{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YRHVAUTXZ3I5BDOP63GBTS5DD5","short_pith_number":"pith:YRHVAUTX","canonical_record":{"source":{"id":"2406.11629","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T15:11:58Z","cross_cats_sorted":[],"title_canon_sha256":"84d960fef51f102d7b02278277cecaeea1e54b211c75c6438d5c66ae03c41d1f","abstract_canon_sha256":"917dffb0a5115d5e62e7ce40e73bfebfc76de37677c2b5a723c0e245cdbec166"},"schema_version":"1.0"},"canonical_sha256":"c44f505277ced1d08dcff6cc19cba31f562aefc9e0f47e87c0e502b03d16e6c1","source":{"kind":"arxiv","id":"2406.11629","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11629","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11629v6","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11629","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_12","alias_value":"YRHVAUTXZ3I5","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_16","alias_value":"YRHVAUTXZ3I5BDOP","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_8","alias_value":"YRHVAUTX","created_at":"2026-07-05T10:09:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YRHVAUTXZ3I5BDOP63GBTS5DD5","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11629","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T15:11:58Z","cross_cats_sorted":[],"title_canon_sha256":"84d960fef51f102d7b02278277cecaeea1e54b211c75c6438d5c66ae03c41d1f","abstract_canon_sha256":"917dffb0a5115d5e62e7ce40e73bfebfc76de37677c2b5a723c0e245cdbec166"},"schema_version":"1.0"},"canonical_sha256":"c44f505277ced1d08dcff6cc19cba31f562aefc9e0f47e87c0e502b03d16e6c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:44.824026Z","signature_b64":"GxzHIL8345eNMth/5OIDlb7JjEhiqUXe8EjGsgRqmezmQ5ALRHIP2ChlWGBdNAB9KKquR1f7pmHCvoqRxliNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c44f505277ced1d08dcff6cc19cba31f562aefc9e0f47e87c0e502b03d16e6c1","last_reissued_at":"2026-07-05T10:09:44.823555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:44.823555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11629","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"485pRPHApmI2p+4PWv7zb9/6LEPUVD4JSWhAI4GeHfKwhnnXEFNzkYV8jTFiR8Z/fyrhxwn3UxQbTJbaj2ZWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T09:29:09.625137Z"},"content_sha256":"451ac76d3097ff71d3520b176191ecea91fb9cfb3efa816b0e82db83bb955e35","schema_version":"1.0","event_id":"sha256:451ac76d3097ff71d3520b176191ecea91fb9cfb3efa816b0e82db83bb955e35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YRHVAUTXZ3I5BDOP63GBTS5DD5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Many-Shot In-Context Learning Help LLMs as Evaluators? A Preliminary Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mao Zheng, Mingyang Song, Xuan Luo, Yue Pan","submitted_at":"2024-06-17T15:11:58Z","abstract_excerpt":"Utilizing Large Language Models (LLMs) as evaluators to assess the performance of LLMs has garnered attention. However, this kind of evaluation approach is affected by potential biases within LLMs, raising concerns about the accuracy and reliability of the evaluation results of LLMs. To address this problem, we propose and study two many-shot In-Context Learning (ICL) prompt templates to help LLM evaluators mitigate potential biases: Many-Shot with Reference (MSwR) and Many-Shot without Reference (MSoR). Specifically, the former utilizes in-context examples with model-generated evaluation rati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11629","kind":"arxiv","version":6},"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/2406.11629/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":"2026-07-05T10:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mXma4tIyaYeLx+EpV8LV4KfzqxJd/AC5pgDZK8E2eF0XJlQ2J+vszYe8wzWSpmJw+D6SY0/T2Cse7LT5YGxJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T09:29:09.625829Z"},"content_sha256":"879cba02bcd56012291256687948288c8aca8824d39b32a3478c4dbc59e73b19","schema_version":"1.0","event_id":"sha256:879cba02bcd56012291256687948288c8aca8824d39b32a3478c4dbc59e73b19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YRHVAUTXZ3I5BDOP63GBTS5DD5/bundle.json","state_url":"https://pith.science/pith/YRHVAUTXZ3I5BDOP63GBTS5DD5