{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I4JAJ2YZPZ5X7INPWVR4XKSIBH","short_pith_number":"pith:I4JAJ2YZ","schema_version":"1.0","canonical_sha256":"471204eb197e7b7fa1afb563cbaa4809fc09e49323c80d0e5a42f3a743298ca5","source":{"kind":"arxiv","id":"2607.00171","version":1},"attestation_state":"computed","paper":{"title":"ALEE: Any-Language Evaluation of Embeddings via English-Centric Minimal Pairs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrianos Michail, Juri Opitz, Michelle Wastl, Rico Sennrich, Simon Clematide, Stylianos Psychias","submitted_at":"2026-06-30T20:45:17Z","abstract_excerpt":"Text embeddings are standard for semantic similarity tasks, yet their evaluation remains an open challenge. Current benchmarks are static, cover only a limited set of languages, are often domain-specific, susceptible to overfitting, and poorly representative of low-resource languages. To address these limitations, we introduce ALEE, a framework that extends Sentence Smith (Li et al., 2025) to the cross-lingual and paragraph level. ALEE uses Abstract Meaning Representations (AMR) to generate English minimal pairs with controlled, fine-grained semantic shifts, which are paired with translations "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.00171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T20:45:17Z","cross_cats_sorted":[],"title_canon_sha256":"80d0eb13e573bc727c4d0b812e1d092c8d980dc610488dd7f18b755c35efee2b","abstract_canon_sha256":"be3a8d348ea81a62bc17c9e369a3f6a13125f1e79cdb4af4ad4d16b003f92a44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:37.774913Z","signature_b64":"YRm3Ck5rJPxmiHXqADomnshEfv9rYfO3MwT/Sh5PSDL/phbYrQTOUcxj128mfH38mcM1rQdRyQd+wvrxoVo3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"471204eb197e7b7fa1afb563cbaa4809fc09e49323c80d0e5a42f3a743298ca5","last_reissued_at":"2026-07-02T00:18:37.774262Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:37.774262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALEE: Any-Language Evaluation of Embeddings via English-Centric Minimal Pairs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrianos Michail, Juri Opitz, Michelle Wastl, Rico Sennrich, Simon Clematide, Stylianos Psychias","submitted_at":"2026-06-30T20:45:17Z","abstract_excerpt":"Text embeddings are standard for semantic similarity tasks, yet their evaluation remains an open challenge. Current benchmarks are static, cover only a limited set of languages, are often domain-specific, susceptible to overfitting, and poorly representative of low-resource languages. To address these limitations, we introduce ALEE, a framework that extends Sentence Smith (Li et al., 2025) to the cross-lingual and paragraph level. ALEE uses Abstract Meaning Representations (AMR) to generate English minimal pairs with controlled, fine-grained semantic shifts, which are paired with translations "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00171","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/2607.00171/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.00171","created_at":"2026-07-02T00:18:37.774364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00171v1","created_at":"2026-07-02T00:18:37.774364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00171","created_at":"2026-07-02T00:18:37.774364+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4JAJ2YZPZ5X","created_at":"2026-07-02T00:18:37.774364+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4JAJ2YZPZ5X7INP","created_at":"2026-07-02T00:18:37.774364+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4JAJ2YZ","created_at":"2026-07-02T00:18:37.774364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I4JAJ2YZPZ5X7INPWVR4XKSIBH","json":"https://pith.science/pith/I4JAJ2YZPZ5X7INPWVR4XKSIBH.json","graph_json":"https://pith.science/api/pith-number/I4JAJ2YZPZ5X7INPWVR4XKSIBH/graph.json","events_json":"https://pith.science/api/pith-number/I4JAJ2YZPZ5X7INPWVR4XKSIBH/events.json","paper":"https://pith.science/paper/I4JAJ2YZ"},"agent_actions":{"view_html":"https://pith.science/pith/I4JAJ2YZPZ5X7INPWVR4XKSIBH","download_json":"https://pith.science/pith/I4JAJ2YZPZ5X7INPWVR4XKSIBH.json","view_paper":"https://pith.science/paper/I4JAJ2YZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00171&json=true","fetch_graph":"https://pith.science/api/pith-number/I4JAJ2YZPZ5X7INPWVR4XKSIBH/graph.json","fetch_events":"https://pith.science/api/pith-number/I4JAJ2YZPZ5X7INPWVR4XKSIBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4JAJ2YZPZ5X7INPWVR4XKSIBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4JAJ2YZPZ5X7INPWVR4XKSIBH/action/storage_attestation","attest_author":"https://pith.science/pith/I4JAJ2YZPZ5X7INPWVR4XKSIBH/action/author_attestation","sign_citation":"https://pith.science/pith/I4JAJ2YZPZ5X7INPWVR4XKSIBH/action/citation_signature","submit_replication":"https://pith.science/pith/I4JAJ2YZPZ5X7INPWVR4XKSIBH/action/replication_record"}},"created_at":"2026-07-02T00:18:37.774364+00:00","updated_at":"2026-07-02T00:18:37.774364+00:00"}