{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Y4PNRKIUQ7P3KJRXNPMK6F7SL2","short_pith_number":"pith:Y4PNRKIU","canonical_record":{"source":{"id":"2305.14282","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:27:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85d9824be6e577825dacc7f57f656d18441e618377d1daf2d255e35f3a270859","abstract_canon_sha256":"1313f98538376c866dbaac8e81fd8de7918d0f48adc92331e08c835b250f5f4a"},"schema_version":"1.0"},"canonical_sha256":"c71ed8a91487dfb526376bd8af17f25e8001a856c9935a1dbdbe986fac1b8323","source":{"kind":"arxiv","id":"2305.14282","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14282","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14282v3","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14282","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"Y4PNRKIUQ7P3","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"Y4PNRKIUQ7P3KJRX","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"Y4PNRKIU","created_at":"2026-07-05T07:05:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Y4PNRKIUQ7P3KJRXNPMK6F7SL2","target":"record","payload":{"canonical_record":{"source":{"id":"2305.14282","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:27:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85d9824be6e577825dacc7f57f656d18441e618377d1daf2d255e35f3a270859","abstract_canon_sha256":"1313f98538376c866dbaac8e81fd8de7918d0f48adc92331e08c835b250f5f4a"},"schema_version":"1.0"},"canonical_sha256":"c71ed8a91487dfb526376bd8af17f25e8001a856c9935a1dbdbe986fac1b8323","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:43.373791Z","signature_b64":"3xgDVxlVM9DAtPZBbmEfiFzE7U4KA5JSK5khXFeB13lgDVUmUZ/XTXwl0HE797y5dxwBsgtPTZjSiECuSsBpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c71ed8a91487dfb526376bd8af17f25e8001a856c9935a1dbdbe986fac1b8323","last_reissued_at":"2026-07-05T07:05:43.373292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:43.373292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.14282","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oo04hN/vn+yFTtb4wMIvWP98+dYrhna4yk8cFqt9ZEGAWGYcxkL/yOA6NQa/PimMmL5Y+poBFm49bNeXp9S1Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:15:30.028864Z"},"content_sha256":"71da363eb1e6b8c295ec178b39e18baf651c3419f28177de8b56b15fb3cbadff","schema_version":"1.0","event_id":"sha256:71da363eb1e6b8c295ec178b39e18baf651c3419f28177de8b56b15fb3cbadff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Y4PNRKIUQ7P3KJRXNPMK6F7SL2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Danqing Wang, Lei Li, Liangming Pan, Markus Freitag, Wenda Xu, William Yang Wang, Zhenqiao Song","submitted_at":"2023-05-23T17:27:22Z","abstract_excerpt":"Automatically evaluating the quality of language generation is critical. Although recent learned metrics show high correlation with human judgement, these metrics can not explain their verdict or associate the scores with defects in generated text. To address this limitation, we present InstructScore, an explainable evaluation metric for text generation. By harnessing both explicit human instruction and the implicit knowledge of GPT-4, we fine-tune a text evaluation metric based on LLaMA, producing both a score for generated text and a human readable diagnostic report. We evaluate InstructScor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14282","kind":"arxiv","version":3},"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/2305.14282/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":"2026-07-05T07:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BXGE3QRREN7ZiEgr1XUXKR32u6uiD3EmAo10kGjgmHtReChhxIlMY6HbETcIkZLS7gtFUj/p3V92Xw6i9mCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:15:30.029565Z"},"content_sha256":"bbe56b740e6ee523f469e4b31613115ed55cc0e7af29ded8f1d82be393b03299","schema_version":"1.0","event_id":"sha256:bbe56b740e6ee523f469e4b31613115ed55cc0e7af29ded8f1d82be393b03299"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y4PNRKIUQ7P3KJRXNPMK6F7SL2/bundle.json","state_url":"https://pith.science/pith/Y4PNRKIUQ7P3KJRXNPMK6F7SL2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y4