{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MYQTQG6UIXU67EBESGEY2MMNID","short_pith_number":"pith:MYQTQG6U","canonical_record":{"source":{"id":"2109.06352","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T22:46:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"11576c6a71a4d2f87078627c9c3007bfed2e5532d2f5b812cbaa8f7824155385","abstract_canon_sha256":"2d84b38ccba066641bc2467d348be116871d492b497ee6c33896f8afe57fc561"},"schema_version":"1.0"},"canonical_sha256":"6621381bd445e9ef902491898d318d40e921c51cd0e5bf799cf9fc5ec5e118cd","source":{"kind":"arxiv","id":"2109.06352","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.06352","created_at":"2026-07-05T04:08:25Z"},{"alias_kind":"arxiv_version","alias_value":"2109.06352v2","created_at":"2026-07-05T04:08:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06352","created_at":"2026-07-05T04:08:25Z"},{"alias_kind":"pith_short_12","alias_value":"MYQTQG6UIXU6","created_at":"2026-07-05T04:08:25Z"},{"alias_kind":"pith_short_16","alias_value":"MYQTQG6UIXU67EBE","created_at":"2026-07-05T04:08:25Z"},{"alias_kind":"pith_short_8","alias_value":"MYQTQG6U","created_at":"2026-07-05T04:08:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MYQTQG6UIXU67EBESGEY2MMNID","target":"record","payload":{"canonical_record":{"source":{"id":"2109.06352","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T22:46:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"11576c6a71a4d2f87078627c9c3007bfed2e5532d2f5b812cbaa8f7824155385","abstract_canon_sha256":"2d84b38ccba066641bc2467d348be116871d492b497ee6c33896f8afe57fc561"},"schema_version":"1.0"},"canonical_sha256":"6621381bd445e9ef902491898d318d40e921c51cd0e5bf799cf9fc5ec5e118cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:25.756930Z","signature_b64":"ZrRJDJ73XB0mr9Z8k6EjgG0To5AUSKR8lLdEIiIeOVYG012hKsIkJXTPo/uJPFARvwx+4GJwHlaXJHn2kIQoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6621381bd445e9ef902491898d318d40e921c51cd0e5bf799cf9fc5ec5e118cd","last_reissued_at":"2026-07-05T04:08:25.756421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:25.756421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.06352","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:08:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mn/UeGev9mgULn7P+h9QakdxJXn+ABFlnicQrXN/Fd3KcgqRXRuxNaYjPbQdrmTRJzJ+XK6O2OoMAjA+0JuOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:59:01.066406Z"},"content_sha256":"4b729f3bcd3064e99eb83435e6da119e23a6c921750148684c6e4b11c1746cf5","schema_version":"1.0","event_id":"sha256:4b729f3bcd3064e99eb83435e6da119e23a6c921750148684c6e4b11c1746cf5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MYQTQG6UIXU67EBESGEY2MMNID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty-Aware Machine Translation Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andr\\'e F. T. Martins, Chrysoula Zerva, Ricardo Rei, Taisiya Glushkova","submitted_at":"2021-09-13T22:46:03Z","abstract_excerpt":"Several neural-based metrics have been recently proposed to evaluate machine translation quality. However, all of them resort to point estimates, which provide limited information at segment level. This is made worse as they are trained on noisy, biased and scarce human judgements, often resulting in unreliable quality predictions. In this paper, we introduce uncertainty-aware MT evaluation and analyze the trustworthiness of the predicted quality. We combine the COMET framework with two uncertainty estimation methods, Monte Carlo dropout and deep ensembles, to obtain quality scores along with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06352","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/2109.06352/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":"2026-07-05T04:08:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JrrXLeU5CxYm+m4qucbweLqmckaNH32S5ytPA+E6s+1iAr+MWvXSvrn7rEtFKRr+HLmwszl2M24hZnfwEYc2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:59:01.066782Z"},"content_sha256":"ff5cc265bd0e6728bc75908649c66d06549d7a43af27c65a371a9f60a0ce690a","schema_version":"1.0","event_id":"sha256:ff5cc265bd0e6728bc75908649c66d06549d7a43af27c65a371a9f60a0ce690a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MYQTQG6UIXU67EBESGEY2MMNID/bundle.json","state_url":"https://pith.science/pith/MYQTQG6UIXU67EBESGEY2MMNID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MYQTQG6UIXU67EBESGEY2MMNID/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":"2026-07-07T08:59:01Z","links":{"resolver":"https://pith.science/pith/MYQTQG6UIXU67EBESGEY2MMNID","bundle":"https://pith.science/pith/MYQTQG6UIXU67EBESGEY2MMNID/bundle.json","state":"https://pith.science/pith/MYQTQG6UIXU67EBESGEY2MMNID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MYQTQG6UIXU67EBESGEY2MMNID/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MYQTQG6UIXU67EBESGEY2MMNID","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":"2d84b38ccba066641bc2467d348be116871d492b497ee6c33896f8afe57fc561","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T22:46:03Z","title_canon_sha256":"11576c6a71a4d2f87078627c9c3007bfed2e5532d2f5b812cbaa8f7824155385"},"schema_version":"1.0","source":{"id":"2109.06352","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.06352","created_at":"2026-07-05T04:08:25Z"},{"alias_kind":"arxiv_version","alias_value":"2109.06352v2","created_at":"2026-07-05T04:08:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06352","created_at":"2026-07-05T04:08:25Z"},{"alias_kind":"pith_short_12","alias_value":"MYQTQG6UIXU6","created_at":"2026-07-05T04:08:25Z"},{"alias_kind":"pith_short_16","alias_value":"MYQTQG6UIXU67EBE","created_at":"2026-07-05T04:08:25Z"},{"alias_kind":"pith_short_8","alias_value":"MYQTQG6U","created_at":"2026-07-05T04:08:25Z"}],"graph_snapshots":[{"event_id":"sha256:ff5cc265bd0e6728bc75908649c66d06549d7a43af27c65a371a9f60a0ce690a","target":"graph","created_at":"2026-07-05T04:08:25Z","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/2109.06352/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Several neural-based metrics have been recently proposed to evaluate machine translation quality. However, all of them resort to point estimates, which provide limited information at segment level. This is made worse as they are trained on noisy, biased and scarce human judgements, often resulting in unreliable quality predictions. In this paper, we introduce uncertainty-aware MT evaluation and analyze the trustworthiness of the predicted quality. We combine the COMET framework with two uncertainty estimation methods, Monte Carlo dropout and deep ensembles, to obtain quality scores along with ","authors_text":"Andr\\'e F. T. Martins, Chrysoula Zerva, Ricardo Rei, Taisiya Glushkova","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T22:46:03Z","title":"Uncertainty-Aware Machine Translation Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06352","kind":"arxiv","version":2},"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":"sha256:4b729f3bcd3064e99eb83435e6da119e23a6c921750148684c6e4b11c1746cf5","target":"record","created_at":"2026-07-05T04:08:25Z","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":"2d84b38ccba066641bc2467d348be116871d492b497ee6c33896f8afe57fc561","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T22:46:03Z","title_canon_sha256":"11576c6a71a4d2f87078627c9c3007bfed2e5532d2f5b812cbaa8f7824155385"},"schema_version":"1.0","source":{"id":"2109.06352","kind":"arxiv","version":2}},"canonical_sha256":"6621381bd445e9ef902491898d318d40e921c51cd0e5bf799cf9fc5ec5e118cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6621381bd445e9ef902491898d318d40e921c51cd0e5bf799cf9fc5ec5e118cd","first_computed_at":"2026-07-05T04:08:25.756421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:25.756421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZrRJDJ73XB0mr9Z8k6EjgG0To5AUSKR8lLdEIiIeOVYG012hKsIkJXTPo/uJPFARvwx+4GJwHlaXJHn2kIQoCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:25.756930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.06352","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b729f3bcd3064e99eb83435e6da119e23a6c921750148684c6e4b11c1746cf5","sha256:ff5cc265bd0e6728bc75908649c66d06549d7a43af27c65a371a9f60a0ce690a"],"state_sha256":"69d16cd9ac476e35383da53b35251dfa4b7862da4f80990b56fbf6e963a43397"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iE1xknpWWvaFLFu5RjtPBmZq+2SGFuvyNzYgJ0VbLI7Axbh/YrYVzmYYuVX5B8F2yaKaoM+vf0VUOYD2kjDcDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:59:01.068842Z","bundle_sha256":"402b59961e7be48057ad36aed9da9aa99b68fcea71f0edc69d54390add51b762"}}