{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HBEX3RNH77EMRVMH4L5FRUDT7M","short_pith_number":"pith:HBEX3RNH","schema_version":"1.0","canonical_sha256":"38497dc5a7ffc8c8d587e2fa58d073fb217923309e28fbe7741b28dd9721ab80","source":{"kind":"arxiv","id":"2601.10925","version":3},"attestation_state":"computed","paper":{"title":"Massively Multilingual Joint Segmentation and Glossing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Palmer, Ali Marashian, Enora Rice, Graham Neubig, Jasmine Xu, Lindia Tjuatja, Maria Valentini, Michael Ginn","submitted_at":"2026-01-16T00:55:35Z","abstract_excerpt":"Automated interlinear gloss prediction with neural networks is a promising approach to accelerate language documentation efforts. However, while state-of-the-art models like GlossLM achieve high scores on glossing benchmarks, user studies with linguists have found critical barriers to the usefulness of such models in real-world scenarios. In particular, existing models typically generate morpheme-level glosses but assign them to whole words without predicting the actual morpheme boundaries, making the predictions less interpretable and thus untrustworthy to human annotators.\n  We conduct the f"},"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":"2601.10925","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-16T00:55:35Z","cross_cats_sorted":[],"title_canon_sha256":"5310bf3c7782220ac54cc9df86d4c0f4bd01ea000692ca95673882b2429aa202","abstract_canon_sha256":"8d306f341497c469aea83ac8f9674cebc606af39115c7d02fcf3ffac33ed3a1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:12.863892Z","signature_b64":"N5Wd3gGsqlx+S3bo7BfyRxVyiq7Xv5e6Lcq+GcO1Zu/IOVG9n6b6HqUGqLOFH+ncRmjMXTLpapNQVkVrvl0UDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38497dc5a7ffc8c8d587e2fa58d073fb217923309e28fbe7741b28dd9721ab80","last_reissued_at":"2026-06-09T01:05:12.863425Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:12.863425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Massively Multilingual Joint Segmentation and Glossing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Palmer, Ali Marashian, Enora Rice, Graham Neubig, Jasmine Xu, Lindia Tjuatja, Maria Valentini, Michael Ginn","submitted_at":"2026-01-16T00:55:35Z","abstract_excerpt":"Automated interlinear gloss prediction with neural networks is a promising approach to accelerate language documentation efforts. However, while state-of-the-art models like GlossLM achieve high scores on glossing benchmarks, user studies with linguists have found critical barriers to the usefulness of such models in real-world scenarios. In particular, existing models typically generate morpheme-level glosses but assign them to whole words without predicting the actual morpheme boundaries, making the predictions less interpretable and thus untrustworthy to human annotators.\n  We conduct the f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.10925","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/2601.10925/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":"2601.10925","created_at":"2026-06-09T01:05:12.863483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.10925v3","created_at":"2026-06-09T01:05:12.863483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.10925","created_at":"2026-06-09T01:05:12.863483+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBEX3RNH77EM","created_at":"2026-06-09T01:05:12.863483+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBEX3RNH77EMRVMH","created_at":"2026-06-09T01:05:12.863483+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBEX3RNH","created_at":"2026-06-09T01:05:12.863483+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/HBEX3RNH77EMRVMH4L5FRUDT7M","json":"https://pith.science/pith/HBEX3RNH77EMRVMH4L5FRUDT7M.json","graph_json":"https://pith.science/api/pith-number/HBEX3RNH77EMRVMH4L5FRUDT7M/graph.json","events_json":"https://pith.science/api/pith-number/HBEX3RNH77EMRVMH4L5FRUDT7M/events.json","paper":"https://pith.science/paper/HBEX3RNH"},"agent_actions":{"view_html":"https://pith.science/pith/HBEX3RNH77EMRVMH4L5FRUDT7M","download_json":"https://pith.science/pith/HBEX3RNH77EMRVMH4L5FRUDT7M.json","view_paper":"https://pith.science/paper/HBEX3RNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.10925&json=true","fetch_graph":"https://pith.science/api/pith-number/HBEX3RNH77EMRVMH4L5FRUDT7M/graph.json","fetch_events":"https://pith.science/api/pith-number/HBEX3RNH77EMRVMH4L5FRUDT7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBEX3RNH77EMRVMH4L5FRUDT7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBEX3RNH77EMRVMH4L5FRUDT7M/action/storage_attestation","attest_author":"https://pith.science/pith/HBEX3RNH77EMRVMH4L5FRUDT7M/action/author_attestation","sign_citation":"https://pith.science/pith/HBEX3RNH77EMRVMH4L5FRUDT7M/action/citation_signature","submit_replication":"https://pith.science/pith/HBEX3RNH77EMRVMH4L5FRUDT7M/action/replication_record"}},"created_at":"2026-06-09T01:05:12.863483+00:00","updated_at":"2026-06-09T01:05:12.863483+00:00"}