{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QPX2MLIAPTE5PQWL3GOGRAK3EX","short_pith_number":"pith:QPX2MLIA","schema_version":"1.0","canonical_sha256":"83efa62d007cc9d7c2cbd99c68815b25dce33a93764ad4ecad94dd3354d8199f","source":{"kind":"arxiv","id":"2109.05281","version":1},"attestation_state":"computed","paper":{"title":"COSMic: A Coherence-Aware Generation Metric for Image Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Baber Khalid, Malihe Alikhani, Matthew Stone, Mert \\.Inan, Piyush Sharma, Radu Soricut","submitted_at":"2021-09-11T13:43:36Z","abstract_excerpt":"Developers of text generation models rely on automated evaluation metrics as a stand-in for slow and expensive manual evaluations. However, image captioning metrics have struggled to give accurate learned estimates of the semantic and pragmatic success of output text. We address this weakness by introducing the first discourse-aware learned generation metric for evaluating image descriptions. Our approach is inspired by computational theories of discourse for capturing information goals using coherence. We present a dataset of image$\\unicode{x2013}$description pairs annotated with coherence re"},"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":"2109.05281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-11T13:43:36Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"366f3365861b5dfb95e972cbd897f0ed97ef28e99bdd80930d02ca1f85bc766b","abstract_canon_sha256":"d864622aa48736290025902c5729d2de97b8d1d6a51c9854be6016592a896642"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:16.861746Z","signature_b64":"ASTx8yQ2AbILIjjJWm4caIwC7Dwv0Ha4FQLQkJjmzRBrjUT4BDCMzoi4bSITlTlgTU5z3WiCp8SqBxMVmgrZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83efa62d007cc9d7c2cbd99c68815b25dce33a93764ad4ecad94dd3354d8199f","last_reissued_at":"2026-07-05T04:06:16.861198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:16.861198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COSMic: A Coherence-Aware Generation Metric for Image Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Baber Khalid, Malihe Alikhani, Matthew Stone, Mert \\.Inan, Piyush Sharma, Radu Soricut","submitted_at":"2021-09-11T13:43:36Z","abstract_excerpt":"Developers of text generation models rely on automated evaluation metrics as a stand-in for slow and expensive manual evaluations. However, image captioning metrics have struggled to give accurate learned estimates of the semantic and pragmatic success of output text. We address this weakness by introducing the first discourse-aware learned generation metric for evaluating image descriptions. Our approach is inspired by computational theories of discourse for capturing information goals using coherence. We present a dataset of image$\\unicode{x2013}$description pairs annotated with coherence re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05281","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/2109.05281/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":"2109.05281","created_at":"2026-07-05T04:06:16.861255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05281v1","created_at":"2026-07-05T04:06:16.861255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05281","created_at":"2026-07-05T04:06:16.861255+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPX2MLIAPTE5","created_at":"2026-07-05T04:06:16.861255+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPX2MLIAPTE5PQWL","created_at":"2026-07-05T04:06:16.861255+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPX2MLIA","created_at":"2026-07-05T04:06:16.861255+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/QPX2MLIAPTE5PQWL3GOGRAK3EX","json":"https://pith.science/pith/QPX2MLIAPTE5PQWL3GOGRAK3EX.json","graph_json":"https://pith.science/api/pith-number/QPX2MLIAPTE5PQWL3GOGRAK3EX/graph.json","events_json":"https://pith.science/api/pith-number/QPX2MLIAPTE5PQWL3GOGRAK3EX/events.json","paper":"https://pith.science/paper/QPX2MLIA"},"agent_actions":{"view_html":"https://pith.science/pith/QPX2MLIAPTE5PQWL3GOGRAK3EX","download_json":"https://pith.science/pith/QPX2MLIAPTE5PQWL3GOGRAK3EX.json","view_paper":"https://pith.science/paper/QPX2MLIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05281&json=true","fetch_graph":"https://pith.science/api/pith-number/QPX2MLIAPTE5PQWL3GOGRAK3EX/graph.json","fetch_events":"https://pith.science/api/pith-number/QPX2MLIAPTE5PQWL3GOGRAK3EX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPX2MLIAPTE5PQWL3GOGRAK3EX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPX2MLIAPTE5PQWL3GOGRAK3EX/action/storage_attestation","attest_author":"https://pith.science/pith/QPX2MLIAPTE5PQWL3GOGRAK3EX/action/author_attestation","sign_citation":"https://pith.science/pith/QPX2MLIAPTE5PQWL3GOGRAK3EX/action/citation_signature","submit_replication":"https://pith.science/pith/QPX2MLIAPTE5PQWL3GOGRAK3EX/action/replication_record"}},"created_at":"2026-07-05T04:06:16.861255+00:00","updated_at":"2026-07-05T04:06:16.861255+00:00"}