{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HA2DEQCV2LLOBM7Y6ZPHNEEKRL","short_pith_number":"pith:HA2DEQCV","schema_version":"1.0","canonical_sha256":"3834324055d2d6e0b3f8f65e76908a8af6f6038904f88d886d88ce5f54dc1716","source":{"kind":"arxiv","id":"2008.12009","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Evaluation Metrics Used for NLG Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akash Kumar Mohankumar, Ananya B. Sai, Mitesh M. Khapra","submitted_at":"2020-08-27T09:25:05Z","abstract_excerpt":"The success of Deep Learning has created a surge in interest in a wide a range of Natural Language Generation (NLG) tasks. Deep Learning has not only pushed the state of the art in several existing NLG tasks but has also facilitated researchers to explore various newer NLG tasks such as image captioning. Such rapid progress in NLG has necessitated the development of accurate automatic evaluation metrics that would allow us to track the progress in the field of NLG. However, unlike classification tasks, automatically evaluating NLG systems in itself is a huge challenge. Several works have shown"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2008.12009","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-27T09:25:05Z","cross_cats_sorted":[],"title_canon_sha256":"d62a189606ebd8279a03e7cc0a73c2618f1b1f2e32e9d34a91699a7bf1a2a446","abstract_canon_sha256":"92138e30fec281778168479585db1f1814543b9fdf46e2da31989506617638eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:17.440807Z","signature_b64":"hvIEgIbWIt7InA9R1TYboeLZLpMYARwfcOAXfGJET08exmdNbgeFxk/WAyAfJqeTzM0p4WUoJia2FM4M2tLRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3834324055d2d6e0b3f8f65e76908a8af6f6038904f88d886d88ce5f54dc1716","last_reissued_at":"2026-07-05T01:40:17.440399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:17.440399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Evaluation Metrics Used for NLG Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akash Kumar Mohankumar, Ananya B. Sai, Mitesh M. Khapra","submitted_at":"2020-08-27T09:25:05Z","abstract_excerpt":"The success of Deep Learning has created a surge in interest in a wide a range of Natural Language Generation (NLG) tasks. Deep Learning has not only pushed the state of the art in several existing NLG tasks but has also facilitated researchers to explore various newer NLG tasks such as image captioning. Such rapid progress in NLG has necessitated the development of accurate automatic evaluation metrics that would allow us to track the progress in the field of NLG. However, unlike classification tasks, automatically evaluating NLG systems in itself is a huge challenge. Several works have shown"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.12009","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/2008.12009/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2008.12009","created_at":"2026-07-05T01:40:17.440454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.12009v2","created_at":"2026-07-05T01:40:17.440454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.12009","created_at":"2026-07-05T01:40:17.440454+00:00"},{"alias_kind":"pith_short_12","alias_value":"HA2DEQCV2LLO","created_at":"2026-07-05T01:40:17.440454+00:00"},{"alias_kind":"pith_short_16","alias_value":"HA2DEQCV2LLOBM7Y","created_at":"2026-07-05T01:40:17.440454+00:00"},{"alias_kind":"pith_short_8","alias_value":"HA2DEQCV","created_at":"2026-07-05T01:40:17.440454+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07054","citing_title":"Sell More, Play Less: Benchmarking LLM Realistic Selling Skill","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HA2DEQCV2LLOBM7Y6ZPHNEEKRL","json":"https://pith.science/pith/HA2DEQCV2LLOBM7Y6ZPHNEEKRL.json","graph_json":"https://pith.science/api/pith-number/HA2DEQCV2LLOBM7Y6ZPHNEEKRL/graph.json","events_json":"https://pith.science/api/pith-number/HA2DEQCV2LLOBM7Y6ZPHNEEKRL/events.json","paper":"https://pith.science/paper/HA2DEQCV"},"agent_actions":{"view_html":"https://pith.science/pith/HA2DEQCV2LLOBM7Y6ZPHNEEKRL","download_json":"https://pith.science/pith/HA2DEQCV2LLOBM7Y6ZPHNEEKRL.json","view_paper":"https://pith.science/paper/HA2DEQCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.12009&json=true","fetch_graph":"https://pith.science/api/pith-number/HA2DEQCV2LLOBM7Y6ZPHNEEKRL/graph.json","fetch_events":"https://pith.science/api/pith-number/HA2DEQCV2LLOBM7Y6ZPHNEEKRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HA2DEQCV2LLOBM7Y6ZPHNEEKRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HA2DEQCV2LLOBM7Y6ZPHNEEKRL/action/storage_attestation","attest_author":"https://pith.science/pith/HA2DEQCV2LLOBM7Y6ZPHNEEKRL/action/author_attestation","sign_citation":"https://pith.science/pith/HA2DEQCV2LLOBM7Y6ZPHNEEKRL/action/citation_signature","submit_replication":"https://pith.science/pith/HA2DEQCV2LLOBM7Y6ZPHNEEKRL/action/replication_record"}},"created_at":"2026-07-05T01:40:17.440454+00:00","updated_at":"2026-07-05T01:40:17.440454+00:00"}