{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4ILNP7ZKPUZR2ZWOTK775A4CXQ","short_pith_number":"pith:4ILNP7ZK","schema_version":"1.0","canonical_sha256":"e216d7ff2a7d331d66ce9abffe8382bc3216444f2ff3a15292521afb8598d6f1","source":{"kind":"arxiv","id":"2206.07615","version":1},"attestation_state":"computed","paper":{"title":"The SIGMORPHON 2022 Shared Task on Morpheme Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amarsanaa Ganbold, Aryaman Arora, Ekaterina Vylomova, Fausto Giunchiglia, G\\'abor Bella, Kate\\v{r}ina Pelegrinov\\'a, Khuyagbaatar Batsuren, Kyle Gorman, Magda \\v{S}ev\\v{c}\\'ikov\\'a, Ryan Cotterell, Viktor Martinovi\\'c, \\v{S}\\'arka Dohnalov\\'a, Zden\\v{e}k \\v{Z}abokrtsk\\'y","submitted_at":"2022-06-15T15:57:22Z","abstract_excerpt":"The SIGMORPHON 2022 shared task on morpheme segmentation challenged systems to decompose a word into a sequence of morphemes and covered most types of morphology: compounds, derivations, and inflections. Subtask 1, word-level morpheme segmentation, covered 5 million words in 9 languages (Czech, English, Spanish, Hungarian, French, Italian, Russian, Latin, Mongolian) and received 13 system submissions from 7 teams and the best system averaged 97.29% F1 score across all languages, ranging English (93.84%) to Latin (99.38%). Subtask 2, sentence-level morpheme segmentation, covered 18,735 sentence"},"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":"2206.07615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-15T15:57:22Z","cross_cats_sorted":[],"title_canon_sha256":"78fc63714988f473cd9f9194f360a878099904cba7d1d7a134b2e9cbc17d056f","abstract_canon_sha256":"be8bac6c112805794c70d58cf05ee56c4980ed2a913c18c71e2234f7935f5573"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:06.957034Z","signature_b64":"rQa1cG1NJsE8qWw9XEDUy2L1a1p9UYh7zQp06mvkbeS0SletbiprcE7FjOTqJXtLDUZiNj3Kz8xP6E0hfdz1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e216d7ff2a7d331d66ce9abffe8382bc3216444f2ff3a15292521afb8598d6f1","last_reissued_at":"2026-07-05T04:32:06.956540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:06.956540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The SIGMORPHON 2022 Shared Task on Morpheme Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amarsanaa Ganbold, Aryaman Arora, Ekaterina Vylomova, Fausto Giunchiglia, G\\'abor Bella, Kate\\v{r}ina Pelegrinov\\'a, Khuyagbaatar Batsuren, Kyle Gorman, Magda \\v{S}ev\\v{c}\\'ikov\\'a, Ryan Cotterell, Viktor Martinovi\\'c, \\v{S}\\'arka Dohnalov\\'a, Zden\\v{e}k \\v{Z}abokrtsk\\'y","submitted_at":"2022-06-15T15:57:22Z","abstract_excerpt":"The SIGMORPHON 2022 shared task on morpheme segmentation challenged systems to decompose a word into a sequence of morphemes and covered most types of morphology: compounds, derivations, and inflections. Subtask 1, word-level morpheme segmentation, covered 5 million words in 9 languages (Czech, English, Spanish, Hungarian, French, Italian, Russian, Latin, Mongolian) and received 13 system submissions from 7 teams and the best system averaged 97.29% F1 score across all languages, ranging English (93.84%) to Latin (99.38%). Subtask 2, sentence-level morpheme segmentation, covered 18,735 sentence"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07615","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/2206.07615/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":"2206.07615","created_at":"2026-07-05T04:32:06.956598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07615v1","created_at":"2026-07-05T04:32:06.956598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07615","created_at":"2026-07-05T04:32:06.956598+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ILNP7ZKPUZR","created_at":"2026-07-05T04:32:06.956598+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ILNP7ZKPUZR2ZWO","created_at":"2026-07-05T04:32:06.956598+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ILNP7ZK","created_at":"2026-07-05T04:32:06.956598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11115","citing_title":"Incorporating Domain Knowledge into Materials Tokenization","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ILNP7ZKPUZR2ZWOTK775A4CXQ","json":"https://pith.science/pith/4ILNP7ZKPUZR2ZWOTK775A4CXQ.json","graph_json":"https://pith.science/api/pith-number/4ILNP7ZKPUZR2ZWOTK775A4CXQ/graph.json","events_json":"https://pith.science/api/pith-number/4ILNP7ZKPUZR2ZWOTK775A4CXQ/events.json","paper":"https://pith.science/paper/4ILNP7ZK"},"agent_actions":{"view_html":"https://pith.science/pith/4ILNP7ZKPUZR2ZWOTK775A4CXQ","download_json":"https://pith.science/pith/4ILNP7ZKPUZR2ZWOTK775A4CXQ.json","view_paper":"https://pith.science/paper/4ILNP7ZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07615&json=true","fetch_graph":"https://pith.science/api/pith-number/4ILNP7ZKPUZR2ZWOTK775A4CXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4ILNP7ZKPUZR2ZWOTK775A4CXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ILNP7ZKPUZR2ZWOTK775A4CXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ILNP7ZKPUZR2ZWOTK775A4CXQ/action/storage_attestation","attest_author":"https://pith.science/pith/4ILNP7ZKPUZR2ZWOTK775A4CXQ/action/author_attestation","sign_citation":"https://pith.science/pith/4ILNP7ZKPUZR2ZWOTK775A4CXQ/action/citation_signature","submit_replication":"https://pith.science/pith/4ILNP7ZKPUZR2ZWOTK775A4CXQ/action/replication_record"}},"created_at":"2026-07-05T04:32:06.956598+00:00","updated_at":"2026-07-05T04:32:06.956598+00:00"}