{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:J4Q7LJHZI53MWJPD7VVBPQLFDS","short_pith_number":"pith:J4Q7LJHZ","schema_version":"1.0","canonical_sha256":"4f21f5a4f94776cb25e3fd6a17c1651caed37ba04919a3d150b8879d6d946a5f","source":{"kind":"arxiv","id":"1909.02622","version":2},"attestation_state":"computed","paper":{"title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian M. Meyer, Fei Liu, Maxime Peyrard, Steffen Eger, Wei Zhao, Yang Gao","submitted_at":"2019-09-05T20:26:44Z","abstract_excerpt":"A robust evaluation metric has a profound impact on the development of text generation systems. A desirable metric compares system output against references based on their semantics rather than surface forms. In this paper we investigate strategies to encode system and reference texts to devise a metric that shows a high correlation with human judgment of text quality. We validate our new metric, namely MoverScore, on a number of text generation tasks including summarization, machine translation, image captioning, and data-to-text generation, where the outputs are produced by a variety of neur"},"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":"1909.02622","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-05T20:26:44Z","cross_cats_sorted":[],"title_canon_sha256":"e026a458670104b5119439203381a2cc3c19b96cce6b821cfbe8b87531cffa43","abstract_canon_sha256":"8553c8b705cec7008eda8af5e31856f5a69cbdd55d9ea81e7917d3d2b2e5ed03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:24.728888Z","signature_b64":"6yudkQcvbGoASQC6DaKocGO7f35gnv3SRf1613hWtaMDg1Qlje4IJqkwA7P1OVgSXubcFaw8fyPvNDEyI4fACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f21f5a4f94776cb25e3fd6a17c1651caed37ba04919a3d150b8879d6d946a5f","last_reissued_at":"2026-07-05T00:07:24.728390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:24.728390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian M. Meyer, Fei Liu, Maxime Peyrard, Steffen Eger, Wei Zhao, Yang Gao","submitted_at":"2019-09-05T20:26:44Z","abstract_excerpt":"A robust evaluation metric has a profound impact on the development of text generation systems. A desirable metric compares system output against references based on their semantics rather than surface forms. In this paper we investigate strategies to encode system and reference texts to devise a metric that shows a high correlation with human judgment of text quality. We validate our new metric, namely MoverScore, on a number of text generation tasks including summarization, machine translation, image captioning, and data-to-text generation, where the outputs are produced by a variety of neur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02622","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/1909.02622/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":"1909.02622","created_at":"2026-07-05T00:07:24.728453+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.02622v2","created_at":"2026-07-05T00:07:24.728453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02622","created_at":"2026-07-05T00:07:24.728453+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4Q7LJHZI53M","created_at":"2026-07-05T00:07:24.728453+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4Q7LJHZI53MWJPD","created_at":"2026-07-05T00:07:24.728453+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4Q7LJHZ","created_at":"2026-07-05T00:07:24.728453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.07201","citing_title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20878","citing_title":"AITP: Traffic Accident Responsibility Allocation via Multimodal Large Language Models","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J4Q7LJHZI53MWJPD7VVBPQLFDS","json":"https://pith.science/pith/J4Q7LJHZI53MWJPD7VVBPQLFDS.json","graph_json":"https://pith.science/api/pith-number/J4Q7LJHZI53MWJPD7VVBPQLFDS/graph.json","events_json":"https://pith.science/api/pith-number/J4Q7LJHZI53MWJPD7VVBPQLFDS/events.json","paper":"https://pith.science/paper/J4Q7LJHZ"},"agent_actions":{"view_html":"https://pith.science/pith/J4Q7LJHZI53MWJPD7VVBPQLFDS","download_json":"https://pith.science/pith/J4Q7LJHZI53MWJPD7VVBPQLFDS.json","view_paper":"https://pith.science/paper/J4Q7LJHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.02622&json=true","fetch_graph":"https://pith.science/api/pith-number/J4Q7LJHZI53MWJPD7VVBPQLFDS/graph.json","fetch_events":"https://pith.science/api/pith-number/J4Q7LJHZI53MWJPD7VVBPQLFDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4Q7LJHZI53MWJPD7VVBPQLFDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4Q7LJHZI53MWJPD7VVBPQLFDS/action/storage_attestation","attest_author":"https://pith.science/pith/J4Q7LJHZI53MWJPD7VVBPQLFDS/action/author_attestation","sign_citation":"https://pith.science/pith/J4Q7LJHZI53MWJPD7VVBPQLFDS/action/citation_signature","submit_replication":"https://pith.science/pith/J4Q7LJHZI53MWJPD7VVBPQLFDS/action/replication_record"}},"created_at":"2026-07-05T00:07:24.728453+00:00","updated_at":"2026-07-05T00:07:24.728453+00:00"}