{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6J4GG266G6VT6F24DGXEINYN4P","short_pith_number":"pith:6J4GG266","canonical_record":{"source":{"id":"2406.11044","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T19:02:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"58d6c704d126ae89ed92304dac9201e41f1c5a84b1fe253acc31caf60203f144","abstract_canon_sha256":"fb2bba6d8de8eb58934642889e0dda9b3b5cc336b7d3ea1813e877b96f51fb9c"},"schema_version":"1.0"},"canonical_sha256":"f278636bde37ab3f175c19ae44370de3e7aedcc2c0e917a352a88dfbfb1cc340","source":{"kind":"arxiv","id":"2406.11044","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11044","created_at":"2026-07-05T10:11:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11044v2","created_at":"2026-07-05T10:11:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11044","created_at":"2026-07-05T10:11:20Z"},{"alias_kind":"pith_short_12","alias_value":"6J4GG266G6VT","created_at":"2026-07-05T10:11:20Z"},{"alias_kind":"pith_short_16","alias_value":"6J4GG266G6VT6F24","created_at":"2026-07-05T10:11:20Z"},{"alias_kind":"pith_short_8","alias_value":"6J4GG266","created_at":"2026-07-05T10:11:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6J4GG266G6VT6F24DGXEINYN4P","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11044","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T19:02:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"58d6c704d126ae89ed92304dac9201e41f1c5a84b1fe253acc31caf60203f144","abstract_canon_sha256":"fb2bba6d8de8eb58934642889e0dda9b3b5cc336b7d3ea1813e877b96f51fb9c"},"schema_version":"1.0"},"canonical_sha256":"f278636bde37ab3f175c19ae44370de3e7aedcc2c0e917a352a88dfbfb1cc340","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:20.944525Z","signature_b64":"qcx6nquuEpczaVMaNyPdRajIvYqgu6RVMOZh5TkPE+RYgd1qPt+UkhfK48j72KXTM/6c0vsdd+bA8zJUGULwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f278636bde37ab3f175c19ae44370de3e7aedcc2c0e917a352a88dfbfb1cc340","last_reissued_at":"2026-07-05T10:11:20.944068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:20.944068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11044","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:11:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ewYHK6OXucg2u51M1+XG7pCAtoX6hWWYCBSmYeZkE5XVNUhXY6Q9tenWzWMvOBdQxryoHBZfAlEQvXVb3ssAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:26:00.607975Z"},"content_sha256":"5836f376f4df7521814b9aaaea75195b243488fd4d27d43d4270f5251adf08eb","schema_version":"1.0","event_id":"sha256:5836f376f4df7521814b9aaaea75195b243488fd4d27d43d4270f5251adf08eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6J4GG266G6VT6F24DGXEINYN4P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating the Performance of Large Language Models via Debates","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Behrad Moniri, Edgar Dobriban, Hamed Hassani","submitted_at":"2024-06-16T19:02:31Z","abstract_excerpt":"Large Language Models (LLMs) are rapidly evolving and impacting various fields, necessitating the development of effective methods to evaluate and compare their performance. Most current approaches for performance evaluation are either based on fixed, domain-specific questions that lack the flexibility required in many real-world applications, or rely on human input, making them unscalable. To address these issues, we propose an automated benchmarking framework based on debates between LLMs, judged by another LLM. This method assesses not only domain knowledge, but also skills such as argument"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11044","kind":"arxiv","version":2},"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/2406.11044/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":"2026-07-05T10:11:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q99KYYVJdzuu7pqDpsma3zzZFsVOFRJt9K89ntXmcd+1lmgP7ZnGauGjFhHb5cuITP7HlhMmJSdGEzpUeY9TAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:26:00.608491Z"},"content_sha256":"643f4211ea6270a590968b252ede5a02cd830b2c6c267dae29935c0871a7c919","schema_version":"1.0","event_id":"sha256:643f4211ea6270a590968b252ede5a02cd830b2c6c267dae29935c0871a7c919"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6J4GG266G6VT6F24DGXEINYN4P/bundle.json","state_url":"https://pith