{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C2OUHYVCYFFCQWVKKTYOSRBBP7","short_pith_number":"pith:C2OUHYVC","canonical_record":{"source":{"id":"2407.14467","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T17:14:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd72144e1eb53f6e76614a98650f4e7f1484b459f3d9c8496679e908c9d77938","abstract_canon_sha256":"d00419b44735045a84638dfa9abdfdc8546c6bce8a074270408a4149164e0e0d"},"schema_version":"1.0"},"canonical_sha256":"169d43e2a2c14a285aaa54f0e944217fddad2ababca8e39af4ecedd24c2004f8","source":{"kind":"arxiv","id":"2407.14467","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.14467","created_at":"2026-07-05T09:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2407.14467v2","created_at":"2026-07-05T09:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14467","created_at":"2026-07-05T09:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"C2OUHYVCYFFC","created_at":"2026-07-05T09:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"C2OUHYVCYFFCQWVK","created_at":"2026-07-05T09:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"C2OUHYVC","created_at":"2026-07-05T09:05:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C2OUHYVCYFFCQWVKKTYOSRBBP7","target":"record","payload":{"canonical_record":{"source":{"id":"2407.14467","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T17:14:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd72144e1eb53f6e76614a98650f4e7f1484b459f3d9c8496679e908c9d77938","abstract_canon_sha256":"d00419b44735045a84638dfa9abdfdc8546c6bce8a074270408a4149164e0e0d"},"schema_version":"1.0"},"canonical_sha256":"169d43e2a2c14a285aaa54f0e944217fddad2ababca8e39af4ecedd24c2004f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:18.039394Z","signature_b64":"0FnXhFGYUV+BqKxP1sHGF69A+iR+M14dOniHOcyRimfRy09w+ou5jncRe+KFWr/wod8Vyv9lant5KP5dbYIdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"169d43e2a2c14a285aaa54f0e944217fddad2ababca8e39af4ecedd24c2004f8","last_reissued_at":"2026-07-05T09:05:18.038938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:18.038938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.14467","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":"2026-07-05T09:05:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ts21YVBnLwSEbu1mupmcRRKbicu5I25U5fBNE7MiklZii8CcGkmkAMChVVb39ZJQyGZmu2ZnuiCxsVLHFtbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:23:07.240648Z"},"content_sha256":"d3ed629897dbcbebbc663783476b51c5c79a2709a420a761de815fcff71c0df9","schema_version":"1.0","event_id":"sha256:d3ed629897dbcbebbc663783476b51c5c79a2709a420a761de815fcff71c0df9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C2OUHYVCYFFCQWVKKTYOSRBBP7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Check-Eval: A Checklist-based Approach for Evaluating Text Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andre Assumpcao, Jayr Pereira, Roberto Lotufo","submitted_at":"2024-07-19T17:14:16Z","abstract_excerpt":"Evaluating the quality of text generated by large language models (LLMs) remains a significant challenge. Traditional metrics often fail to align well with human judgments, particularly in tasks requiring creativity and nuance. In this paper, we propose \\textsc{Check-Eval}, a novel evaluation framework leveraging LLMs to assess the quality of generated text through a checklist-based approach. \\textsc{Check-Eval} can be employed as both a reference-free and reference-dependent evaluation method, providing a structured and interpretable assessment of text quality. The framework consists of two m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14467","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/2407.14467/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":"2026-07-05T09:05:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CsO78MGxMj4+BCm2KWP3b+/D/PRa3a4mtWmLnk7b2HoHLY50lt29Z70CYnsFG8rzKeCqBL1EnOp5zA3MT/W/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:23:07.241166Z"},"content_sha256":"7ad45c29afb0b6c922df700809eda4a3d5e5a69332754ff5305c8d921221f575","schema_version":"1.0","event_id":"sha256:7ad45c29afb0b6c922df700809eda4a3d5e5a69332754ff5305c8d921221f575"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7/bundle.json","state_url":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7/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":"2026-08-09T05:23:07Z","links":{"resolver":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7","bundle":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7/bundle.json","state":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C2OUHYVCYFFCQWVKKTYOSRBBP7","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":"d00419b44735045a84638dfa9abdfdc8546c6bce8a074270408a4149164e0e0d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T17:14:16Z","title_canon_sha256":"cd72144e1eb53f6e76614a98650f4e7f1484b459f3d9c8496679e908c9d77938"},"schema_version":"1.0","source":{"id":"2407.14467","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.14467","created_at":"2026-07-05T09:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2407.14467v2","created_at":"2026-07-05T09:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14467","created_at":"2026-07-05T09:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"C2OUHYVCYFFC","created_at":"2026-07-05T09:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"C2OUHYVCYFFCQWVK","created_at":"2026-07-05T09:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"C2OUHYVC","created_at":"2026-07-05T09:05:18Z"}],"graph_snapshots":[{"event_id":"sha256:7ad45c29afb0b6c922df700809eda4a3d5e5a69332754ff5305c8d921221f575","target":"graph","created_at":"2026-07-05T09:05:18Z","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/2407.14467/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the quality of text generated by large language models (LLMs) remains a significant challenge. Traditional metrics often fail to align well with human judgments, particularly in tasks requiring creativity and nuance. In this paper, we propose \\textsc{Check-Eval}, a novel evaluation framework leveraging LLMs to assess the quality of generated text through a checklist-based approach. \\textsc{Check-Eval} can be employed as both a reference-free and reference-dependent evaluation method, providing a structured and interpretable assessment of text quality. The framework consists of two m","authors_text":"Andre Assumpcao, Jayr Pereira, Roberto Lotufo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T17:14:16Z","title":"Check-Eval: A Checklist-based Approach for Evaluating Text Quality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14467","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:d3ed629897dbcbebbc663783476b51c5c79a2709a420a761de815fcff71c0df9","target":"record","created_at":"2026-07-05T09:05:18Z","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":"d00419b44735045a84638dfa9abdfdc8546c6bce8a074270408a4149164e0e0d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T17:14:16Z","title_canon_sha256":"cd72144e1eb53f6e76614a98650f4e7f1484b459f3d9c8496679e908c9d77938"},"schema_version":"1.0","source":{"id":"2407.14467","kind":"arxiv","version":2}},"canonical_sha256":"169d43e2a2c14a285aaa54f0e944217fddad2ababca8e39af4ecedd24c2004f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"169d43e2a2c14a285aaa54f0e944217fddad2ababca8e39af4ecedd24c2004f8","first_computed_at":"2026-07-05T09:05:18.038938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:05:18.038938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0FnXhFGYUV+BqKxP1sHGF69A+iR+M14dOniHOcyRimfRy09w+ou5jncRe+KFWr/wod8Vyv9lant5KP5dbYIdCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:05:18.039394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.14467","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3ed629897dbcbebbc663783476b51c5c79a2709a420a761de815fcff71c0df9","sha256:7ad45c29afb0b6c922df700809eda4a3d5e5a69332754ff5305c8d921221f575"],"state_sha256":"9e533e8351081e26a545a5b05166412f7d7eddc921bb3f0710ad8d452ccc7470"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M0E9ZUbVDGsh/pTW67cXER504chFGek2W/aeBZtW9t819McFgcfncxN/MfGL3xkzEZbPGJ+o1XjNiFyazW05DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:23:07.247240Z","bundle_sha256":"be41d9f57a928df8baff81baf49a345b643f3b95f0eb9e1dcff9ce5c8301ec8d"}}