{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KBID3T6KGA6NK4TQKA76W7RSG6","short_pith_number":"pith:KBID3T6K","canonical_record":{"source":{"id":"2406.02863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T02:25:10Z","cross_cats_sorted":[],"title_canon_sha256":"224101ace06b3cbf459621dd8f54b9fc58cf0a984c94ebc63efe375cfd23ef5f","abstract_canon_sha256":"4464a54e4ba4d0f10d1b182ed08ccecc3d9718e83c0c38aeecc6e94bca98815e"},"schema_version":"1.0"},"canonical_sha256":"50503dcfca303cd57270503feb7e32378213d72a910aacce1fa1f581a8bdf162","source":{"kind":"arxiv","id":"2406.02863","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02863","created_at":"2026-07-05T08:27:31Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02863v1","created_at":"2026-07-05T08:27:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02863","created_at":"2026-07-05T08:27:31Z"},{"alias_kind":"pith_short_12","alias_value":"KBID3T6KGA6N","created_at":"2026-07-05T08:27:31Z"},{"alias_kind":"pith_short_16","alias_value":"KBID3T6KGA6NK4TQ","created_at":"2026-07-05T08:27:31Z"},{"alias_kind":"pith_short_8","alias_value":"KBID3T6K","created_at":"2026-07-05T08:27:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KBID3T6KGA6NK4TQKA76W7RSG6","target":"record","payload":{"canonical_record":{"source":{"id":"2406.02863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T02:25:10Z","cross_cats_sorted":[],"title_canon_sha256":"224101ace06b3cbf459621dd8f54b9fc58cf0a984c94ebc63efe375cfd23ef5f","abstract_canon_sha256":"4464a54e4ba4d0f10d1b182ed08ccecc3d9718e83c0c38aeecc6e94bca98815e"},"schema_version":"1.0"},"canonical_sha256":"50503dcfca303cd57270503feb7e32378213d72a910aacce1fa1f581a8bdf162","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:31.410626Z","signature_b64":"VPpcZ4O1PoUeR/MCDZNaimQlzA+61oTFs/zLvyCi8jWx6FP9izpL6NdiYQ/nORuhPFOse1eXbm++VAPKdJBrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50503dcfca303cd57270503feb7e32378213d72a910aacce1fa1f581a8bdf162","last_reissued_at":"2026-07-05T08:27:31.410113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:31.410113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.02863","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":"2026-07-05T08:27:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o06sITAGd1LlvTo+w3TZr1v6R1DyiEl131RUp8xqVyAYv33mZJlH3FFnuN/R3WVJZWckzbFqwYndRIprkgz2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:24:42.820866Z"},"content_sha256":"79805da04fe6c018ffe2265f9be11a3a02db13862bd1433d6222704db652d0f3","schema_version":"1.0","event_id":"sha256:79805da04fe6c018ffe2265f9be11a3a02db13862bd1433d6222704db652d0f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KBID3T6KGA6NK4TQKA76W7RSG6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM as a Scorer: The Impact of Output Order on Dialogue Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hideki Nakayama, KuanChao Chu, Yi-Pei Chen","submitted_at":"2024-06-05T02:25:10Z","abstract_excerpt":"This research investigates the effect of prompt design on dialogue evaluation using large language models (LLMs). While LLMs are increasingly used for scoring various inputs, creating effective prompts for dialogue evaluation remains challenging due to model sensitivity and subjectivity in dialogue assessments. Our study experimented with different prompt structures, altering the sequence of output instructions and including explanatory reasons. We found that the order of presenting reasons and scores significantly influences LLMs' scoring, with a \"reason-first\" approach yielding more comprehe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02863","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/2406.02863/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":"2026-07-05T08:27:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"62tiqdXHaPvT/7TgHSUBboF/Tm5rb/mqqt4jA5esQ5B9ugn9di++C9vgCjpfbt9I8JhIn4F3/HjeKqaPx/fCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:24:42.821363Z"},"content_sha256":"7450821b8124ad354d3a4afd09c43051aa8062f9cef050ae072580e405de6a63","schema_version":"1.0","event_id":"sha256:7450821b8124ad354d3a4afd09c43051aa8062f9cef050ae072580e405de6a63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KBID3T6KGA6NK4TQKA76W7RSG6/bundle.json","state_url":"https://pith.science