{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MLOZBVTB6DDHEUC2SM26NDAI5U","short_pith_number":"pith:MLOZBVTB","canonical_record":{"source":{"id":"1806.06422","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-17T17:57:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"40d821a16c14640f82e84a3834e38b48be36662f22662a31234f4d1397252a41","abstract_canon_sha256":"63b39068ccd3bb6238e9ebc5a0683b210db936f68a181ec05241aaf7f38aed6a"},"schema_version":"1.0"},"canonical_sha256":"62dd90d661f0c672505a9335e68c08ed0cd28b75bab3007853bca5fb4b8ace7d","source":{"kind":"arxiv","id":"1806.06422","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06422","created_at":"2026-05-18T00:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06422v1","created_at":"2026-05-18T00:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06422","created_at":"2026-05-18T00:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"MLOZBVTB6DDH","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MLOZBVTB6DDHEUC2","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MLOZBVTB","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MLOZBVTB6DDHEUC2SM26NDAI5U","target":"record","payload":{"canonical_record":{"source":{"id":"1806.06422","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-17T17:57:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"40d821a16c14640f82e84a3834e38b48be36662f22662a31234f4d1397252a41","abstract_canon_sha256":"63b39068ccd3bb6238e9ebc5a0683b210db936f68a181ec05241aaf7f38aed6a"},"schema_version":"1.0"},"canonical_sha256":"62dd90d661f0c672505a9335e68c08ed0cd28b75bab3007853bca5fb4b8ace7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:02.474080Z","signature_b64":"oyn3gaSLW0pshhdYos8aylHHGA9C7pWm3nP8PaIerEoGZJ1Wl6caTCEao+WBQfaDWzD54g7jpw6+O31886NQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62dd90d661f0c672505a9335e68c08ed0cd28b75bab3007853bca5fb4b8ace7d","last_reissued_at":"2026-05-18T00:13:02.473412Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:02.473412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.06422","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qBfbOOsK/Hw3GUmasWEr9RE+hvISjQ2TBThW8b+zxAqYFFYku+wKiQhlZmDjFGi8hQc4a0rNIQdexLWwysMxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:21:41.594003Z"},"content_sha256":"76afa3e446f1165cec314e8f96823467cc690a67403430443dc2808be3515762","schema_version":"1.0","event_id":"sha256:76afa3e446f1165cec314e8f96823467cc690a67403430443dc2808be3515762"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MLOZBVTB6DDHEUC2SM26NDAI5U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Evaluate Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andreas Veit, Guandao Yang, Serge Belongie, Xun Huang, Yin Cui","submitted_at":"2018-06-17T17:57:32Z","abstract_excerpt":"Evaluation metrics for image captioning face two challenges. Firstly, commonly used metrics such as CIDEr, METEOR, ROUGE and BLEU often do not correlate well with human judgments. Secondly, each metric has well known blind spots to pathological caption constructions, and rule-based metrics lack provisions to repair such blind spots once identified. For example, the newly proposed SPICE correlates well with human judgments, but fails to capture the syntactic structure of a sentence. To address these two challenges, we propose a novel learning based discriminative evaluation metric that is direc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06422","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1YilNP8WbLwROvIs6LI7tfVueS593g+5+Qm02gbJTdWpEIhrpMftq5Fn6RuDTk6d543IdKKywhEQlHMvs3QkAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:21:41.594586Z"},"content_sha256":"b0a47c2f1181becd9053e21f874a739a88860a1c4da73037327c04fe53fb663f","schema_version":"1.0","event_id":"sha256:b0a47c2f1181becd9053e21f874a739a88860a1c4da73037327c04fe53fb663f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MLOZBVTB6DDHEUC2SM26NDAI5U/bundle.json","state_url":"https://pith.science/pith/MLOZBVTB6DDHEUC2SM26NDAI5U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MLOZBVTB6DDHEUC2SM26NDAI5U/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-07T06:21:41Z","links":{"resolver":"https://pith.science/pith/MLOZBVTB6DDHEUC2SM26NDAI5U","bundle":"https://pith.science/pith/MLOZBVTB6DDHEUC2SM26NDAI5U/bundle.json","state":"https://pith.science/pith/MLOZBVTB6DDHEUC2SM26NDAI5U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MLOZBVTB6DDHEUC2SM26NDAI5U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MLOZBVTB6DDHEUC2SM26NDAI5U","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":"63b39068ccd3bb6238e9ebc5a0683b210db936f68a181ec05241aaf7f38aed6a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-17T17:57:32Z","title_canon_sha256":"40d821a16c14640f82e84a3834e38b48be36662f22662a31234f4d1397252a41"},"schema_version":"1.0","source":{"id":"1806.06422","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06422","created_at":"2026-05-18T00:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06422v1","created_at":"2026-05-18T00:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06422","created_at":"2026-05-18T00:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"MLOZBVTB6DDH","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MLOZBVTB6DDHEUC2","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MLOZBVTB","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:b0a47c2f1181becd9053e21f874a739a88860a1c4da73037327c04fe53fb663f","target":"graph","created_at":"2026-05-18T00:13:02Z","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"},"paper":{"abstract_excerpt":"Evaluation metrics for image captioning face two challenges. Firstly, commonly used metrics such as CIDEr, METEOR, ROUGE and BLEU often do not correlate well with human judgments. Secondly, each metric has well known blind spots to pathological caption constructions, and rule-based metrics lack provisions to repair such blind spots once identified. For example, the newly proposed SPICE correlates well with human judgments, but fails to capture the syntactic structure of a sentence. To address these two challenges, we propose a novel learning based discriminative evaluation metric that is direc","authors_text":"Andreas Veit, Guandao Yang, Serge Belongie, Xun Huang, Yin Cui","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-17T17:57:32Z","title":"Learning to Evaluate Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06422","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":"sha256:76afa3e446f1165cec314e8f96823467cc690a67403430443dc2808be3515762","target":"record","created_at":"2026-05-18T00:13:02Z","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":"63b39068ccd3bb6238e9ebc5a0683b210db936f68a181ec05241aaf7f38aed6a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-17T17:57:32Z","title_canon_sha256":"40d821a16c14640f82e84a3834e38b48be36662f22662a31234f4d1397252a41"},"schema_version":"1.0","source":{"id":"1806.06422","kind":"arxiv","version":1}},"canonical_sha256":"62dd90d661f0c672505a9335e68c08ed0cd28b75bab3007853bca5fb4b8ace7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62dd90d661f0c672505a9335e68c08ed0cd28b75bab3007853bca5fb4b8ace7d","first_computed_at":"2026-05-18T00:13:02.473412Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:02.473412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oyn3gaSLW0pshhdYos8aylHHGA9C7pWm3nP8PaIerEoGZJ1Wl6caTCEao+WBQfaDWzD54g7jpw6+O31886NQDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:02.474080Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.06422","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76afa3e446f1165cec314e8f96823467cc690a67403430443dc2808be3515762","sha256:b0a47c2f1181becd9053e21f874a739a88860a1c4da73037327c04fe53fb663f"],"state_sha256":"6d81e24f96d00c52a3a0e0c77b96085900af5819f004ccff8aa5f76147fdc06f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J+Ww8Yu0s3F+CaTcGvs/QpBxar2SNq8PUC5kk4ZD5TGakb3bnrUa0xL4EyqLFjzJhxjq3pyXQxgZqcpTdT+7Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T06:21:41.597521Z","bundle_sha256":"9d8bf3a40dcf5be7e7a91b8c410f2063dd9cdfaaa5f85c8af09d5ab8146a951d"}}