{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UUAXB26XLACFXBA45TWI4V6O56","short_pith_number":"pith:UUAXB26X","canonical_record":{"source":{"id":"2403.13169","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-19T21:45:29Z","cross_cats_sorted":[],"title_canon_sha256":"29e4e88b1016ae1f2b92f5e5dbe44e3074dc88be618968cc60b4bea520082912","abstract_canon_sha256":"5a8c0886a7ab3bb8997d976707b5f90f40a24a8da2bc74bb3ed1b6784fa601bd"},"schema_version":"1.0"},"canonical_sha256":"a50170ebd758045b841cecec8e57ceef9d5f7188ee9812197423be8fe2b2a578","source":{"kind":"arxiv","id":"2403.13169","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13169","created_at":"2026-07-05T08:28:08Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13169v2","created_at":"2026-07-05T08:28:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13169","created_at":"2026-07-05T08:28:08Z"},{"alias_kind":"pith_short_12","alias_value":"UUAXB26XLACF","created_at":"2026-07-05T08:28:08Z"},{"alias_kind":"pith_short_16","alias_value":"UUAXB26XLACFXBA4","created_at":"2026-07-05T08:28:08Z"},{"alias_kind":"pith_short_8","alias_value":"UUAXB26X","created_at":"2026-07-05T08:28:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UUAXB26XLACFXBA45TWI4V6O56","target":"record","payload":{"canonical_record":{"source":{"id":"2403.13169","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-19T21:45:29Z","cross_cats_sorted":[],"title_canon_sha256":"29e4e88b1016ae1f2b92f5e5dbe44e3074dc88be618968cc60b4bea520082912","abstract_canon_sha256":"5a8c0886a7ab3bb8997d976707b5f90f40a24a8da2bc74bb3ed1b6784fa601bd"},"schema_version":"1.0"},"canonical_sha256":"a50170ebd758045b841cecec8e57ceef9d5f7188ee9812197423be8fe2b2a578","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:08.763546Z","signature_b64":"x9EMzcJKmQIhk6NrgabSx6J1FkhryG+drr5CkBVPFbpET9G7lFblnNA/4B1rn8dsTR+bwBc4AbvIpg9us7kbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a50170ebd758045b841cecec8e57ceef9d5f7188ee9812197423be8fe2b2a578","last_reissued_at":"2026-07-05T08:28:08.763034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:08.763034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.13169","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":"2026-07-05T08:28:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mUSjSGb9xZqkZz275l7k7xqPZw0q/vPNNHuMdEO5O7HAyZ7d0jm25OWe/iF+1isuLVOtSYfmXYiYjCL2BfqeDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T13:48:55.392448Z"},"content_sha256":"03e155e72d05fe079aeddb3c5893c0a0db3b2ca05816a98fd00440285e8f7055","schema_version":"1.0","event_id":"sha256:03e155e72d05fe079aeddb3c5893c0a0db3b2ca05816a98fd00440285e8f7055"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UUAXB26XLACFXBA45TWI4V6O56","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wav2Gloss: Generating Interlinear Glossed Text from Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David R. Mortensen, Graham Neubig, Jiatong Shi, Kwanghee Choi, Lindia Tjuatja, Lori Levin, Nathaniel R. Robinson, Shinji Watanabe, Taiqi He","submitted_at":"2024-03-19T21:45:29Z","abstract_excerpt":"Thousands of the world's languages are in danger of extinction--a tremendous threat to cultural identities and human language diversity. Interlinear Glossed Text (IGT) is a form of linguistic annotation that can support documentation and resource creation for these languages' communities. IGT typically consists of (1) transcriptions, (2) morphological segmentation, (3) glosses, and (4) free translations to a majority language. We propose Wav2Gloss: a task in which these four annotation components are extracted automatically from speech, and introduce the first dataset to this end, Fieldwork: a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13169","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/2403.13169/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":"2026-07-05T08:28:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mT5MsWiOgTLVU5pWyjgkGdVkMLJF+H+MgfUsYW1T2KRr1Czlg+xiGrezAZNqf7zmnFQ0G2c97FU9jVy7W9lNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T13:48:55.392910Z"},"content_sha256":"643230c6afca01181776adf93607cf01ca9f7b259112524c974201e58c7c466f","schema_version":"1.0","event_id":"sha256:643230c6afca01181776adf93607cf01ca9f7b259112524c974201e58c7c466f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UUAXB26XLACFXBA45TWI4V6O56/bundle.json","state_url":"https://pith