{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M2J27UWKR3QA3ZR5VQ562EUZZJ","short_pith_number":"pith:M2J27UWK","canonical_record":{"source":{"id":"2403.06399","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T03:21:15Z","cross_cats_sorted":[],"title_canon_sha256":"24b3b5b6c74c844f18c66d74f9f96ccacb85ba218dd6b71a83c1f45bcc5f36e6","abstract_canon_sha256":"b9e2f6408b9689017acf955575849dd4e633e4526c78d77f1b0f158f8c72de92"},"schema_version":"1.0"},"canonical_sha256":"6693afd2ca8ee00de63dac3bed1299ca5219910db37a05a750b19f0f8b15df79","source":{"kind":"arxiv","id":"2403.06399","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06399","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06399v3","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06399","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_12","alias_value":"M2J27UWKR3QA","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_16","alias_value":"M2J27UWKR3QA3ZR5","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_8","alias_value":"M2J27UWK","created_at":"2026-07-05T09:34:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M2J27UWKR3QA3ZR5VQ562EUZZJ","target":"record","payload":{"canonical_record":{"source":{"id":"2403.06399","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T03:21:15Z","cross_cats_sorted":[],"title_canon_sha256":"24b3b5b6c74c844f18c66d74f9f96ccacb85ba218dd6b71a83c1f45bcc5f36e6","abstract_canon_sha256":"b9e2f6408b9689017acf955575849dd4e633e4526c78d77f1b0f158f8c72de92"},"schema_version":"1.0"},"canonical_sha256":"6693afd2ca8ee00de63dac3bed1299ca5219910db37a05a750b19f0f8b15df79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:35.046645Z","signature_b64":"4WWDMu9TCflfsBr46wmVpuPra4e09G50t8lT+4fzBWCE62uyzyayomJsb80YmLiPOrc0kkj9j82h/Ejgj8//Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6693afd2ca8ee00de63dac3bed1299ca5219910db37a05a750b19f0f8b15df79","last_reissued_at":"2026-07-05T09:34:35.046103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:35.046103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.06399","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:34:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qfgUSBthBzFAC0Ihk+qLKni44O7/1nnyggvfxR/jjsjap/Qg6ujRiTbiC55QmpvfA1CpHIFCcMFEaYpz3XftAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:45:03.466760Z"},"content_sha256":"b196b14bee777158a0a652014423b9bde5a900d7211e822a4ec4578a803a8204","schema_version":"1.0","event_id":"sha256:b196b14bee777158a0a652014423b9bde5a900d7211e822a4ec4578a803a8204"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M2J27UWKR3QA3ZR5VQ562EUZZJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"(2) Carnegie Mellon University), Alexis Palmer (1), Enora Rice (1), Graham Neubig (2), Lindia Tjuatja (2), Lori Levin (2) ((1) University of Colorado, Michael Ginn (1), Taiqi He (2)","submitted_at":"2024-03-11T03:21:15Z","abstract_excerpt":"Language documentation projects often involve the creation of annotated text in a format such as interlinear glossed text (IGT), which captures fine-grained morphosyntactic analyses in a morpheme-by-morpheme format. However, there are few existing resources providing large amounts of standardized, easily accessible IGT data, limiting their applicability to linguistic research, and making it difficult to use such data in NLP modeling.\n  We compile the largest existing corpus of IGT data from a variety of sources, covering over 450k examples across 1.8k languages, to enable research on crossling"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06399","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/2403.06399/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":"2026-07-05T09:34:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+T2gIoe021mW6I5WSLXASduGeWtug0z3gZk+NhNaI9McdEaVgtQ3Z8CkwktQU1xEYMWXay1loEiB1AEF7xF8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:45:03.467779Z"},"content_sha256":"63e4a70a487562807bae3bbcad0e8f1c6d21c03f7661f38fee19ea01de1656ad","schema_version":"1.0","event_id":"sha256:63e4a70a487562807bae3bbcad0e8f1c6d21c03f7661f38fee19ea01de1656ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M2J27UWKR3QA3ZR5VQ562EUZZJ/bundle.json","state_url":"https://pith.science/pith/M2J27UWKR3QA3ZR5VQ562EUZZJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M2J27UWKR3QA3ZR5VQ562EUZZJ/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":"2026-08-11T00:45:03Z","links":{"resolver":"https://pith.science/pith/M2J27UWKR3QA3ZR5VQ562EUZZJ","bundle":"https://pith.science/pith/M2J27UWKR3QA3ZR5VQ562EUZZJ/bundle.json","state":"https://pith.science/pith/M2J27UWKR3QA3ZR5VQ562EUZZJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M2J27UWKR3QA3ZR5VQ562EUZZJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M2J27UWKR3QA3ZR5VQ562EUZZJ","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":"b9e2f6408b9689017acf955575849dd4e633e4526c78d77f1b0f158f8c72de92","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T03:21:15Z","title_canon_sha256":"24b3b5b6c74c844f18c66d74f9f96ccacb85ba218dd6b71a83c1f45bcc5f36e6"},"schema_version":"1.0","source":{"id":"2403.06399","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06399","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06399v3","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06399","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_12","alias_value":"M2J27UWKR3QA","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_16","alias_value":"M2J27UWKR3QA3ZR5","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_8","alias_value":"M2J27UWK","created_at":"2026-07-05T09:34:35Z"}],"graph_snapshots":[{"event_id":"sha256:63e4a70a487562807bae3bbcad0e8f1c6d21c03f7661f38fee19ea01de1656ad","target":"graph","created_at":"2026-07-05T09:34:35Z","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/2403.06399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language documentation projects often involve the creation of annotated text in a format such as interlinear glossed text (IGT), which captures fine-grained morphosyntactic analyses in a morpheme-by-morpheme format. However, there are few existing resources providing large amounts of standardized, easily accessible IGT data, limiting their applicability to linguistic research, and making it difficult to use such data in NLP modeling.\n  We compile the largest existing corpus of IGT data from a variety of sources, covering over 450k examples across 1.8k languages, to enable research on crossling","authors_text":"(2) Carnegie Mellon University), Alexis Palmer (1), Enora Rice (1), Graham Neubig (2), Lindia Tjuatja (2), Lori Levin (2) ((1) University of Colorado, Michael Ginn (1), Taiqi He (2)","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T03:21:15Z","title":"GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06399","kind":"arxiv","version":3},"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:b196b14bee777158a0a652014423b9bde5a900d7211e822a4ec4578a803a8204","target":"record","created_at":"2026-07-05T09:34:35Z","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":"b9e2f6408b9689017acf955575849dd4e633e4526c78d77f1b0f158f8c72de92","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T03:21:15Z","title_canon_sha256":"24b3b5b6c74c844f18c66d74f9f96ccacb85ba218dd6b71a83c1f45bcc5f36e6"},"schema_version":"1.0","source":{"id":"2403.06399","kind":"arxiv","version":3}},"canonical_sha256":"6693afd2ca8ee00de63dac3bed1299ca5219910db37a05a750b19f0f8b15df79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6693afd2ca8ee00de63dac3bed1299ca5219910db37a05a750b19f0f8b15df79","first_computed_at":"2026-07-05T09:34:35.046103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:35.046103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4WWDMu9TCflfsBr46wmVpuPra4e09G50t8lT+4fzBWCE62uyzyayomJsb80YmLiPOrc0kkj9j82h/Ejgj8//Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:35.046645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06399","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b196b14bee777158a0a652014423b9bde5a900d7211e822a4ec4578a803a8204","sha256:63e4a70a487562807bae3bbcad0e8f1c6d21c03f7661f38fee19ea01de1656ad"],"state_sha256":"b74823ae4e7a80aca8949ddb51f1dac3dfa77caf88d4186915e210bbc6f09677"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v45ifJvp+3tDtgNVlYvsP3h7OK5cXcqWuC+fV1LTNxLkVhKavcU/s03bJH7Y3+5ADrUo25nCd4xjF6nWx58sDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T00:45:03.474191Z","bundle_sha256":"29eaeb18bf99616d17c149fec8e3e479b638b4ab0f63e4bf8cb8c4b99ae9140e"}}