{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BX4DKBUB7TRY7GBCXRHHHGFZX3","short_pith_number":"pith:BX4DKBUB","canonical_record":{"source":{"id":"2108.13897","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-31T14:53:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2de63d843651eb4632477ef6f6e2f4d4a6006c130fce0029c836559af69e002b","abstract_canon_sha256":"1435b3838da85fccde469d4fbf9f05dfa65b226c9d1ac84e3ae723f6b5c43039"},"schema_version":"1.0"},"canonical_sha256":"0df8350681fce38f9822bc4e7398b9bef910208805508c06a50ca8df2d361e53","source":{"kind":"arxiv","id":"2108.13897","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.13897","created_at":"2026-07-05T04:49:21Z"},{"alias_kind":"arxiv_version","alias_value":"2108.13897v5","created_at":"2026-07-05T04:49:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13897","created_at":"2026-07-05T04:49:21Z"},{"alias_kind":"pith_short_12","alias_value":"BX4DKBUB7TRY","created_at":"2026-07-05T04:49:21Z"},{"alias_kind":"pith_short_16","alias_value":"BX4DKBUB7TRY7GBC","created_at":"2026-07-05T04:49:21Z"},{"alias_kind":"pith_short_8","alias_value":"BX4DKBUB","created_at":"2026-07-05T04:49:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BX4DKBUB7TRY7GBCXRHHHGFZX3","target":"record","payload":{"canonical_record":{"source":{"id":"2108.13897","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-31T14:53:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2de63d843651eb4632477ef6f6e2f4d4a6006c130fce0029c836559af69e002b","abstract_canon_sha256":"1435b3838da85fccde469d4fbf9f05dfa65b226c9d1ac84e3ae723f6b5c43039"},"schema_version":"1.0"},"canonical_sha256":"0df8350681fce38f9822bc4e7398b9bef910208805508c06a50ca8df2d361e53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:21.326069Z","signature_b64":"S3jmtrFQRwFBkpeFUC92PjN0xLFHIbAhjKRAC34uUCTubzIAa2cOhGWjUn/DBfmCvM+KOneE7F4hcnaFDb28Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0df8350681fce38f9822bc4e7398b9bef910208805508c06a50ca8df2d361e53","last_reissued_at":"2026-07-05T04:49:21.325670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:21.325670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.13897","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:49:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"al2Vhrg1OKp/SoNTlOXEmCf4/lcW045EanE4F9Xt9zYYas893qCIuZyI9v3XHl5yDvcB5VJ8BpP+uFykra6qDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T22:03:19.082345Z"},"content_sha256":"3aeb49eccc216ff26f6568cb2747e95559eefe52ec8aa938fc7877c27ca3e7d5","schema_version":"1.0","event_id":"sha256:3aeb49eccc216ff26f6568cb2747e95559eefe52ec8aa938fc7877c27ca3e7d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BX4DKBUB7TRY7GBCXRHHHGFZX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hugo Queiroz Abonizio, Israel Campiotti, Luiz Bonifacio, Marzieh Fadaee, Roberto Lotufo, Rodrigo Nogueira, Vitor Jeronymo","submitted_at":"2021-08-31T14:53:37Z","abstract_excerpt":"The MS MARCO ranking dataset has been widely used for training deep learning models for IR tasks, achieving considerable effectiveness on diverse zero-shot scenarios. However, this type of resource is scarce in languages other than English. In this work, we present mMARCO, a multilingual version of the MS MARCO passage ranking dataset comprising 13 languages that was created using machine translation. We evaluated mMARCO by finetuning monolingual and multilingual reranking models, as well as a multilingual dense retrieval model on this dataset. We also evaluated models finetuned using the mMAR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13897","kind":"arxiv","version":5},"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/2108.13897/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":"2026-07-05T04:49:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"McaES7X5Z9a7MlyZ+tH8hFGEkQmepcmLgOsH0W1tYUaVpCK3n+gw1JWuz1bE9BsKSPLfCOiVag11Xw6gRj8UBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T22:03:19.083160Z"},"content_sha256":"15442ec7fda1de37eb4c70f1785404375a5165161585608bbf34e2e4c8599499","schema_version":"1.0","event_id":"sha256:15442ec7fda1de37eb4c70f1785404375a5165161585608bbf34e2e4c8599499"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BX4DKBUB7TRY7GBCXRHHHGFZX3/bundle.json","state_url":"https://pith.science/pith/BX4DKBUB7TRY7GBCXRHHHGFZX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BX4DKBUB7TRY7GBCXRHHHGFZX3/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":"2026-07-10T22:03:19Z","links":{"resolver":"https://pith.science/pith/BX4DKBUB7TRY7GBCXRHHHGFZX3","bundle":"https://pith.science/pith/BX4DKBUB7TRY7GBCXRHHHGFZX3/bundle.json","state":"https://pith.science/pith/BX4DKBUB7TRY7GBCXRHHHGFZX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BX4DKBUB7TRY7GBCXRHHHGFZX3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BX4DKBUB7TRY7GBCXRHHHGFZX3","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":"1435b3838da85fccde469d4fbf9f05dfa65b226c9d1ac84e3ae723f6b5c43039","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-31T14:53:37Z","title_canon_sha256":"2de63d843651eb4632477ef6f6e2f4d4a6006c130fce0029c836559af69e002b"},"schema_version":"1.0","source":{"id":"2108.13897","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.13897","created_at":"2026-07-05T04:49:21Z"},{"alias_kind":"arxiv_version","alias_value":"2108.13897v5","created_at":"2026-07-05T04:49:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13897","created_at":"2026-07-05T04:49:21Z"},{"alias_kind":"pith_short_12","alias_value":"BX4DKBUB7TRY","created_at":"2026-07-05T04:49:21Z"},{"alias_kind":"pith_short_16","alias_value":"BX4DKBUB7TRY7GBC","created_at":"2026-07-05T04:49:21Z"},{"alias_kind":"pith_short_8","alias_value":"BX4DKBUB","created_at":"2026-07-05T04:49:21Z"}],"graph_snapshots":[{"event_id":"sha256:15442ec7fda1de37eb4c70f1785404375a5165161585608bbf34e2e4c8599499","target":"graph","created_at":"2026-07-05T04:49:21Z","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/2108.13897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The MS MARCO ranking dataset has been widely used for training deep learning models for IR tasks, achieving considerable effectiveness on diverse zero-shot scenarios. However, this type of resource is scarce in languages other than English. In this work, we present mMARCO, a multilingual version of the MS MARCO passage ranking dataset comprising 13 languages that was created using machine translation. We evaluated mMARCO by finetuning monolingual and multilingual reranking models, as well as a multilingual dense retrieval model on this dataset. We also evaluated models finetuned using the mMAR","authors_text":"Hugo Queiroz Abonizio, Israel Campiotti, Luiz Bonifacio, Marzieh Fadaee, Roberto Lotufo, Rodrigo Nogueira, Vitor Jeronymo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-31T14:53:37Z","title":"mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13897","kind":"arxiv","version":5},"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":"sha256:3aeb49eccc216ff26f6568cb2747e95559eefe52ec8aa938fc7877c27ca3e7d5","target":"record","created_at":"2026-07-05T04:49:21Z","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":"1435b3838da85fccde469d4fbf9f05dfa65b226c9d1ac84e3ae723f6b5c43039","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-31T14:53:37Z","title_canon_sha256":"2de63d843651eb4632477ef6f6e2f4d4a6006c130fce0029c836559af69e002b"},"schema_version":"1.0","source":{"id":"2108.13897","kind":"arxiv","version":5}},"canonical_sha256":"0df8350681fce38f9822bc4e7398b9bef910208805508c06a50ca8df2d361e53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0df8350681fce38f9822bc4e7398b9bef910208805508c06a50ca8df2d361e53","first_computed_at":"2026-07-05T04:49:21.325670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:49:21.325670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S3jmtrFQRwFBkpeFUC92PjN0xLFHIbAhjKRAC34uUCTubzIAa2cOhGWjUn/DBfmCvM+KOneE7F4hcnaFDb28Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:49:21.326069Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.13897","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3aeb49eccc216ff26f6568cb2747e95559eefe52ec8aa938fc7877c27ca3e7d5","sha256:15442ec7fda1de37eb4c70f1785404375a5165161585608bbf34e2e4c8599499"],"state_sha256":"b87b83663fc435e735dfb67f7e3f3f0090c3a32c63bcc4570a599b2575bf7986"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F2r3rO/FWBANxLX4N6TLddY/np6L8zkQQ3TUGxQ3M5dBjs6MfPnzqWkpBw1qBL8LbKZnADXoEJq8/bjBwApPCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T22:03:19.087493Z","bundle_sha256":"7f766cb42278802c78351ce1f4f27861764f84144b81a0b6ac5a4dbf4290a353"}}