.science/pith/6J4GG266G6VT6F24DGXEINYN4P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6J4GG266G6VT6F24DGXEINYN4P/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":"2026-08-07T21:26:00Z","links":{"resolver":"https://pith.science/pith/6J4GG266G6VT6F24DGXEINYN4P","bundle":"https://pith.science/pith/6J4GG266G6VT6F24DGXEINYN4P/bundle.json","state":"https://pith.science/pith/6J4GG266G6VT6F24DGXEINYN4P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6J4GG266G6VT6F24DGXEINYN4P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6J4GG266G6VT6F24DGXEINYN4P","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":"fb2bba6d8de8eb58934642889e0dda9b3b5cc336b7d3ea1813e877b96f51fb9c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T19:02:31Z","title_canon_sha256":"58d6c704d126ae89ed92304dac9201e41f1c5a84b1fe253acc31caf60203f144"},"schema_version":"1.0","source":{"id":"2406.11044","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11044","created_at":"2026-07-05T10:11:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11044v2","created_at":"2026-07-05T10:11:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11044","created_at":"2026-07-05T10:11:20Z"},{"alias_kind":"pith_short_12","alias_value":"6J4GG266G6VT","created_at":"2026-07-05T10:11:20Z"},{"alias_kind":"pith_short_16","alias_value":"6J4GG266G6VT6F24","created_at":"2026-07-05T10:11:20Z"},{"alias_kind":"pith_short_8","alias_value":"6J4GG266","created_at":"2026-07-05T10:11:20Z"}],"graph_snapshots":[{"event_id":"sha256:643f4211ea6270a590968b252ede5a02cd830b2c6c267dae29935c0871a7c919","target":"graph","created_at":"2026-07-05T10:11:20Z","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/2406.11044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are rapidly evolving and impacting various fields, necessitating the development of effective methods to evaluate and compare their performance. Most current approaches for performance evaluation are either based on fixed, domain-specific questions that lack the flexibility required in many real-world applications, or rely on human input, making them unscalable. To address these issues, we propose an automated benchmarking framework based on debates between LLMs, judged by another LLM. This method assesses not only domain knowledge, but also skills such as argument","authors_text":"Behrad Moniri, Edgar Dobriban, Hamed Hassani","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T19:02:31Z","title":"Evaluating the Performance of Large Language Models via Debates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11044","kind":"arxiv","version":2},"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":"sha256:5836f376f4df7521814b9aaaea75195b243488fd4d27d43d4270f5251adf08eb","target":"record","created_at":"2026-07-05T10:11:20Z","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":"fb2bba6d8de8eb58934642889e0dda9b3b5cc336b7d3ea1813e877b96f51fb9c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T19:02:31Z","title_canon_sha256":"58d6c704d126ae89ed92304dac9201e41f1c5a84b1fe253acc31caf60203f144"},"schema_version":"1.0","source":{"id":"2406.11044","kind":"arxiv","version":2}},"canonical_sha256":"f278636bde37ab3f175c19ae44370de3e7aedcc2c0e917a352a88dfbfb1cc340","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f278636bde37ab3f175c19ae44370de3e7aedcc2c0e917a352a88dfbfb1cc340","first_computed_at":"2026-07-05T10:11:20.944068Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:20.944068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qcx6nquuEpczaVMaNyPdRajIvYqgu6RVMOZh5TkPE+RYgd1qPt+UkhfK48j72KXTM/6c0vsdd+bA8zJUGULwDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:20.944525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11044","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5836f376f4df7521814b9aaaea75195b243488fd4d27d43d4270f5251adf08eb","sha256:643f4211ea6270a590968b252ede5a02cd830b2c6c267dae29935c0871a7c919"],"state_sha256":"db970808d3231a9a3c3c5f3bb33a0a0c1c6a293f6bc26641a0435e8f3c03e40e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ekRGqO9cnG+2sHDP2ATTL7HOdgJP9W3YtUDLTF9wcQSYXQFGo214DdxLyn2M3VbtioLS2uWTashBhWoHC0zFDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:26:00.612932Z","bundle_sha256":"e75615af1cad3623f4e50587575e299e31aa75bf8bb3e15d6cf1d4e6ef60a72f"}}