{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QU7FABKH7EOTSZAKUPS6RTRQPI","short_pith_number":"pith:QU7FABKH","canonical_record":{"source":{"id":"2406.07424","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T16:26:18Z","cross_cats_sorted":[],"title_canon_sha256":"2ec59f0edc21c360a8f05ac31813c4a215f7a04225ddffba50f9a05359567ba9","abstract_canon_sha256":"d35379f199433d4b815882a8c04d9bc10e5143d17b35642beab23000f89fa6a1"},"schema_version":"1.0"},"canonical_sha256":"853e500547f91d39640aa3e5e8ce307a3ce1ce903ac4539835f0af6af8c22feb","source":{"kind":"arxiv","id":"2406.07424","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07424","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07424v3","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07424","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"pith_short_12","alias_value":"QU7FABKH7EOT","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"pith_short_16","alias_value":"QU7FABKH7EOTSZAK","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"pith_short_8","alias_value":"QU7FABKH","created_at":"2026-07-05T09:10:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QU7FABKH7EOTSZAKUPS6RTRQPI","target":"record","payload":{"canonical_record":{"source":{"id":"2406.07424","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T16:26:18Z","cross_cats_sorted":[],"title_canon_sha256":"2ec59f0edc21c360a8f05ac31813c4a215f7a04225ddffba50f9a05359567ba9","abstract_canon_sha256":"d35379f199433d4b815882a8c04d9bc10e5143d17b35642beab23000f89fa6a1"},"schema_version":"1.0"},"canonical_sha256":"853e500547f91d39640aa3e5e8ce307a3ce1ce903ac4539835f0af6af8c22feb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:48.153003Z","signature_b64":"j89S0c06AJhJTAsLbwRQHXA+ArqubcNJI6mipvjM5BRHm6+OxDzKnGBKugu5zEOu9o9OP+LJfpEO2cVQpCs8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"853e500547f91d39640aa3e5e8ce307a3ce1ce903ac4539835f0af6af8c22feb","last_reissued_at":"2026-07-05T09:10:48.152540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:48.152540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.07424","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:10:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rcO5TSLPnEoNAE7fyB2gaa1aXO6sRQFoL+CgKIYyhzFgAneRWNjD0hzBgNaX5o2bzHgGOQUai9yhYiVHh+glDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:02:06.398162Z"},"content_sha256":"1e4ac0147db7f5816b6dbc58b923ae633011e69844e0d3f4c91bf08626014ff4","schema_version":"1.0","event_id":"sha256:1e4ac0147db7f5816b6dbc58b923ae633011e69844e0d3f4c91bf08626014ff4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QU7FABKH7EOTSZAKUPS6RTRQPI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MINERS: Multilingual Language Models as Semantic Retrievers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Ifeoluwa Adelani, Genta Indra Winata, Ruochen Zhang","submitted_at":"2024-06-11T16:26:18Z","abstract_excerpt":"Words have been represented in a high-dimensional vector space that encodes their semantic similarities, enabling downstream applications such as retrieving synonyms, antonyms, and relevant contexts. However, despite recent advances in multilingual language models (LMs), the effectiveness of these models' representations in semantic retrieval contexts has not been comprehensively explored. To fill this gap, this paper introduces the MINERS, a benchmark designed to evaluate the ability of multilingual LMs in semantic retrieval tasks, including bitext mining and classification via retrieval-augm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07424","kind":"arxiv","version":3},"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/2406.07424/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":"2026-07-05T09:10:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5pOuqLGFt2/Nszh5d3n+WWEonDnEBNC90AAZeIaTQftI4QjealqNqOC+iKp306xAciGevPyDv8khrL/28w4EBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T08:02:06.399094Z"},"content_sha256":"01d67ff2aa937edf094eae436aa3bf1c6ba6de2f54044b7e3aa95d4759e2e514","schema_version":"1.0","event_id":"sha256:01d67ff2aa937edf094eae436aa3bf1c6ba6de2f54044b7e3aa95d4759e2e514"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QU7FABKH7EOTSZAKUPS6RTRQPI/bundle.json","state_url":"https://pith.science