{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZQ6WARDJMC6JAYOB4BQLTSGMKO","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":"b3df3f6d6fe0579aaa03fdb6714cd78b5d819a772a11208b71dc2be460262017","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-14T13:58:53Z","title_canon_sha256":"b4c4ce38c4b05662046a5ca3a759576aff6801955d70aa5cb99c14e026d7ecc5"},"schema_version":"1.0","source":{"id":"2010.07100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.07100","created_at":"2026-07-05T01:43:02Z"},{"alias_kind":"arxiv_version","alias_value":"2010.07100v1","created_at":"2026-07-05T01:43:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07100","created_at":"2026-07-05T01:43:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZQ6WARDJMC6J","created_at":"2026-07-05T01:43:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZQ6WARDJMC6JAYOB","created_at":"2026-07-05T01:43:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZQ6WARDJ","created_at":"2026-07-05T01:43:02Z"}],"graph_snapshots":[{"event_id":"sha256:7f43f482cb061ae357c5194696e37ab5f1c0cceec6a7a999888f9a3d6b9a3ebf","target":"graph","created_at":"2026-07-05T01:43:02Z","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/2010.07100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated evaluation metrics as a stand-in for manual evaluation are an essential part of the development of text-generation tasks such as text summarization. However, while the field has progressed, our standard metrics have not -- for nearly 20 years ROUGE has been the standard evaluation in most summarization papers. In this paper, we make an attempt to re-evaluate the evaluation method for text summarization: assessing the reliability of automatic metrics using top-scoring system outputs, both abstractive and extractive, on recently popular datasets for both system-level and summary-level ","authors_text":"Atabak Ashfaq, Graham Neubig, Manik Bhandari, Pengfei Liu, Pranav Gour","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-14T13:58:53Z","title":"Re-evaluating Evaluation in Text Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07100","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":"sha256:5bb064006909612b21fdb1ea37530e0e7b635b628a3ab586f5d55c6ca043332f","target":"record","created_at":"2026-07-05T01:43:02Z","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":"b3df3f6d6fe0579aaa03fdb6714cd78b5d819a772a11208b71dc2be460262017","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-14T13:58:53Z","title_canon_sha256":"b4c4ce38c4b05662046a5ca3a759576aff6801955d70aa5cb99c14e026d7ecc5"},"schema_version":"1.0","source":{"id":"2010.07100","kind":"arxiv","version":1}},"canonical_sha256":"cc3d60446960bc9061c1e060b9c8cc5393eaf9594818b558fa51f01ff0628934","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc3d60446960bc9061c1e060b9c8cc5393eaf9594818b558fa51f01ff0628934","first_computed_at":"2026-07-05T01:43:02.761639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:02.761639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+ZXCCbot7AifAbzr2RFguUjdEUTDpIwChdh7c/+oBmvyN5QvNUadNaHw206cHZJaQ1/oISA7Vup/HEITf8pBCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:02.762101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.07100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bb064006909612b21fdb1ea37530e0e7b635b628a3ab586f5d55c6ca043332f","sha256:7f43f482cb061ae357c5194696e37ab5f1c0cceec6a7a999888f9a3d6b9a3ebf"],"state_sha256":"d11fd0b259ef5c093f32f1b6d6fbb201754df7e682f9f504e18f0ba48f2f5e81"}