PNRKIUQ7P3KJRXNPMK6F7SL2/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":"2026-08-05T17:15:30Z","links":{"resolver":"https://pith.science/pith/Y4PNRKIUQ7P3KJRXNPMK6F7SL2","bundle":"https://pith.science/pith/Y4PNRKIUQ7P3KJRXNPMK6F7SL2/bundle.json","state":"https://pith.science/pith/Y4PNRKIUQ7P3KJRXNPMK6F7SL2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y4PNRKIUQ7P3KJRXNPMK6F7SL2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y4PNRKIUQ7P3KJRXNPMK6F7SL2","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":"1313f98538376c866dbaac8e81fd8de7918d0f48adc92331e08c835b250f5f4a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:27:22Z","title_canon_sha256":"85d9824be6e577825dacc7f57f656d18441e618377d1daf2d255e35f3a270859"},"schema_version":"1.0","source":{"id":"2305.14282","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14282","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14282v3","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14282","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"Y4PNRKIUQ7P3","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"Y4PNRKIUQ7P3KJRX","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"Y4PNRKIU","created_at":"2026-07-05T07:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:bbe56b740e6ee523f469e4b31613115ed55cc0e7af29ded8f1d82be393b03299","target":"graph","created_at":"2026-07-05T07:05:43Z","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/2305.14282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatically evaluating the quality of language generation is critical. Although recent learned metrics show high correlation with human judgement, these metrics can not explain their verdict or associate the scores with defects in generated text. To address this limitation, we present InstructScore, an explainable evaluation metric for text generation. By harnessing both explicit human instruction and the implicit knowledge of GPT-4, we fine-tune a text evaluation metric based on LLaMA, producing both a score for generated text and a human readable diagnostic report. We evaluate InstructScor","authors_text":"Danqing Wang, Lei Li, Liangming Pan, Markus Freitag, Wenda Xu, William Yang Wang, Zhenqiao Song","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:27:22Z","title":"INSTRUCTSCORE: Explainable Text Generation Evaluation with Finegrained Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14282","kind":"arxiv","version":3},"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":"sha256:71da363eb1e6b8c295ec178b39e18baf651c3419f28177de8b56b15fb3cbadff","target":"record","created_at":"2026-07-05T07:05:43Z","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":"1313f98538376c866dbaac8e81fd8de7918d0f48adc92331e08c835b250f5f4a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:27:22Z","title_canon_sha256":"85d9824be6e577825dacc7f57f656d18441e618377d1daf2d255e35f3a270859"},"schema_version":"1.0","source":{"id":"2305.14282","kind":"arxiv","version":3}},"canonical_sha256":"c71ed8a91487dfb526376bd8af17f25e8001a856c9935a1dbdbe986fac1b8323","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c71ed8a91487dfb526376bd8af17f25e8001a856c9935a1dbdbe986fac1b8323","first_computed_at":"2026-07-05T07:05:43.373292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:43.373292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3xgDVxlVM9DAtPZBbmEfiFzE7U4KA5JSK5khXFeB13lgDVUmUZ/XTXwl0HE797y5dxwBsgtPTZjSiECuSsBpAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:43.373791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14282","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71da363eb1e6b8c295ec178b39e18baf651c3419f28177de8b56b15fb3cbadff","sha256:bbe56b740e6ee523f469e4b31613115ed55cc0e7af29ded8f1d82be393b03299"],"state_sha256":"5eb8bb77ef3a250bb56b29f09186f9cbf3ae2ee97019829ef605d02094a414ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VXtoHvzlruPENLmXSwYlzoulT2RxbnmWE9XpQtH3ePPbPfivnWf/tV3GHaTAOTgCo2aUmjKZ9HbXSXYNh2n5Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:15:30.034928Z","bundle_sha256":"198ff6487294dd0fa8549bbd5a085f932675165110186ff598c5beccea83a7ea"}}