{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MVBYRZEKWCY3ZUBSDPPQZJGCAK","short_pith_number":"pith:MVBYRZEK","canonical_record":{"source":{"id":"2406.11085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T22:01:15Z","cross_cats_sorted":[],"title_canon_sha256":"c9b0ca3965ff8a0476e7d8645d14f3cefe3fed355f497a922bc222fc27bb4bad","abstract_canon_sha256":"0a43a8193f5a32b414146ba03d71a3eedd4d271ac8a1d5e544fa076f7f3e37ed"},"schema_version":"1.0"},"canonical_sha256":"654388e48ab0b1bcd0321bdf0ca4c202aab54da9ac0c81bc6b6ac39a7817b224","source":{"kind":"arxiv","id":"2406.11085","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11085","created_at":"2026-07-05T08:32:48Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11085v1","created_at":"2026-07-05T08:32:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11085","created_at":"2026-07-05T08:32:48Z"},{"alias_kind":"pith_short_12","alias_value":"MVBYRZEKWCY3","created_at":"2026-07-05T08:32:48Z"},{"alias_kind":"pith_short_16","alias_value":"MVBYRZEKWCY3ZUBS","created_at":"2026-07-05T08:32:48Z"},{"alias_kind":"pith_short_8","alias_value":"MVBYRZEK","created_at":"2026-07-05T08:32:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MVBYRZEKWCY3ZUBSDPPQZJGCAK","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T22:01:15Z","cross_cats_sorted":[],"title_canon_sha256":"c9b0ca3965ff8a0476e7d8645d14f3cefe3fed355f497a922bc222fc27bb4bad","abstract_canon_sha256":"0a43a8193f5a32b414146ba03d71a3eedd4d271ac8a1d5e544fa076f7f3e37ed"},"schema_version":"1.0"},"canonical_sha256":"654388e48ab0b1bcd0321bdf0ca4c202aab54da9ac0c81bc6b6ac39a7817b224","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:48.772180Z","signature_b64":"25P2ULkh8zRGL7luh/HMTgD8rWQd4vDhQZfmusSI2P2ZGbnft5C7WYzKi79cvOOf9hbndacMKgBPRgrIg9+EBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"654388e48ab0b1bcd0321bdf0ca4c202aab54da9ac0c81bc6b6ac39a7817b224","last_reissued_at":"2026-07-05T08:32:48.771616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:48.771616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11085","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":"2026-07-05T08:32:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"13DAXcYchE7LBaTGRYsfQmIJ8Pb42hwnHeiN22SrQTPraSDTh/JAHAgJpod+EiSZfUAtpKMxypVd7BZiWWvMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:05:53.287625Z"},"content_sha256":"42f767a791ca6572644244d60314ba64d2eaa3ed31a824e3a3cf3a26cfbd1f74","schema_version":"1.0","event_id":"sha256:42f767a791ca6572644244d60314ba64d2eaa3ed31a824e3a3cf3a26cfbd1f74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MVBYRZEKWCY3ZUBSDPPQZJGCAK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multiple Sources are Better Than One: Incorporating External Knowledge in Low-Resource Glossing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changbing Yang, Garrett Nicolai, Miikka Silfverberg","submitted_at":"2024-06-16T22:01:15Z","abstract_excerpt":"In this paper, we address the data scarcity problem in automatic data-driven glossing for low-resource languages by coordinating multiple sources of linguistic expertise. We supplement models with translations at both the token and sentence level as well as leverage the extensive linguistic capability of modern LLMs. Our enhancements lead to an average absolute improvement of 5%-points in word-level accuracy over the previous state of the art on a typologically diverse dataset spanning six low-resource languages. The improvements are particularly noticeable for the lowest-resourced language Gi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11085","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/2406.11085/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":"2026-07-05T08:32:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0rLlfyQpghKZxZUwkFZ0+91aD9wTuVHpnkUCe3gUAkB6T7frI5z1SE5RouWHPRkBh4qFi28YztBOxxwAkNh5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:05:53.288111Z"},"content_sha256":"6d6ae2995501eaecbbedb6d3fdba6a12c1382708d906036c6d204673263d6833","schema_version":"1.0","event_id":"sha256:6d6ae2995501eaecbbedb6d3fdba6a12c1382708d906036c6d204673263d6833"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MVBYRZEKWCY3ZUBSDPPQZJGCAK/bundle.json","state_url":"https://pith.science/pith/MVBYRZEKWCY3ZUBSDPPQZJGCAK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MVBYRZEKWCY3ZUBSDPPQZJGCAK/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":"2026-08-20T20:05:53Z","links":{"resolver":"https://pith.science/pith/MVBYRZEKWCY3ZUBSDPPQZJGCAK","bundle":"https://pith.science/pith/MVBYRZEKWCY3ZUBSDPPQZJGCAK/bundle.json","state":"https://pith.science/pith/MVBYRZEKWCY3ZUBSDPPQZJGCAK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MVBYRZEKWCY3ZUBSDPPQZJGCAK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MVBYRZEKWCY3ZUBSDPPQZJGCAK","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":"0a43a8193f5a32b414146ba03d71a3eedd4d271ac8a1d5e544fa076f7f3e37ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T22:01:15Z","title_canon_sha256":"c9b0ca3965ff8a0476e7d8645d14f3cefe3fed355f497a922bc222fc27bb4bad"},"schema_version":"1.0","source":{"id":"2406.11085","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11085","created_at":"2026-07-05T08:32:48Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11085v1","created_at":"2026-07-05T08:32:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11085","created_at":"2026-07-05T08:32:48Z"},{"alias_kind":"pith_short_12","alias_value":"MVBYRZEKWCY3","created_at":"2026-07-05T08:32:48Z"},{"alias_kind":"pith_short_16","alias_value":"MVBYRZEKWCY3ZUBS","created_at":"2026-07-05T08:32:48Z"},{"alias_kind":"pith_short_8","alias_value":"MVBYRZEK","created_at":"2026-07-05T08:32:48Z"}],"graph_snapshots":[{"event_id":"sha256:6d6ae2995501eaecbbedb6d3fdba6a12c1382708d906036c6d204673263d6833","target":"graph","created_at":"2026-07-05T08:32:48Z","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/2406.11085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we address the data scarcity problem in automatic data-driven glossing for low-resource languages by coordinating multiple sources of linguistic expertise. We supplement models with translations at both the token and sentence level as well as leverage the extensive linguistic capability of modern LLMs. Our enhancements lead to an average absolute improvement of 5%-points in word-level accuracy over the previous state of the art on a typologically diverse dataset spanning six low-resource languages. The improvements are particularly noticeable for the lowest-resourced language Gi","authors_text":"Changbing Yang, Garrett Nicolai, Miikka Silfverberg","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T22:01:15Z","title":"Multiple Sources are Better Than One: Incorporating External Knowledge in Low-Resource Glossing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11085","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":"sha256:42f767a791ca6572644244d60314ba64d2eaa3ed31a824e3a3cf3a26cfbd1f74","target":"record","created_at":"2026-07-05T08:32:48Z","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":"0a43a8193f5a32b414146ba03d71a3eedd4d271ac8a1d5e544fa076f7f3e37ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T22:01:15Z","title_canon_sha256":"c9b0ca3965ff8a0476e7d8645d14f3cefe3fed355f497a922bc222fc27bb4bad"},"schema_version":"1.0","source":{"id":"2406.11085","kind":"arxiv","version":1}},"canonical_sha256":"654388e48ab0b1bcd0321bdf0ca4c202aab54da9ac0c81bc6b6ac39a7817b224","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"654388e48ab0b1bcd0321bdf0ca4c202aab54da9ac0c81bc6b6ac39a7817b224","first_computed_at":"2026-07-05T08:32:48.771616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:48.771616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"25P2ULkh8zRGL7luh/HMTgD8rWQd4vDhQZfmusSI2P2ZGbnft5C7WYzKi79cvOOf9hbndacMKgBPRgrIg9+EBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:48.772180Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11085","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42f767a791ca6572644244d60314ba64d2eaa3ed31a824e3a3cf3a26cfbd1f74","sha256:6d6ae2995501eaecbbedb6d3fdba6a12c1382708d906036c6d204673263d6833"],"state_sha256":"ce18ec9f2de01e21d2152dfa62e76ba6cd27d994198e72c71cee0fd49149c2ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZMlFSeV6bvRmf3MY5knlGqozEYjnNWqEVuLpP7DLMHR84O+2A9yNbBG64EcjELyecrWdkYr3tw/8jO99z57ECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T20:05:53.291429Z","bundle_sha256":"9f32fbf95742f92502e6b84faafa97c2adc20c03c4904b3485c4203e9375e731"}}