{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KPHXHYZV7M5STF7YMU6GA76RTC","short_pith_number":"pith:KPHXHYZV","canonical_record":{"source":{"id":"2306.11838","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T18:46:47Z","cross_cats_sorted":[],"title_canon_sha256":"adf7eb5300aee545cf2c64461cbf7681142e9c3bf2606b142e039ddda80c12ff","abstract_canon_sha256":"4f49a519f959a3712033f6f0a534d20020c8eaa16ebf087675c46b928d1862a9"},"schema_version":"1.0"},"canonical_sha256":"53cf73e335fb3b2997f8653c607fd198adae98c4d768bc976e9498f0be89b239","source":{"kind":"arxiv","id":"2306.11838","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11838","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11838v1","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11838","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"pith_short_12","alias_value":"KPHXHYZV7M5S","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"pith_short_16","alias_value":"KPHXHYZV7M5STF7Y","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"pith_short_8","alias_value":"KPHXHYZV","created_at":"2026-07-05T06:23:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KPHXHYZV7M5STF7YMU6GA76RTC","target":"record","payload":{"canonical_record":{"source":{"id":"2306.11838","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T18:46:47Z","cross_cats_sorted":[],"title_canon_sha256":"adf7eb5300aee545cf2c64461cbf7681142e9c3bf2606b142e039ddda80c12ff","abstract_canon_sha256":"4f49a519f959a3712033f6f0a534d20020c8eaa16ebf087675c46b928d1862a9"},"schema_version":"1.0"},"canonical_sha256":"53cf73e335fb3b2997f8653c607fd198adae98c4d768bc976e9498f0be89b239","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:07.424047Z","signature_b64":"wM9KPiYlsmgGBdVz0lnqunW4VQrT/iXSuqQsO9/F2EGTlBl5DEGoZHdyiYhG02gVdVMJyUL/goCeYc6MvuCRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53cf73e335fb3b2997f8653c607fd198adae98c4d768bc976e9498f0be89b239","last_reissued_at":"2026-07-05T06:23:07.423649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:07.423649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.11838","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":"2026-07-05T06:23:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v0g3reasANFK3NhQjJJBj6Ag1alQeKpMDql4NRnHABo+w4vfkAqSUixnSnrHtfCyOQ1O62kH4d3USbBlE3qCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T20:00:00.626296Z"},"content_sha256":"f3d40ef0c2e7900256a50f83397afdad2395de7b9c6aed43e898d3215e831457","schema_version":"1.0","event_id":"sha256:f3d40ef0c2e7900256a50f83397afdad2395de7b9c6aed43e898d3215e831457"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KPHXHYZV7M5STF7YMU6GA76RTC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Machine Translation Corpus Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmet Gunduz, Hassan Sawaf, Kamer Ali Yuksel, Shreyas Sharma","submitted_at":"2023-06-20T18:46:47Z","abstract_excerpt":"This paper proposes an efficient and semi-automated method for human-in-the-loop post-editing for machine translation (MT) corpus generation. The method is based on online training of a custom MT quality estimation metric on-the-fly as linguists perform post-edits. The online estimator is used to prioritize worse hypotheses for post-editing, and auto-close best hypotheses without post-editing. This way, significant improvements can be achieved in the resulting quality of post-edits at a lower cost due to reduced human involvement. The trained estimator can also provide an online sanity check m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11838","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/2306.11838/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":"2026-07-05T06:23:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ugQHnxrDQFsLia0bmsYL2Qjg1uXQ6SV3E8Zr9sg+WK48HPV58/zLtUrTArOx4s78H8ii5hYdemBfsb/c1bSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T20:00:00.626677Z"},"content_sha256":"89716fca89415ab3f144f116609e3cfca28c44ef0ebc7538499567c48b4d5105","schema_version":"1.0","event_id":"sha256:89716fca89415ab3f144f116609e3cfca28c44ef0ebc7538499567c48b4d5105"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPHXHYZV7M5STF7YMU6GA76RTC/bundle.json","state_url":"https://pith.science/pith/KPHXHYZV7M5STF7YMU6GA76RTC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPHXHYZV7M5STF7YMU6GA76RTC/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":"2026-08-23T20:00:00Z","links":{"resolver":"https://pith.science/pith/KPHXHYZV7M5STF7YMU6GA76RTC","bundle":"https://pith.science/pith/KPHXHYZV7M5STF7YMU6GA76RTC/bundle.json","state":"https://pith.science/pith/KPHXHYZV7M5STF7YMU6GA76RTC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPHXHYZV7M5STF7YMU6GA76RTC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KPHXHYZV7M5STF7YMU6GA76RTC","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":"4f49a519f959a3712033f6f0a534d20020c8eaa16ebf087675c46b928d1862a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T18:46:47Z","title_canon_sha256":"adf7eb5300aee545cf2c64461cbf7681142e9c3bf2606b142e039ddda80c12ff"},"schema_version":"1.0","source":{"id":"2306.11838","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11838","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11838v1","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11838","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"pith_short_12","alias_value":"KPHXHYZV7M5S","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"pith_short_16","alias_value":"KPHXHYZV7M5STF7Y","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"pith_short_8","alias_value":"KPHXHYZV","created_at":"2026-07-05T06:23:07Z"}],"graph_snapshots":[{"event_id":"sha256:89716fca89415ab3f144f116609e3cfca28c44ef0ebc7538499567c48b4d5105","target":"graph","created_at":"2026-07-05T06:23:07Z","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/2306.11838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes an efficient and semi-automated method for human-in-the-loop post-editing for machine translation (MT) corpus generation. The method is based on online training of a custom MT quality estimation metric on-the-fly as linguists perform post-edits. The online estimator is used to prioritize worse hypotheses for post-editing, and auto-close best hypotheses without post-editing. This way, significant improvements can be achieved in the resulting quality of post-edits at a lower cost due to reduced human involvement. The trained estimator can also provide an online sanity check m","authors_text":"Ahmet Gunduz, Hassan Sawaf, Kamer Ali Yuksel, Shreyas Sharma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T18:46:47Z","title":"Efficient Machine Translation Corpus Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11838","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:f3d40ef0c2e7900256a50f83397afdad2395de7b9c6aed43e898d3215e831457","target":"record","created_at":"2026-07-05T06:23:07Z","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":"4f49a519f959a3712033f6f0a534d20020c8eaa16ebf087675c46b928d1862a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T18:46:47Z","title_canon_sha256":"adf7eb5300aee545cf2c64461cbf7681142e9c3bf2606b142e039ddda80c12ff"},"schema_version":"1.0","source":{"id":"2306.11838","kind":"arxiv","version":1}},"canonical_sha256":"53cf73e335fb3b2997f8653c607fd198adae98c4d768bc976e9498f0be89b239","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53cf73e335fb3b2997f8653c607fd198adae98c4d768bc976e9498f0be89b239","first_computed_at":"2026-07-05T06:23:07.423649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:23:07.423649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wM9KPiYlsmgGBdVz0lnqunW4VQrT/iXSuqQsO9/F2EGTlBl5DEGoZHdyiYhG02gVdVMJyUL/goCeYc6MvuCRBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:23:07.424047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11838","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3d40ef0c2e7900256a50f83397afdad2395de7b9c6aed43e898d3215e831457","sha256:89716fca89415ab3f144f116609e3cfca28c44ef0ebc7538499567c48b4d5105"],"state_sha256":"ae4663eb9dbce1da2f84f14c2d0d3e13d1d112072712e84bbd53ba9cdec12ccb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4tr3uIzZ5X+dvcQLUb/jtMc4l4EX/g4fOKkWuJxLZ313Z28AIuNSIXX7yFdCegFvzFgtCBf/83k7fT7wo+34Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T20:00:00.635743Z","bundle_sha256":"e3bbca5b2972380402737370714f87dae75fd0bbe1d6926c9721cdf09a3c14a9"}}