{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CBAHIVY7IWEZ6MLVJSV7FL2R47","short_pith_number":"pith:CBAHIVY7","canonical_record":{"source":{"id":"2606.04367","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T02:29:30Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"98f02fe1ea51206b62f00362ed47313fcaedb16a6802efbab6318c840477ca6e","abstract_canon_sha256":"6d45a4e02d2635b4d354cf5616e4d58845847fc5453ee3c32fa1b2f6a4953b9f"},"schema_version":"1.0"},"canonical_sha256":"104074571f45899f31754cabf2af51e7d08176b66018d2e91cbaedfb24139f92","source":{"kind":"arxiv","id":"2606.04367","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04367","created_at":"2026-06-04T01:09:05Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04367v1","created_at":"2026-06-04T01:09:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04367","created_at":"2026-06-04T01:09:05Z"},{"alias_kind":"pith_short_12","alias_value":"CBAHIVY7IWEZ","created_at":"2026-06-04T01:09:05Z"},{"alias_kind":"pith_short_16","alias_value":"CBAHIVY7IWEZ6MLV","created_at":"2026-06-04T01:09:05Z"},{"alias_kind":"pith_short_8","alias_value":"CBAHIVY7","created_at":"2026-06-04T01:09:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CBAHIVY7IWEZ6MLVJSV7FL2R47","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04367","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T02:29:30Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"98f02fe1ea51206b62f00362ed47313fcaedb16a6802efbab6318c840477ca6e","abstract_canon_sha256":"6d45a4e02d2635b4d354cf5616e4d58845847fc5453ee3c32fa1b2f6a4953b9f"},"schema_version":"1.0"},"canonical_sha256":"104074571f45899f31754cabf2af51e7d08176b66018d2e91cbaedfb24139f92","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:05.484227Z","signature_b64":"DybxQGflPKpEqXgLSzW9KEy1VAUUSzh6gaHxlXoG8RXdd17e2l+9PB8oTsIQ6YPbh7AAcXkFn4t3xESPrrEUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"104074571f45899f31754cabf2af51e7d08176b66018d2e91cbaedfb24139f92","last_reissued_at":"2026-06-04T01:09:05.483738Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:05.483738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04367","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:09:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mfnreEr05YOqJc1a9q/7zVSXLWhFy45d0g8C7aN7MP9a8+9uKNTn2JTBy+PsdLvw3L5LF6RF+c+DSO8HsOtoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T06:48:22.235770Z"},"content_sha256":"fe5e6bf3c4a34b428d46b9fe1f9aad920da703911c42dd485206ab2bbf9d6760","schema_version":"1.0","event_id":"sha256:fe5e6bf3c4a34b428d46b9fe1f9aad920da703911c42dd485206ab2bbf9d6760"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CBAHIVY7IWEZ6MLVJSV7FL2R47","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GlossAssist -- A Tool to Simplify Corpus Creation and Study the Effect of NLP Models in Low-Resource Documentation Settings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Alexis Palmer, Bhargav Shandilya, Matt Buchholz","submitted_at":"2026-06-03T02:29:30Z","abstract_excerpt":"Interlinear glossed text (IGT) is the standard format for linguistic annotation in language documentation. Producing it manually, however, is often slow and costly. Automated glossing systems have improved substantially in recent years, but adoption among field linguists remains limited. Existing tools are designed to be evaluated rather than used, offering no interpretable path for correction or the incorporation of linguistic expertise back into model behavior. We present GlossAssist, a glossing tool built around the retrieval-based architecture of CWoMP (Contrastive Word-Morpheme Pre-traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04367","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/2606.04367/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":"2026-06-04T01:09:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oyOF1GSwRktBfCoELfSKTxJnL65wxK8JzOD8q2Y8rk/L2Vsd3kAQsfOdR8UxXTm+2JplavEc8UmSgvQtQDQaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T06:48:22.236156Z"},"content_sha256":"8aa3a1345c2d2557b52b0aaa2500c7a9d6315409ba5c7be87d79a4d9a1e82e96","schema_version":"1.0","event_id":"sha256:8aa3a1345c2d2557b52b0aaa2500c7a9d6315409ba5c7be87d79a4d9a1e82e96"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CBAHIVY7IWEZ6MLVJSV7FL2R47/bundle.json","state_url":"https://pith.science/pith/CBAHIVY7IWEZ6