.science/pith/UUAXB26XLACFXBA45TWI4V6O56/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UUAXB26XLACFXBA45TWI4V6O56/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":"2026-07-12T13:48:55Z","links":{"resolver":"https://pith.science/pith/UUAXB26XLACFXBA45TWI4V6O56","bundle":"https://pith.science/pith/UUAXB26XLACFXBA45TWI4V6O56/bundle.json","state":"https://pith.science/pith/UUAXB26XLACFXBA45TWI4V6O56/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UUAXB26XLACFXBA45TWI4V6O56/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UUAXB26XLACFXBA45TWI4V6O56","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":"5a8c0886a7ab3bb8997d976707b5f90f40a24a8da2bc74bb3ed1b6784fa601bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-19T21:45:29Z","title_canon_sha256":"29e4e88b1016ae1f2b92f5e5dbe44e3074dc88be618968cc60b4bea520082912"},"schema_version":"1.0","source":{"id":"2403.13169","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13169","created_at":"2026-07-05T08:28:08Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13169v2","created_at":"2026-07-05T08:28:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13169","created_at":"2026-07-05T08:28:08Z"},{"alias_kind":"pith_short_12","alias_value":"UUAXB26XLACF","created_at":"2026-07-05T08:28:08Z"},{"alias_kind":"pith_short_16","alias_value":"UUAXB26XLACFXBA4","created_at":"2026-07-05T08:28:08Z"},{"alias_kind":"pith_short_8","alias_value":"UUAXB26X","created_at":"2026-07-05T08:28:08Z"}],"graph_snapshots":[{"event_id":"sha256:643230c6afca01181776adf93607cf01ca9f7b259112524c974201e58c7c466f","target":"graph","created_at":"2026-07-05T08:28:08Z","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/2403.13169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Thousands of the world's languages are in danger of extinction--a tremendous threat to cultural identities and human language diversity. Interlinear Glossed Text (IGT) is a form of linguistic annotation that can support documentation and resource creation for these languages' communities. IGT typically consists of (1) transcriptions, (2) morphological segmentation, (3) glosses, and (4) free translations to a majority language. We propose Wav2Gloss: a task in which these four annotation components are extracted automatically from speech, and introduce the first dataset to this end, Fieldwork: a","authors_text":"David R. Mortensen, Graham Neubig, Jiatong Shi, Kwanghee Choi, Lindia Tjuatja, Lori Levin, Nathaniel R. Robinson, Shinji Watanabe, Taiqi He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-19T21:45:29Z","title":"Wav2Gloss: Generating Interlinear Glossed Text from Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13169","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":"sha256:03e155e72d05fe079aeddb3c5893c0a0db3b2ca05816a98fd00440285e8f7055","target":"record","created_at":"2026-07-05T08:28:08Z","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":"5a8c0886a7ab3bb8997d976707b5f90f40a24a8da2bc74bb3ed1b6784fa601bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-19T21:45:29Z","title_canon_sha256":"29e4e88b1016ae1f2b92f5e5dbe44e3074dc88be618968cc60b4bea520082912"},"schema_version":"1.0","source":{"id":"2403.13169","kind":"arxiv","version":2}},"canonical_sha256":"a50170ebd758045b841cecec8e57ceef9d5f7188ee9812197423be8fe2b2a578","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a50170ebd758045b841cecec8e57ceef9d5f7188ee9812197423be8fe2b2a578","first_computed_at":"2026-07-05T08:28:08.763034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:08.763034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x9EMzcJKmQIhk6NrgabSx6J1FkhryG+drr5CkBVPFbpET9G7lFblnNA/4B1rn8dsTR+bwBc4AbvIpg9us7kbBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:08.763546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.13169","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03e155e72d05fe079aeddb3c5893c0a0db3b2ca05816a98fd00440285e8f7055","sha256:643230c6afca01181776adf93607cf01ca9f7b259112524c974201e58c7c466f"],"state_sha256":"b50f4384e0773df3e084ca0ce73912e37111abc6e4957cf90ca11e7f1ecb79f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tQgr6FzM5YD5LNqO0Iykhs7P0D/Ge+GZNEWCiX6Ef3Kaiy98/ND1f5hT/wwO9VYRYy2dBIs80lADgiuIxqi7Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T13:48:55.395486Z","bundle_sha256":"5a0e94006b2782864e00554382c54fd8edaa50b261174fc78f91393f2d387f6c"}}