{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EWMXXUMZVKZ5CZDBDBWEVQ3KAL","short_pith_number":"pith:EWMXXUMZ","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"},"canonical_sha256":"25997bd199aab3d16461186c4ac36a02d953cc4319bed7a8d8d102227cce1004","source":{"kind":"arxiv","id":"2603.00620","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.00620","created_at":"2026-07-13T01:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2603.00620v2","created_at":"2026-07-13T01:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00620","created_at":"2026-07-13T01:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"EWMXXUMZVKZ5","created_at":"2026-07-13T01:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"EWMXXUMZVKZ5CZDB","created_at":"2026-07-13T01:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"EWMXXUMZ","created_at":"2026-07-13T01:18:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EWMXXUMZVKZ5CZDBDBWEVQ3KAL","target":"record","payload":{"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"},"canonical_sha256":"25997bd199aab3d16461186c4ac36a02d953cc4319bed7a8d8d102227cce1004","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"},"source_kind":"arxiv","source_id":"2603.00620","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-13T01:18:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JbHkPNnwgqDUHtkfs/PEkj/0jgtck+dUU2WU+MX81WgZdaYqExRL/5psTo8lZdzR2C1vhx2v/ot4XxlDpTs4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:00:57.786498Z"},"content_sha256":"e413d7f8c02323e9b749e4ada3c6a62e3ea0b82cf2c432528ed6a36e32337c0f","schema_version":"1.0","event_id":"sha256:e413d7f8c02323e9b749e4ada3c6a62e3ea0b82cf2c432528ed6a36e32337c0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EWMXXUMZVKZ5CZDBDBWEVQ3KAL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-13T01:18:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QJOUw+fv2V5qvNswJJ9Vc3HkvsjQ1vpSTMTbcrYbsrmB15xQqXjgR/xPQUaChGQnoF1UtjxdIZJvRoFPukevCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:00:57.787796Z"},"content_sha256":"035481810867064ad7b3a9caaff22992dc39d306fbc3a556c990fdfe7a0b0ff8","schema_version":"1.0","event_id":"sha256:035481810867064ad7b3a9caaff22992dc39d306fbc3a556c990fdfe7a0b0ff8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/bundle.json","state_url":"https://pith.science/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/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":"2026-08-10T05:00:57Z","links":{"resolver":"https://pith.science/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL","bundle":"https://pith.science/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/bundle.json","state":"https://pith.science/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EWMXXUMZVKZ5CZDBDBWEVQ3KAL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EWMXXUMZVKZ5CZDBDBWEVQ3KAL","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":"9cf1f7e888f1ac1ab180dc8b105fab53ec09ecda17f4126dbcb779e4be3feecc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-28T12:29:45Z","title_canon_sha256":"31b3a0c2b048f054eafac14c9f41443c4559437a3a8346c09adf389f5f095376"},"schema_version":"1.0","source":{"id":"2603.00620","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.00620","created_at":"2026-07-13T01:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2603.00620v2","created_at":"2026-07-13T01:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00620","created_at":"2026-07-13T01:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"EWMXXUMZVKZ5","created_at":"2026-07-13T01:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"EWMXXUMZVKZ5CZDB","created_at":"2026-07-13T01:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"EWMXXUMZ","created_at":"2026-07-13T01:18:03Z"}],"graph_snapshots":[{"event_id":"sha256:035481810867064ad7b3a9caaff22992dc39d306fbc3a556c990fdfe7a0b0ff8","target":"graph","created_at":"2026-07-13T01:18:03Z","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/2603.00620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Miryam de Lhoneux, Wessel Poelman, Yiyi Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-28T12:29:45Z","title":"QQ: A Language Metadata Toolkit for Multilingual NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00620","kind":"arxiv","version":2},"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:e413d7f8c02323e9b749e4ada3c6a62e3ea0b82cf2c432528ed6a36e32337c0f","target":"record","created_at":"2026-07-13T01:18:03Z","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":"9cf1f7e888f1ac1ab180dc8b105fab53ec09ecda17f4126dbcb779e4be3feecc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-28T12:29:45Z","title_canon_sha256":"31b3a0c2b048f054eafac14c9f41443c4559437a3a8346c09adf389f5f095376"},"schema_version":"1.0","source":{"id":"2603.00620","kind":"arxiv","version":2}},"canonical_sha256":"25997bd199aab3d16461186c4ac36a02d953cc4319bed7a8d8d102227cce1004","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25997bd199aab3d16461186c4ac36a02d953cc4319bed7a8d8d102227cce1004","first_computed_at":"2026-07-13T01:18:03.745459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:18:03.745459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HoBK14De+KwkAz1dgAlf5BNxKLjxBAY/g0NNpdJ90gcJZWGk/UAhnjvU3bnze34mNoGKmUr5hNP+4D+aaFQWBw==","signature_status":"signed_v1","signed_at":"2026-07-13T01:18:03.746707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.00620","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e413d7f8c02323e9b749e4ada3c6a62e3ea0b82cf2c432528ed6a36e32337c0f","sha256:035481810867064ad7b3a9caaff22992dc39d306fbc3a556c990fdfe7a0b0ff8"],"state_sha256":"e25671d72b0ea6ea225937ec7b055a39b1ad9e49370975a7b3dbdbfe4dd74007"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kFKy65zFxSLKx0lLUmSvWrV4R9S0tm1EEIZMc4OU2xvADHYLE5IyjyfKB1qZSJFuFneaT/JzqC7d2sO91vniCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:00:57.879150Z","bundle_sha256":"807c9f390c3c38691db4a68b7d7f7ec7f065b3f8bb99b58d1f7caf2c1019a54f"}}