MLVJSV7FL2R47/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CBAHIVY7IWEZ6MLVJSV7FL2R47/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":"2026-06-28T06:48:22Z","links":{"resolver":"https://pith.science/pith/CBAHIVY7IWEZ6MLVJSV7FL2R47","bundle":"https://pith.science/pith/CBAHIVY7IWEZ6MLVJSV7FL2R47/bundle.json","state":"https://pith.science/pith/CBAHIVY7IWEZ6MLVJSV7FL2R47/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CBAHIVY7IWEZ6MLVJSV7FL2R47/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CBAHIVY7IWEZ6MLVJSV7FL2R47","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":"6d45a4e02d2635b4d354cf5616e4d58845847fc5453ee3c32fa1b2f6a4953b9f","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T02:29:30Z","title_canon_sha256":"98f02fe1ea51206b62f00362ed47313fcaedb16a6802efbab6318c840477ca6e"},"schema_version":"1.0","source":{"id":"2606.04367","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04367","created_at":"2026-06-04T01:09:05Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04367v1","created_at":"2026-06-04T01:09:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04367","created_at":"2026-06-04T01:09:05Z"},{"alias_kind":"pith_short_12","alias_value":"CBAHIVY7IWEZ","created_at":"2026-06-04T01:09:05Z"},{"alias_kind":"pith_short_16","alias_value":"CBAHIVY7IWEZ6MLV","created_at":"2026-06-04T01:09:05Z"},{"alias_kind":"pith_short_8","alias_value":"CBAHIVY7","created_at":"2026-06-04T01:09:05Z"}],"graph_snapshots":[{"event_id":"sha256:8aa3a1345c2d2557b52b0aaa2500c7a9d6315409ba5c7be87d79a4d9a1e82e96","target":"graph","created_at":"2026-06-04T01:09:05Z","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/2606.04367/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Interlinear glossed text (IGT) is the standard format for linguistic annotation in language documentation. Producing it manually, however, is often slow and costly. Automated glossing systems have improved substantially in recent years, but adoption among field linguists remains limited. Existing tools are designed to be evaluated rather than used, offering no interpretable path for correction or the incorporation of linguistic expertise back into model behavior. We present GlossAssist, a glossing tool built around the retrieval-based architecture of CWoMP (Contrastive Word-Morpheme Pre-traini","authors_text":"Alexis Palmer, Bhargav Shandilya, Matt Buchholz","cross_cats":["cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T02:29:30Z","title":"GlossAssist -- A Tool to Simplify Corpus Creation and Study the Effect of NLP Models in Low-Resource Documentation Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04367","kind":"arxiv","version":1},"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:fe5e6bf3c4a34b428d46b9fe1f9aad920da703911c42dd485206ab2bbf9d6760","target":"record","created_at":"2026-06-04T01:09:05Z","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":"6d45a4e02d2635b4d354cf5616e4d58845847fc5453ee3c32fa1b2f6a4953b9f","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T02:29:30Z","title_canon_sha256":"98f02fe1ea51206b62f00362ed47313fcaedb16a6802efbab6318c840477ca6e"},"schema_version":"1.0","source":{"id":"2606.04367","kind":"arxiv","version":1}},"canonical_sha256":"104074571f45899f31754cabf2af51e7d08176b66018d2e91cbaedfb24139f92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"104074571f45899f31754cabf2af51e7d08176b66018d2e91cbaedfb24139f92","first_computed_at":"2026-06-04T01:09:05.483738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:05.483738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DybxQGflPKpEqXgLSzW9KEy1VAUUSzh6gaHxlXoG8RXdd17e2l+9PB8oTsIQ6YPbh7AAcXkFn4t3xESPrrEUBA==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:05.484227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04367","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe5e6bf3c4a34b428d46b9fe1f9aad920da703911c42dd485206ab2bbf9d6760","sha256:8aa3a1345c2d2557b52b0aaa2500c7a9d6315409ba5c7be87d79a4d9a1e82e96"],"state_sha256":"8808fa15bcecaf41c6e11c4dbb0143498f54f890943043f88d8b2a5936fe4cd5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qvTW/I56O88PNDj6flIfHkubnrq4tAjYgfKQJaBRbFaWVMc8G3p/CqgL/9Dlk8i22JY+flTFuDgOP87fXJWzDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T06:48:22.238054Z","bundle_sha256":"8fd0ebd0ef3e654b5780bba48ddd2e151e4072193bd6b2febe4701047b87cb8a"}}