{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HAQ6JFBUNVQEBBH5FI55D43H7G","short_pith_number":"pith:HAQ6JFBU","canonical_record":{"source":{"id":"2106.14019","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-26T13:27:14Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"30e7f8bf43737d1b1a38e5fdd3e22dc67677d1bc11c377bd64a4c0e765d0999f","abstract_canon_sha256":"a01e0008e96faaeb63fd53269b13b65edc13f2fdaa4a5075f272eeb8fe78b918"},"schema_version":"1.0"},"canonical_sha256":"3821e494346d604084fd2a3bd1f367f9a7f9ab8869279ced5393f7f9aa791c55","source":{"kind":"arxiv","id":"2106.14019","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.14019","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"arxiv_version","alias_value":"2106.14019v1","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14019","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"pith_short_12","alias_value":"HAQ6JFBUNVQE","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"pith_short_16","alias_value":"HAQ6JFBUNVQEBBH5","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"pith_short_8","alias_value":"HAQ6JFBU","created_at":"2026-07-05T02:52:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HAQ6JFBUNVQEBBH5FI55D43H7G","target":"record","payload":{"canonical_record":{"source":{"id":"2106.14019","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-26T13:27:14Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"30e7f8bf43737d1b1a38e5fdd3e22dc67677d1bc11c377bd64a4c0e765d0999f","abstract_canon_sha256":"a01e0008e96faaeb63fd53269b13b65edc13f2fdaa4a5075f272eeb8fe78b918"},"schema_version":"1.0"},"canonical_sha256":"3821e494346d604084fd2a3bd1f367f9a7f9ab8869279ced5393f7f9aa791c55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:46.555681Z","signature_b64":"pHCpM1yAMJcPmRsQ8DrpP+aqhkOFlvueCkTx30uVpClUC497SIqbjwVICdJQCwlaGV1/dXT2ome2WWK++u51Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3821e494346d604084fd2a3bd1f367f9a7f9ab8869279ced5393f7f9aa791c55","last_reissued_at":"2026-07-05T02:52:46.555156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:46.555156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.14019","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":"2026-07-05T02:52:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g49zKy9VP86jP/g+fM8EL6JRgw2+fHUjDlyFHDVscXMIMzspujfxIVbefZTBbiWpvO2EUZFiGHQc5ssGljiCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:29:40.256146Z"},"content_sha256":"ca38a2d72113aa7a8e900b6849e065840b171be9691e78a070fa443c142de1c0","schema_version":"1.0","event_id":"sha256:ca38a2d72113aa7a8e900b6849e065840b171be9691e78a070fa443c142de1c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HAQ6JFBUNVQEBBH5FI55D43H7G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Franck Dernoncourt, Hwanhee Lee, Kyomin Jung, Seunghyun Yoon, Trung Bui","submitted_at":"2021-06-26T13:27:14Z","abstract_excerpt":"Despite the success of various text generation metrics such as BERTScore, it is still difficult to evaluate the image captions without enough reference captions due to the diversity of the descriptions. In this paper, we introduce a new metric UMIC, an Unreferenced Metric for Image Captioning which does not require reference captions to evaluate image captions. Based on Vision-and-Language BERT, we train UMIC to discriminate negative captions via contrastive learning. Also, we observe critical problems of the previous benchmark dataset (i.e., human annotations) on image captioning metric, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14019","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/2106.14019/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:52:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y9OEewsCGSn8gJtgPABPgaOsDrk63yAYYuKzM0iRCRWhDQVBuCAFNetIECJVdO89/CLJyHntEVmEVLOSzbcjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:29:40.256695Z"},"content_sha256":"26a1daf5c2da89d3522782076a8c9fd09f0dda6174e6cdeff0f7e0896fc03c1f","schema_version":"1.0","event_id":"sha256:26a1daf5c2da89d3522782076a8c9fd09f0dda6174e6cdeff0f7e0896fc03c1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HAQ6JFBUNVQEBBH5FI55D43H7G/bundle.json","state_url":"https://pith.science/pith/HAQ6JFBUNVQEBBH5FI55D43H7G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HAQ6JFBUNVQEBBH5FI55D43H7G/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":"2026-08-20T21:29:40Z","links":{"resolver":"https://pith.science/pith/HAQ6JFBUNVQEBBH5FI55D43H7G","bundle":"https://pith.science/pith/HAQ6JFBUNVQEBBH5FI55D43H7G/bundle.json","state":"https://pith.science/pith/HAQ6JFBUNVQEBBH5FI55D43H7G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HAQ6JFBUNVQEBBH5FI55D43H7G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HAQ6JFBUNVQEBBH5FI55D43H7G","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":"a01e0008e96faaeb63fd53269b13b65edc13f2fdaa4a5075f272eeb8fe78b918","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-26T13:27:14Z","title_canon_sha256":"30e7f8bf43737d1b1a38e5fdd3e22dc67677d1bc11c377bd64a4c0e765d0999f"},"schema_version":"1.0","source":{"id":"2106.14019","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.14019","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"arxiv_version","alias_value":"2106.14019v1","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14019","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"pith_short_12","alias_value":"HAQ6JFBUNVQE","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"pith_short_16","alias_value":"HAQ6JFBUNVQEBBH5","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"pith_short_8","alias_value":"HAQ6JFBU","created_at":"2026-07-05T02:52:46Z"}],"graph_snapshots":[{"event_id":"sha256:26a1daf5c2da89d3522782076a8c9fd09f0dda6174e6cdeff0f7e0896fc03c1f","target":"graph","created_at":"2026-07-05T02:52:46Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.14019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the success of various text generation metrics such as BERTScore, it is still difficult to evaluate the image captions without enough reference captions due to the diversity of the descriptions. In this paper, we introduce a new metric UMIC, an Unreferenced Metric for Image Captioning which does not require reference captions to evaluate image captions. Based on Vision-and-Language BERT, we train UMIC to discriminate negative captions via contrastive learning. Also, we observe critical problems of the previous benchmark dataset (i.e., human annotations) on image captioning metric, and ","authors_text":"Franck Dernoncourt, Hwanhee Lee, Kyomin Jung, Seunghyun Yoon, Trung Bui","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-26T13:27:14Z","title":"UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14019","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:ca38a2d72113aa7a8e900b6849e065840b171be9691e78a070fa443c142de1c0","target":"record","created_at":"2026-07-05T02:52:46Z","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":"a01e0008e96faaeb63fd53269b13b65edc13f2fdaa4a5075f272eeb8fe78b918","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-26T13:27:14Z","title_canon_sha256":"30e7f8bf43737d1b1a38e5fdd3e22dc67677d1bc11c377bd64a4c0e765d0999f"},"schema_version":"1.0","source":{"id":"2106.14019","kind":"arxiv","version":1}},"canonical_sha256":"3821e494346d604084fd2a3bd1f367f9a7f9ab8869279ced5393f7f9aa791c55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3821e494346d604084fd2a3bd1f367f9a7f9ab8869279ced5393f7f9aa791c55","first_computed_at":"2026-07-05T02:52:46.555156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:46.555156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pHCpM1yAMJcPmRsQ8DrpP+aqhkOFlvueCkTx30uVpClUC497SIqbjwVICdJQCwlaGV1/dXT2ome2WWK++u51Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:46.555681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.14019","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca38a2d72113aa7a8e900b6849e065840b171be9691e78a070fa443c142de1c0","sha256:26a1daf5c2da89d3522782076a8c9fd09f0dda6174e6cdeff0f7e0896fc03c1f"],"state_sha256":"5b7da7122fa12f0a4c832906a03685fdc89967b9a3860df97509bdf9967605a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b5j3+9ZDx6SpM1M4A7C29ab5denCWkpOrQ9SYsL0WN0/s+lav6xamNvqskEIgqm9rZtDCQSvALr1CWPu0WDkAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T21:29:40.262268Z","bundle_sha256":"3f793710e42aceaf0db683f2f61c9c733f6dbb9816f8e96347288b3ec9a1936a"}}