{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KDT2JVF6NSMM5I3OOKTF5BH6CS","short_pith_number":"pith:KDT2JVF6","schema_version":"1.0","canonical_sha256":"50e7a4d4be6c98cea36e72a65e84fe14997b13086f1d3b353e6fbe8d24f11c3c","source":{"kind":"arxiv","id":"1909.05424","version":1},"attestation_state":"computed","paper":{"title":"VizSeq: A Visual Analysis Toolkit for Text Generation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anirudh Jain, Changhan Wang, Danlu Chen, Jiatao Gu","submitted_at":"2019-09-12T01:16:27Z","abstract_excerpt":"Automatic evaluation of text generation tasks (e.g. machine translation, text summarization, image captioning and video description) usually relies heavily on task-specific metrics, such as BLEU and ROUGE. They, however, are abstract numbers and are not perfectly aligned with human assessment. This suggests inspecting detailed examples as a complement to identify system error patterns. In this paper, we present VizSeq, a visual analysis toolkit for instance-level and corpus-level system evaluation on a wide variety of text generation tasks. It supports multimodal sources and multiple text refe"},"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":"1909.05424","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-12T01:16:27Z","cross_cats_sorted":[],"title_canon_sha256":"d865afaa087b5819c154b998a216ff2cfc4f933fc32646f4b66b34a7fdfb47c3","abstract_canon_sha256":"fa8a413612b850df1bc8eb8863e4a9f8b89a341d2e95e98337d879b8d3975d70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:09.740639Z","signature_b64":"ZPl0lepXDB1uv693sVzH2osp/KrdHHuFgMiLuoh4lCsh4wFz4/v9Y5SuOGIk4POEUWq9FqlSwa3uWL6icK+DDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50e7a4d4be6c98cea36e72a65e84fe14997b13086f1d3b353e6fbe8d24f11c3c","last_reissued_at":"2026-07-05T00:24:09.740222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:09.740222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VizSeq: A Visual Analysis Toolkit for Text Generation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anirudh Jain, Changhan Wang, Danlu Chen, Jiatao Gu","submitted_at":"2019-09-12T01:16:27Z","abstract_excerpt":"Automatic evaluation of text generation tasks (e.g. machine translation, text summarization, image captioning and video description) usually relies heavily on task-specific metrics, such as BLEU and ROUGE. They, however, are abstract numbers and are not perfectly aligned with human assessment. This suggests inspecting detailed examples as a complement to identify system error patterns. In this paper, we present VizSeq, a visual analysis toolkit for instance-level and corpus-level system evaluation on a wide variety of text generation tasks. It supports multimodal sources and multiple text refe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.05424","kind":"arxiv","version":1},"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/1909.05424/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":"1909.05424","created_at":"2026-07-05T00:24:09.740283+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.05424v1","created_at":"2026-07-05T00:24:09.740283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.05424","created_at":"2026-07-05T00:24:09.740283+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDT2JVF6NSMM","created_at":"2026-07-05T00:24:09.740283+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDT2JVF6NSMM5I3O","created_at":"2026-07-05T00:24:09.740283+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDT2JVF6","created_at":"2026-07-05T00:24:09.740283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KDT2JVF6NSMM5I3OOKTF5BH6CS","json":"https://pith.science/pith/KDT2JVF6NSMM5I3OOKTF5BH6CS.json","graph_json":"https://pith.science/api/pith-number/KDT2JVF6NSMM5I3OOKTF5BH6CS/graph.json","events_json":"https://pith.science/api/pith-number/KDT2JVF6NSMM5I3OOKTF5BH6CS/events.json","paper":"https://pith.science/paper/KDT2JVF6"},"agent_actions":{"view_html":"https://pith.science/pith/KDT2JVF6NSMM5I3OOKTF5BH6CS","download_json":"https://pith.science/pith/KDT2JVF6NSMM5I3OOKTF5BH6CS.json","view_paper":"https://pith.science/paper/KDT2JVF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.05424&json=true","fetch_graph":"https://pith.science/api/pith-number/KDT2JVF6NSMM5I3OOKTF5BH6CS/graph.json","fetch_events":"https://pith.science/api/pith-number/KDT2JVF6NSMM5I3OOKTF5BH6CS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDT2JVF6NSMM5I3OOKTF5BH6CS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDT2JVF6NSMM5I3OOKTF5BH6CS/action/storage_attestation","attest_author":"https://pith.science/pith/KDT2JVF6NSMM5I3OOKTF5BH6CS/action/author_attestation","sign_citation":"https://pith.science/pith/KDT2JVF6NSMM5I3OOKTF5BH6CS/action/citation_signature","submit_replication":"https://pith.science/pith/KDT2JVF6NSMM5I3OOKTF5BH6CS/action/replication_record"}},"created_at":"2026-07-05T00:24:09.740283+00:00","updated_at":"2026-07-05T00:24:09.740283+00:00"}