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YRHVAUTXZ3I5BDOP63GBTS5DD5/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":"2026-08-13T09:29:09Z","links":{"resolver":"https://pith.science/pith/YRHVAUTXZ3I5BDOP63GBTS5DD5","bundle":"https://pith.science/pith/YRHVAUTXZ3I5BDOP63GBTS5DD5/bundle.json","state":"https://pith.science/pith/YRHVAUTXZ3I5BDOP63GBTS5DD5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YRHVAUTXZ3I5BDOP63GBTS5DD5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YRHVAUTXZ3I5BDOP63GBTS5DD5","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":"917dffb0a5115d5e62e7ce40e73bfebfc76de37677c2b5a723c0e245cdbec166","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T15:11:58Z","title_canon_sha256":"84d960fef51f102d7b02278277cecaeea1e54b211c75c6438d5c66ae03c41d1f"},"schema_version":"1.0","source":{"id":"2406.11629","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11629","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11629v6","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11629","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_12","alias_value":"YRHVAUTXZ3I5","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_16","alias_value":"YRHVAUTXZ3I5BDOP","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_8","alias_value":"YRHVAUTX","created_at":"2026-07-05T10:09:44Z"}],"graph_snapshots":[{"event_id":"sha256:879cba02bcd56012291256687948288c8aca8824d39b32a3478c4dbc59e73b19","target":"graph","created_at":"2026-07-05T10:09:44Z","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/2406.11629/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Utilizing Large Language Models (LLMs) as evaluators to assess the performance of LLMs has garnered attention. However, this kind of evaluation approach is affected by potential biases within LLMs, raising concerns about the accuracy and reliability of the evaluation results of LLMs. To address this problem, we propose and study two many-shot In-Context Learning (ICL) prompt templates to help LLM evaluators mitigate potential biases: Many-Shot with Reference (MSwR) and Many-Shot without Reference (MSoR). Specifically, the former utilizes in-context examples with model-generated evaluation rati","authors_text":"Mao Zheng, Mingyang Song, Xuan Luo, Yue Pan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T15:11:58Z","title":"Can Many-Shot In-Context Learning Help LLMs as Evaluators? A Preliminary Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11629","kind":"arxiv","version":6},"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":"sha256:451ac76d3097ff71d3520b176191ecea91fb9cfb3efa816b0e82db83bb955e35","target":"record","created_at":"2026-07-05T10:09:44Z","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":"917dffb0a5115d5e62e7ce40e73bfebfc76de37677c2b5a723c0e245cdbec166","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T15:11:58Z","title_canon_sha256":"84d960fef51f102d7b02278277cecaeea1e54b211c75c6438d5c66ae03c41d1f"},"schema_version":"1.0","source":{"id":"2406.11629","kind":"arxiv","version":6}},"canonical_sha256":"c44f505277ced1d08dcff6cc19cba31f562aefc9e0f47e87c0e502b03d16e6c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c44f505277ced1d08dcff6cc19cba31f562aefc9e0f47e87c0e502b03d16e6c1","first_computed_at":"2026-07-05T10:09:44.823555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:44.823555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GxzHIL8345eNMth/5OIDlb7JjEhiqUXe8EjGsgRqmezmQ5ALRHIP2ChlWGBdNAB9KKquR1f7pmHCvoqRxliNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:44.824026Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11629","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:451ac76d3097ff71d3520b176191ecea91fb9cfb3efa816b0e82db83bb955e35","sha256:879cba02bcd56012291256687948288c8aca8824d39b32a3478c4dbc59e73b19"],"state_sha256":"989494b67b5b37d2666637d308becf60754fbce6d7855acb197f5ece6e4e5c0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N8V/Vt0PfFa+T/CYHHKC6Y42xe0IG4Ps+IUvZEPeVinVXx2CMSz8lkzgyrOcxjehvbXhlJNth6xkayfQOb/gBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T09:29:09.635572Z","bundle_sha256":"8dfa37d7d2a12bb3f75e3328c814e0a56a89fc7e687e3b86059fa3bf6583c590"}}