{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:G3F4GU444FO4FPRP2DZX2M7RCN","short_pith_number":"pith:G3F4GU44","canonical_record":{"source":{"id":"2502.12755","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T11:16:38Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"4cf45d869b6842ec456ff205c55ed4e8159d9d5484aef6e62120d0b23ac0db51","abstract_canon_sha256":"2904bfb6caa74b2241249a94850a63bf2a29a56cc2da551c0cf33ef7b85fa3d8"},"schema_version":"1.0"},"canonical_sha256":"36cbc3539ce15dc2be2fd0f37d33f11368e4c08072eb4b064ae3cead743fab59","source":{"kind":"arxiv","id":"2502.12755","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12755","created_at":"2026-07-05T10:16:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12755v1","created_at":"2026-07-05T10:16:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12755","created_at":"2026-07-05T10:16:23Z"},{"alias_kind":"pith_short_12","alias_value":"G3F4GU444FO4","created_at":"2026-07-05T10:16:23Z"},{"alias_kind":"pith_short_16","alias_value":"G3F4GU444FO4FPRP","created_at":"2026-07-05T10:16:23Z"},{"alias_kind":"pith_short_8","alias_value":"G3F4GU44","created_at":"2026-07-05T10:16:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:G3F4GU444FO4FPRP2DZX2M7RCN","target":"record","payload":{"canonical_record":{"source":{"id":"2502.12755","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T11:16:38Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"4cf45d869b6842ec456ff205c55ed4e8159d9d5484aef6e62120d0b23ac0db51","abstract_canon_sha256":"2904bfb6caa74b2241249a94850a63bf2a29a56cc2da551c0cf33ef7b85fa3d8"},"schema_version":"1.0"},"canonical_sha256":"36cbc3539ce15dc2be2fd0f37d33f11368e4c08072eb4b064ae3cead743fab59","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:23.784490Z","signature_b64":"uzxoC/cEEN70fpYDEeMixFIy5R9jLZwDIjx8BpXtuAGfzMfjCObKj+LxivoDzstJYZxlXgPdmlvl6tkUuSB0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36cbc3539ce15dc2be2fd0f37d33f11368e4c08072eb4b064ae3cead743fab59","last_reissued_at":"2026-07-05T10:16:23.783931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:23.783931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.12755","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":"2026-07-05T10:16:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BM0WLX0Idj9SdgyyB6HoTor6ZzTkOe5hK5xUEYHlvaX9zJnjRY9L20grzEeeYd6Ee9FW710Z8Pf+7MC/PLdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T19:10:06.217440Z"},"content_sha256":"ef5ba7fd1a22b3859e133c7054444b211da67d14e8a95ada334ae06730e2d8d0","schema_version":"1.0","event_id":"sha256:ef5ba7fd1a22b3859e133c7054444b211da67d14e8a95ada334ae06730e2d8d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:G3F4GU444FO4FPRP2DZX2M7RCN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Machine Translation Corpus Generation: Integrating Human-in-the-Loop Post-Editing with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Abdul Baseet Anees, Ahmet Gunduz, Hassan Sawaf, Kamer Ali Yuksel","submitted_at":"2025-02-18T11:16:38Z","abstract_excerpt":"This paper introduces an advanced methodology for machine translation (MT) corpus generation, integrating semi-automated, human-in-the-loop post-editing with large language models (LLMs) to enhance efficiency and translation quality. Building upon previous work that utilized real-time training of a custom MT quality estimation metric, this system incorporates novel LLM features such as Enhanced Translation Synthesis and Assisted Annotation Analysis, which improve initial translation hypotheses and quality assessments, respectively. Additionally, the system employs LLM-Driven Pseudo Labeling an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12755","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/2502.12755/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":"2026-07-05T10:16:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"htcfcygOn2ZmVysvQX9zn7PrJ4eg2ksDs3lVgdpWqpxGVNfw5kewKDfyrS/83NXBFm/5A5H1yuckEd8kjDQKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T19:10:06.218041Z"},"content_sha256":"5ad708ed7e33130c029825c2309da9e72355d49ff0da953ba8164ea08e9c6f65","schema_version":"1.0","event_id":"sha256:5ad708ed7e33130c029825c2309da9e72355d49ff0da953ba8164ea08e9c6f65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G3F4GU444FO4FPRP2DZX2M7RCN/bundle.json","state_url":"https://pith.science/pith/G3F4GU444FO4FPRP2DZX2M7RCN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G3F4GU444FO4FPRP2DZX2M7RCN/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":"2026-08-23T19:10:06Z","links":{"resolver":"https://pith.science/pith/G3F4GU444FO4FPRP2DZX2M7RCN","bundle":"https://pith.science/pith/G3F4GU444FO4FPRP2DZX2M7RCN/bundle.json","state":"https://pith.science/pith/G3F4GU444FO4FPRP2DZX2M7RCN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G3F4GU444FO4FPRP2DZX2M7RCN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G3F4GU444FO4FPRP2DZX2M7RCN","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":"2904bfb6caa74b2241249a94850a63bf2a29a56cc2da551c0cf33ef7b85fa3d8","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T11:16:38Z","title_canon_sha256":"4cf45d869b6842ec456ff205c55ed4e8159d9d5484aef6e62120d0b23ac0db51"},"schema_version":"1.0","source":{"id":"2502.12755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12755","created_at":"2026-07-05T10:16:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12755v1","created_at":"2026-07-05T10:16:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12755","created_at":"2026-07-05T10:16:23Z"},{"alias_kind":"pith_short_12","alias_value":"G3F4GU444FO4","created_at":"2026-07-05T10:16:23Z"},{"alias_kind":"pith_short_16","alias_value":"G3F4GU444FO4FPRP","created_at":"2026-07-05T10:16:23Z"},{"alias_kind":"pith_short_8","alias_value":"G3F4GU44","created_at":"2026-07-05T10:16:23Z"}],"graph_snapshots":[{"event_id":"sha256:5ad708ed7e33130c029825c2309da9e72355d49ff0da953ba8164ea08e9c6f65","target":"graph","created_at":"2026-07-05T10:16:23Z","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/2502.12755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces an advanced methodology for machine translation (MT) corpus generation, integrating semi-automated, human-in-the-loop post-editing with large language models (LLMs) to enhance efficiency and translation quality. Building upon previous work that utilized real-time training of a custom MT quality estimation metric, this system incorporates novel LLM features such as Enhanced Translation Synthesis and Assisted Annotation Analysis, which improve initial translation hypotheses and quality assessments, respectively. Additionally, the system employs LLM-Driven Pseudo Labeling an","authors_text":"Abdul Baseet Anees, Ahmet Gunduz, Hassan Sawaf, Kamer Ali Yuksel","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T11:16:38Z","title":"Efficient Machine Translation Corpus Generation: Integrating Human-in-the-Loop Post-Editing with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12755","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:ef5ba7fd1a22b3859e133c7054444b211da67d14e8a95ada334ae06730e2d8d0","target":"record","created_at":"2026-07-05T10:16:23Z","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":"2904bfb6caa74b2241249a94850a63bf2a29a56cc2da551c0cf33ef7b85fa3d8","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T11:16:38Z","title_canon_sha256":"4cf45d869b6842ec456ff205c55ed4e8159d9d5484aef6e62120d0b23ac0db51"},"schema_version":"1.0","source":{"id":"2502.12755","kind":"arxiv","version":1}},"canonical_sha256":"36cbc3539ce15dc2be2fd0f37d33f11368e4c08072eb4b064ae3cead743fab59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36cbc3539ce15dc2be2fd0f37d33f11368e4c08072eb4b064ae3cead743fab59","first_computed_at":"2026-07-05T10:16:23.783931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:23.783931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uzxoC/cEEN70fpYDEeMixFIy5R9jLZwDIjx8BpXtuAGfzMfjCObKj+LxivoDzstJYZxlXgPdmlvl6tkUuSB0CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:23.784490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef5ba7fd1a22b3859e133c7054444b211da67d14e8a95ada334ae06730e2d8d0","sha256:5ad708ed7e33130c029825c2309da9e72355d49ff0da953ba8164ea08e9c6f65"],"state_sha256":"cc9945bac3950f35769de4cd8406b97d4307d9fd6410f5199fbd7d040c6bdc19"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T/2SgktfdpXOa9w/gRcEUigbUawFbndwo37x4OWsd8Mm0qWP8BhpKKqm/UGPW3Bi2ZIhKdt1ypcL8iE8ELayDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T19:10:06.221932Z","bundle_sha256":"6963ee3b3ebdbb7340ebc879baf509452e4f847080928ed4a064a0eabc38a7f5"}}