{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y3KXLAR5K5K7NPI7ZFYF3O4NZA","short_pith_number":"pith:Y3KXLAR5","canonical_record":{"source":{"id":"2406.18528","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T17:56:29Z","cross_cats_sorted":[],"title_canon_sha256":"8e7732b1eb3324aeacd9b307d4cadf80e26304bbef73a09b1d91906c3c0c5ed8","abstract_canon_sha256":"c68471fe2c40cf8240aafebc69bcaf50e19d87c01a74ebd4497a72dcca741847"},"schema_version":"1.0"},"canonical_sha256":"c6d575823d5755f6bd1fc9705dbb8dc8261c13d731f6debd861bcf1275b8d2c1","source":{"kind":"arxiv","id":"2406.18528","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18528","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18528v2","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18528","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_12","alias_value":"Y3KXLAR5K5K7","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_16","alias_value":"Y3KXLAR5K5K7NPI7","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_8","alias_value":"Y3KXLAR5","created_at":"2026-07-05T09:36:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y3KXLAR5K5K7NPI7ZFYF3O4NZA","target":"record","payload":{"canonical_record":{"source":{"id":"2406.18528","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T17:56:29Z","cross_cats_sorted":[],"title_canon_sha256":"8e7732b1eb3324aeacd9b307d4cadf80e26304bbef73a09b1d91906c3c0c5ed8","abstract_canon_sha256":"c68471fe2c40cf8240aafebc69bcaf50e19d87c01a74ebd4497a72dcca741847"},"schema_version":"1.0"},"canonical_sha256":"c6d575823d5755f6bd1fc9705dbb8dc8261c13d731f6debd861bcf1275b8d2c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:12.819489Z","signature_b64":"tp/xItow+3CC9vFwCDpJ/y9sYnt2gYLIVkDMPeItFfLsx7wFRik4u0UnKzvqYbmNBAFtBnaBC9ZlLsO3TMrpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6d575823d5755f6bd1fc9705dbb8dc8261c13d731f6debd861bcf1275b8d2c1","last_reissued_at":"2026-07-05T09:36:12.819021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:12.819021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.18528","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":"2026-07-05T09:36:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q2AORKUektT6Wxj15b+A+qKz/JnY+vq2Jv/r/FqjnJFKtR8hfPxzyoqusmhtiDq7i9h+SsEM7IGDk/PfetuEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:14:56.526069Z"},"content_sha256":"ed73a8d32718b14ca7af50b01d56b6c754c4592b1283d04e8aa388ccccd2a441","schema_version":"1.0","event_id":"sha256:ed73a8d32718b14ca7af50b01d56b6c754c4592b1283d04e8aa388ccccd2a441"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y3KXLAR5K5K7NPI7ZFYF3O4NZA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PrExMe! Large Scale Prompt Exploration of Open Source LLMs for Machine Translation and Summarization Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christoph Leiter, Steffen Eger","submitted_at":"2024-06-26T17:56:29Z","abstract_excerpt":"Large language models (LLMs) have revolutionized NLP research. Notably, in-context learning enables their use as evaluation metrics for natural language generation, making them particularly advantageous in low-resource scenarios and time-restricted applications. In this work, we introduce PrExMe, a large-scale Prompt Exploration for Metrics, where we evaluate more than 720 prompt templates for open-source LLM-based metrics on machine translation (MT) and summarization datasets, totalling over 6.6M evaluations. This extensive comparison (1) benchmarks recent open-source LLMs as metrics and (2) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18528","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/2406.18528/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":"2026-07-05T09:36:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jd/9qsQpm4wDxZsWrDIJmuqhQTRStUxnKIIWd4etnUtw9gQ34hEZ7+dSNAxbVHI7SNXJAd4UblvJx56nImgKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:14:56.526593Z"},"content_sha256":"cd3e686d0d4cee9e9a077399077e206d425df86b710caa135ccb6d948cc02727","schema_version":"1.0","event_id":"sha256:cd3e686d0d4cee9e9a077399077e206d425df86b710caa135ccb6d948cc02727"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y3KXLAR5K5K7NPI7ZFYF3O4NZA/bundle.json","state_url":"