/pith/QU7FABKH7EOTSZAKUPS6RTRQPI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QU7FABKH7EOTSZAKUPS6RTRQPI/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":"2026-08-12T08:02:06Z","links":{"resolver":"https://pith.science/pith/QU7FABKH7EOTSZAKUPS6RTRQPI","bundle":"https://pith.science/pith/QU7FABKH7EOTSZAKUPS6RTRQPI/bundle.json","state":"https://pith.science/pith/QU7FABKH7EOTSZAKUPS6RTRQPI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QU7FABKH7EOTSZAKUPS6RTRQPI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QU7FABKH7EOTSZAKUPS6RTRQPI","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":"d35379f199433d4b815882a8c04d9bc10e5143d17b35642beab23000f89fa6a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T16:26:18Z","title_canon_sha256":"2ec59f0edc21c360a8f05ac31813c4a215f7a04225ddffba50f9a05359567ba9"},"schema_version":"1.0","source":{"id":"2406.07424","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07424","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07424v3","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07424","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"pith_short_12","alias_value":"QU7FABKH7EOT","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"pith_short_16","alias_value":"QU7FABKH7EOTSZAK","created_at":"2026-07-05T09:10:48Z"},{"alias_kind":"pith_short_8","alias_value":"QU7FABKH","created_at":"2026-07-05T09:10:48Z"}],"graph_snapshots":[{"event_id":"sha256:01d67ff2aa937edf094eae436aa3bf1c6ba6de2f54044b7e3aa95d4759e2e514","target":"graph","created_at":"2026-07-05T09:10:48Z","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/2406.07424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Words have been represented in a high-dimensional vector space that encodes their semantic similarities, enabling downstream applications such as retrieving synonyms, antonyms, and relevant contexts. However, despite recent advances in multilingual language models (LMs), the effectiveness of these models' representations in semantic retrieval contexts has not been comprehensively explored. To fill this gap, this paper introduces the MINERS, a benchmark designed to evaluate the ability of multilingual LMs in semantic retrieval tasks, including bitext mining and classification via retrieval-augm","authors_text":"David Ifeoluwa Adelani, Genta Indra Winata, Ruochen Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T16:26:18Z","title":"MINERS: Multilingual Language Models as Semantic Retrievers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07424","kind":"arxiv","version":3},"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":"sha256:1e4ac0147db7f5816b6dbc58b923ae633011e69844e0d3f4c91bf08626014ff4","target":"record","created_at":"2026-07-05T09:10:48Z","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":"d35379f199433d4b815882a8c04d9bc10e5143d17b35642beab23000f89fa6a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T16:26:18Z","title_canon_sha256":"2ec59f0edc21c360a8f05ac31813c4a215f7a04225ddffba50f9a05359567ba9"},"schema_version":"1.0","source":{"id":"2406.07424","kind":"arxiv","version":3}},"canonical_sha256":"853e500547f91d39640aa3e5e8ce307a3ce1ce903ac4539835f0af6af8c22feb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"853e500547f91d39640aa3e5e8ce307a3ce1ce903ac4539835f0af6af8c22feb","first_computed_at":"2026-07-05T09:10:48.152540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:48.152540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j89S0c06AJhJTAsLbwRQHXA+ArqubcNJI6mipvjM5BRHm6+OxDzKnGBKugu5zEOu9o9OP+LJfpEO2cVQpCs8Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:48.153003Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07424","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e4ac0147db7f5816b6dbc58b923ae633011e69844e0d3f4c91bf08626014ff4","sha256:01d67ff2aa937edf094eae436aa3bf1c6ba6de2f54044b7e3aa95d4759e2e514"],"state_sha256":"47972d7e3f148b0dc445622e286efd7aca72b1a187847d6f0dd7f7f6839a5829"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NoLTUV7p5Dy77hUlp+JZUVwh1xiskO+87d70xyrUWWHVuwwXFBBZoWAXeYFqtxPUcR9/W+jvEz2wJIS++dXDBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T08:02:06.417031Z","bundle_sha256":"29553324449797ac7581c691fbcfd40ee340b3dca09b5421aca758448d0aa7c0"}}