/pith/KBID3T6KGA6NK4TQKA76W7RSG6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KBID3T6KGA6NK4TQKA76W7RSG6/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":"2026-08-18T02:24:42Z","links":{"resolver":"https://pith.science/pith/KBID3T6KGA6NK4TQKA76W7RSG6","bundle":"https://pith.science/pith/KBID3T6KGA6NK4TQKA76W7RSG6/bundle.json","state":"https://pith.science/pith/KBID3T6KGA6NK4TQKA76W7RSG6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KBID3T6KGA6NK4TQKA76W7RSG6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KBID3T6KGA6NK4TQKA76W7RSG6","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":"4464a54e4ba4d0f10d1b182ed08ccecc3d9718e83c0c38aeecc6e94bca98815e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T02:25:10Z","title_canon_sha256":"224101ace06b3cbf459621dd8f54b9fc58cf0a984c94ebc63efe375cfd23ef5f"},"schema_version":"1.0","source":{"id":"2406.02863","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02863","created_at":"2026-07-05T08:27:31Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02863v1","created_at":"2026-07-05T08:27:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02863","created_at":"2026-07-05T08:27:31Z"},{"alias_kind":"pith_short_12","alias_value":"KBID3T6KGA6N","created_at":"2026-07-05T08:27:31Z"},{"alias_kind":"pith_short_16","alias_value":"KBID3T6KGA6NK4TQ","created_at":"2026-07-05T08:27:31Z"},{"alias_kind":"pith_short_8","alias_value":"KBID3T6K","created_at":"2026-07-05T08:27:31Z"}],"graph_snapshots":[{"event_id":"sha256:7450821b8124ad354d3a4afd09c43051aa8062f9cef050ae072580e405de6a63","target":"graph","created_at":"2026-07-05T08:27:31Z","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/2406.02863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This research investigates the effect of prompt design on dialogue evaluation using large language models (LLMs). While LLMs are increasingly used for scoring various inputs, creating effective prompts for dialogue evaluation remains challenging due to model sensitivity and subjectivity in dialogue assessments. Our study experimented with different prompt structures, altering the sequence of output instructions and including explanatory reasons. We found that the order of presenting reasons and scores significantly influences LLMs' scoring, with a \"reason-first\" approach yielding more comprehe","authors_text":"Hideki Nakayama, KuanChao Chu, Yi-Pei Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T02:25:10Z","title":"LLM as a Scorer: The Impact of Output Order on Dialogue Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02863","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":"sha256:79805da04fe6c018ffe2265f9be11a3a02db13862bd1433d6222704db652d0f3","target":"record","created_at":"2026-07-05T08:27:31Z","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":"4464a54e4ba4d0f10d1b182ed08ccecc3d9718e83c0c38aeecc6e94bca98815e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T02:25:10Z","title_canon_sha256":"224101ace06b3cbf459621dd8f54b9fc58cf0a984c94ebc63efe375cfd23ef5f"},"schema_version":"1.0","source":{"id":"2406.02863","kind":"arxiv","version":1}},"canonical_sha256":"50503dcfca303cd57270503feb7e32378213d72a910aacce1fa1f581a8bdf162","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50503dcfca303cd57270503feb7e32378213d72a910aacce1fa1f581a8bdf162","first_computed_at":"2026-07-05T08:27:31.410113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:31.410113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VPpcZ4O1PoUeR/MCDZNaimQlzA+61oTFs/zLvyCi8jWx6FP9izpL6NdiYQ/nORuhPFOse1eXbm++VAPKdJBrDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:31.410626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02863","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79805da04fe6c018ffe2265f9be11a3a02db13862bd1433d6222704db652d0f3","sha256:7450821b8124ad354d3a4afd09c43051aa8062f9cef050ae072580e405de6a63"],"state_sha256":"ceaa65affedf2e5630286a77a071b11420dd6436ec4c2e35d0225f32a9bf24ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o8mFrhi4I3Q9iIGyY0TfOEXW1/EZr7hdr0WDeP1KHivOYET612wN5QZq3RXhjyUpbCdKvAXnw9tq75UvX/k7DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T02:24:42.825871Z","bundle_sha256":"997f29d38ae8ce64bf1cb84fa242fd029233a5fe53baa0edd701e4f2934175fd"}}