https://pith.science/pith/Y3KXLAR5K5K7NPI7ZFYF3O4NZA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y3KXLAR5K5K7NPI7ZFYF3O4NZA/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":"2026-08-13T08:14:56Z","links":{"resolver":"https://pith.science/pith/Y3KXLAR5K5K7NPI7ZFYF3O4NZA","bundle":"https://pith.science/pith/Y3KXLAR5K5K7NPI7ZFYF3O4NZA/bundle.json","state":"https://pith.science/pith/Y3KXLAR5K5K7NPI7ZFYF3O4NZA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y3KXLAR5K5K7NPI7ZFYF3O4NZA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y3KXLAR5K5K7NPI7ZFYF3O4NZA","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":"c68471fe2c40cf8240aafebc69bcaf50e19d87c01a74ebd4497a72dcca741847","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T17:56:29Z","title_canon_sha256":"8e7732b1eb3324aeacd9b307d4cadf80e26304bbef73a09b1d91906c3c0c5ed8"},"schema_version":"1.0","source":{"id":"2406.18528","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18528","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18528v2","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18528","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_12","alias_value":"Y3KXLAR5K5K7","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_16","alias_value":"Y3KXLAR5K5K7NPI7","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_8","alias_value":"Y3KXLAR5","created_at":"2026-07-05T09:36:12Z"}],"graph_snapshots":[{"event_id":"sha256:cd3e686d0d4cee9e9a077399077e206d425df86b710caa135ccb6d948cc02727","target":"graph","created_at":"2026-07-05T09:36:12Z","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/2406.18528/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have revolutionized NLP research. Notably, in-context learning enables their use as evaluation metrics for natural language generation, making them particularly advantageous in low-resource scenarios and time-restricted applications. In this work, we introduce PrExMe, a large-scale Prompt Exploration for Metrics, where we evaluate more than 720 prompt templates for open-source LLM-based metrics on machine translation (MT) and summarization datasets, totalling over 6.6M evaluations. This extensive comparison (1) benchmarks recent open-source LLMs as metrics and (2) ","authors_text":"Christoph Leiter, Steffen Eger","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T17:56:29Z","title":"PrExMe! Large Scale Prompt Exploration of Open Source LLMs for Machine Translation and Summarization Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18528","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:ed73a8d32718b14ca7af50b01d56b6c754c4592b1283d04e8aa388ccccd2a441","target":"record","created_at":"2026-07-05T09:36:12Z","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":"c68471fe2c40cf8240aafebc69bcaf50e19d87c01a74ebd4497a72dcca741847","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T17:56:29Z","title_canon_sha256":"8e7732b1eb3324aeacd9b307d4cadf80e26304bbef73a09b1d91906c3c0c5ed8"},"schema_version":"1.0","source":{"id":"2406.18528","kind":"arxiv","version":2}},"canonical_sha256":"c6d575823d5755f6bd1fc9705dbb8dc8261c13d731f6debd861bcf1275b8d2c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6d575823d5755f6bd1fc9705dbb8dc8261c13d731f6debd861bcf1275b8d2c1","first_computed_at":"2026-07-05T09:36:12.819021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:12.819021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tp/xItow+3CC9vFwCDpJ/y9sYnt2gYLIVkDMPeItFfLsx7wFRik4u0UnKzvqYbmNBAFtBnaBC9ZlLsO3TMrpBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:12.819489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.18528","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed73a8d32718b14ca7af50b01d56b6c754c4592b1283d04e8aa388ccccd2a441","sha256:cd3e686d0d4cee9e9a077399077e206d425df86b710caa135ccb6d948cc02727"],"state_sha256":"37a93684bfd2c4bd162a2a3cc9a463e168a85168394c36f68bc0c2fba7f28b99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m951+NNQIHxnt2+psc4JsTShNR2yKWNILD1asjBljpVjff9zEPkBvi/qk/sotKve9UktfkGbdd9WI3+VJon6DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T08:14:56.531413Z","bundle_sha256":"991e6ced57a2b2c975d810c687c28b63a03b4ee88d2cf1e2ae05056cb22c07c8"}}