T09:45:02Z"}],"graph_snapshots":[{"event_id":"sha256:59ee62bde7de780e0985abdebb803283be8fdee5d677346a7affdd61098f9ee7","target":"graph","created_at":"2026-07-05T09:45:02Z","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/2412.04363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open community-driven platforms like Chatbot Arena that collect user preference data from site visitors have gained a reputation as one of the most trustworthy publicly available benchmarks for LLM performance. While now standard, it is tricky to implement effective guardrails to collect high-quality annotations from humans. In this paper, we demonstrate that three sources of bad annotations, both malicious and otherwise, can corrupt the reliability of open leaderboard rankings. In particular, we show that only 10\\% of poor quality votes by apathetic (site visitors not appropriately incentiviz","authors_text":"Alexander M. Rush, Tanya Goyal, Wenting Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-12-05T17:22:04Z","title":"Challenges in Trustworthy Human Evaluation of Chatbots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04363","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":"sha256:19bfe6cb50a749defcbfa0aef77bcb36c1e1b1b6816a37f9c6f81c5ebf640f40","target":"record","created_at":"2026-07-05T09:45:02Z","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":"b28bf1d88601dfbd2d41b4de11072545e7be128d4afa860d9c679370315bb4d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-12-05T17:22:04Z","title_canon_sha256":"214e131de5a46dba8baaeb857b900e50c3bad3d782f53ba06c1f9c89f6514238"},"schema_version":"1.0","source":{"id":"2412.04363","kind":"arxiv","version":1}},"canonical_sha256":"167501886805d6c0ba32e18a58970e290880b8fd1fd34a9e0a8fa89f9123d020","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"167501886805d6c0ba32e18a58970e290880b8fd1fd34a9e0a8fa89f9123d020","first_computed_at":"2026-07-05T09:45:02.870883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:02.870883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CKbb1Q6/5+SlrXYjZAN09JVLmlpOfvcEz9kTPhcT5/2I8VGl6cWKfIg6sJ5qFwkKxgJ6UK9hT/CGy3m7rUp7DA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:02.871369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04363","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19bfe6cb50a749defcbfa0aef77bcb36c1e1b1b6816a37f9c6f81c5ebf640f40","sha256:59ee62bde7de780e0985abdebb803283be8fdee5d677346a7affdd61098f9ee7"],"state_sha256":"e38347a988c678db8011cb72decda60253a5cb37931b818ae49345b32e6cd203"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZNfeBehtR9rK+LT68MuGn/FuNLpaREKAsJQA+owIBMdAL6QZG3++XJZPWBKHttbLrueW9pylML8z2YPkgitjCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:27:10.271714Z","bundle_sha256":"e605acec9f84c4ba015eb276d88d5396c02eabbb6d3b33d083958ad5cf8f5928"}}