{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QXTAAOJBQG2QM7BJWUOSAPM2DH","short_pith_number":"pith:QXTAAOJB","canonical_record":{"source":{"id":"2412.11615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T09:57:28Z","cross_cats_sorted":[],"title_canon_sha256":"f28998d91673c07a68607e071255a9a29b497a7033789e6ce1195aca25380d0d","abstract_canon_sha256":"d1138cc097b9ce6224b5a59a2ba8c43098bb783e19a886808784ef7fe2994c21"},"schema_version":"1.0"},"canonical_sha256":"85e600392181b5067c29b51d203d9a19ee202775061c85e427ff074bc342eea6","source":{"kind":"arxiv","id":"2412.11615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11615","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11615v1","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11615","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"pith_short_12","alias_value":"QXTAAOJBQG2Q","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"pith_short_16","alias_value":"QXTAAOJBQG2QM7BJ","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"pith_short_8","alias_value":"QXTAAOJB","created_at":"2026-07-05T09:49:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QXTAAOJBQG2QM7BJWUOSAPM2DH","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T09:57:28Z","cross_cats_sorted":[],"title_canon_sha256":"f28998d91673c07a68607e071255a9a29b497a7033789e6ce1195aca25380d0d","abstract_canon_sha256":"d1138cc097b9ce6224b5a59a2ba8c43098bb783e19a886808784ef7fe2994c21"},"schema_version":"1.0"},"canonical_sha256":"85e600392181b5067c29b51d203d9a19ee202775061c85e427ff074bc342eea6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:48.443297Z","signature_b64":"c8mi0aFoiSgMibBuXBVatm8pZPf7F90aRcm3PA31jbu9IVjrvqi4/1O5Dd4dC4wpiipWKUKoqoyUAp/9zhEvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85e600392181b5067c29b51d203d9a19ee202775061c85e427ff074bc342eea6","last_reissued_at":"2026-07-05T09:49:48.442754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:48.442754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11615","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":"2026-07-05T09:49:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qt/exBJSy78lGyKj/IK3ALin5eqCTAsbUK/0DK2N1iXt8r6Pj8e2Aa5EdA1F/XNqMTPPUFUzrDoYVWgZtIOOAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:57:26.766092Z"},"content_sha256":"f06d2efec8b99a6f11cfb5d6d280c504c32c333d34fbad2ff61113138b0d0ebf","schema_version":"1.0","event_id":"sha256:f06d2efec8b99a6f11cfb5d6d280c504c32c333d34fbad2ff61113138b0d0ebf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QXTAAOJBQG2QM7BJWUOSAPM2DH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Audrey Mash, Carlos Escolano, Javier Garc\\'ia Gilabert, Maite Melero, Xixian Liao","submitted_at":"2024-12-16T09:57:28Z","abstract_excerpt":"We introduce MT-LENS, a framework designed to evaluate Machine Translation (MT) systems across a variety of tasks, including translation quality, gender bias detection, added toxicity, and robustness to misspellings. While several toolkits have become very popular for benchmarking the capabilities of Large Language Models (LLMs), existing evaluation tools often lack the ability to thoroughly assess the diverse aspects of MT performance. MT-LENS addresses these limitations by extending the capabilities of LM-eval-harness for MT, supporting state-of-the-art datasets and a wide range of evaluatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11615","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/2412.11615/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":"2026-07-05T09:49:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g7MLMin1cpbyfitPspGDWWFF+Ihc51Lyt42C6x6nDUMGzD4aToxxXGJ5JGtPiVdvpnubEaBkW1e2UIK7itr1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:57:26.766704Z"},"content_sha256":"0d4bf609a394415602373073c32be7799546eab1291bbe0ceb831ca07251c6f5","schema_version":"1.0","event_id":"sha256:0d4bf609a394415602373073c32be7799546eab1291bbe0ceb831ca07251c6f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXTAAOJBQG2QM7BJWUOSAPM2DH/bundle.json","state_url":"https://pith.science/pith/QXTAAOJBQG2QM7BJWUOSAPM2DH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXTAAOJBQG2QM7BJWUOSAPM2DH/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":"2026-08-20T22:57:26Z","links":{"resolver":"https://pith.science/pith/QXTAAOJBQG2QM7BJWUOSAPM2DH","bundle":"https://pith.science/pith/QXTAAOJBQG2QM7BJWUOSAPM2DH/bundle.json","state":"https://pith.science/pith/QXTAAOJBQG2QM7BJWUOSAPM2DH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXTAAOJBQG2QM7BJWUOSAPM2DH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QXTAAOJBQG2QM7BJWUOSAPM2DH","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":"d1138cc097b9ce6224b5a59a2ba8c43098bb783e19a886808784ef7fe2994c21","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T09:57:28Z","title_canon_sha256":"f28998d91673c07a68607e071255a9a29b497a7033789e6ce1195aca25380d0d"},"schema_version":"1.0","source":{"id":"2412.11615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11615","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11615v1","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11615","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"pith_short_12","alias_value":"QXTAAOJBQG2Q","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"pith_short_16","alias_value":"QXTAAOJBQG2QM7BJ","created_at":"2026-07-05T09:49:48Z"},{"alias_kind":"pith_short_8","alias_value":"QXTAAOJB","created_at":"2026-07-05T09:49:48Z"}],"graph_snapshots":[{"event_id":"sha256:0d4bf609a394415602373073c32be7799546eab1291bbe0ceb831ca07251c6f5","target":"graph","created_at":"2026-07-05T09:49:48Z","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/2412.11615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce MT-LENS, a framework designed to evaluate Machine Translation (MT) systems across a variety of tasks, including translation quality, gender bias detection, added toxicity, and robustness to misspellings. While several toolkits have become very popular for benchmarking the capabilities of Large Language Models (LLMs), existing evaluation tools often lack the ability to thoroughly assess the diverse aspects of MT performance. MT-LENS addresses these limitations by extending the capabilities of LM-eval-harness for MT, supporting state-of-the-art datasets and a wide range of evaluatio","authors_text":"Audrey Mash, Carlos Escolano, Javier Garc\\'ia Gilabert, Maite Melero, Xixian Liao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T09:57:28Z","title":"MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11615","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:f06d2efec8b99a6f11cfb5d6d280c504c32c333d34fbad2ff61113138b0d0ebf","target":"record","created_at":"2026-07-05T09:49:48Z","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":"d1138cc097b9ce6224b5a59a2ba8c43098bb783e19a886808784ef7fe2994c21","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T09:57:28Z","title_canon_sha256":"f28998d91673c07a68607e071255a9a29b497a7033789e6ce1195aca25380d0d"},"schema_version":"1.0","source":{"id":"2412.11615","kind":"arxiv","version":1}},"canonical_sha256":"85e600392181b5067c29b51d203d9a19ee202775061c85e427ff074bc342eea6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85e600392181b5067c29b51d203d9a19ee202775061c85e427ff074bc342eea6","first_computed_at":"2026-07-05T09:49:48.442754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:48.442754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c8mi0aFoiSgMibBuXBVatm8pZPf7F90aRcm3PA31jbu9IVjrvqi4/1O5Dd4dC4wpiipWKUKoqoyUAp/9zhEvAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:48.443297Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f06d2efec8b99a6f11cfb5d6d280c504c32c333d34fbad2ff61113138b0d0ebf","sha256:0d4bf609a394415602373073c32be7799546eab1291bbe0ceb831ca07251c6f5"],"state_sha256":"28d9612c0219b5ce6fec761954b3e7d6f31b9aa8eeae9520afc7108c3c5e5cab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r9zVnl5R2G+IFSMaIsXxM5EXaXZ6Xhx7ZlVeIexJC0M1E1x6glb9OtFtOAUT7NzHk8GJiV6NIGGkr9kAIiXlDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T22:57:26.771351Z","bundle_sha256":"3d9250c72a94c11f10817b63a5ab667c4f7dc0a709654beed3ae45cd0008d834"}}