{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EWMXXUMZVKZ5CZDBDBWEVQ3KAL","short_pith_number":"pith:EWMXXUMZ","schema_version":"1.0","canonical_sha256":"25997bd199aab3d16461186c4ac36a02d953cc4319bed7a8d8d102227cce1004","source":{"kind":"arxiv","id":"2603.00620","version":2},"attestation_state":"computed","paper":{"title":"QQ: A Language Metadata Toolkit for Multilingual NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Miryam de Lhoneux, Wessel Poelman, Yiyi Chen","submitted_at":"2026-02-28T12:29:45Z","abstract_excerpt":"Multilingual NLP research increasingly involves hundreds or thousands of languages across different datasets. Managing, discovering, and reporting language metadata becomes a common hurdle at these scales. We present QQ, a metadata toolkit and browser explorer. QQ compiles language metadata sources into a graph of language varieties, scripts, regions, identifiers, names, and relations, and exposes it through a Python API, a command-line interface, and a browser-based explorer. Users can normalize identifiers, retrieve metadata, traverse relations, and discover which external resources contain "},"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":"2603.00620","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-28T12:29:45Z","cross_cats_sorted":[],"title_canon_sha256":"31b3a0c2b048f054eafac14c9f41443c4559437a3a8346c09adf389f5f095376","abstract_canon_sha256":"9cf1f7e888f1ac1ab180dc8b105fab53ec09ecda17f4126dbcb779e4be3feecc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:18:03.746707Z","signature_b64":"HoBK14De+KwkAz1dgAlf5BNxKLjxBAY/g0NNpdJ90gcJZWGk/UAhnjvU3bnze34mNoGKmUr5hNP+4D+aaFQWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25997bd199aab3d16461186c4ac36a02d953cc4319bed7a8d8d102227cce1004","last_reissued_at":"2026-07-13T01:18:03.745459Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:18:03.745459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QQ: A Language Metadata Toolkit for Multilingual NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Miryam de Lhoneux, Wessel Poelman, Yiyi Chen","submitted_at":"2026-02-28T12:29:45Z","abstract_excerpt":"Multilingual NLP research increasingly involves hundreds or thousands of languages across different datasets. Managing, discovering, and reporting language metadata becomes a common hurdle at these scales. We present QQ, a metadata toolkit and browser explorer. QQ compiles language metadata sources into a graph of language varieties, scripts, regions, identifiers, names, and relations, and exposes it through a Python API, a command-line interface, and a browser-based explorer. Users can normalize identifiers, retrieve metadata, traverse relations, and discover which external resources contain "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00620","kind":"arxiv","version":2},"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/2603.00620/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":"2603.00620","created_at":"2026-07-13T01:18:03.746032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.00620v2","created_at":"2026-07-13T01:18:03.746032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00620","created_at":"2026-07-13T01:18:03.746032+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWMXXUMZVKZ5","created_at":"2026-07-13T01:18:03.746032+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWMXXUMZVKZ5CZDB","created_at":"2026-07-13T01:18:03.746032+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWMXXUMZ","created_at":"2026-07-13T01:18:03.746032+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/EWMXXUMZVKZ5CZDBDBWEVQ3KAL","json":"https://pith.science/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL.json","graph_json":"https://pith.science/api/pith-number/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/graph.json","events_json":"https://pith.science/api/pith-number/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/events.json","paper":"https://pith.science/paper/EWMXXUMZ"},"agent_actions":{"view_html":"https://pith.science/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL","download_json":"https://pith.science/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL.json","view_paper":"https://pith.science/paper/EWMXXUMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.00620&json=true","fetch_graph":"https://pith.science/api/pith-number/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/graph.json","fetch_events":"https://pith.science/api/pith-number/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/action/storage_attestation","attest_author":"https://pith.science/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/action/author_attestation","sign_citation":"https://pith.science/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/action/citation_signature","submit_replication":"https://pith.science/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/action/replication_record"}},"created_at":"2026-07-13T01:18:03.746032+00:00","updated_at":"2026-07-13T01:18:03.746032+00:00"}