{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XYTTGTQNJZNK7N2J4UNUE6X5QK","short_pith_number":"pith:XYTTGTQN","canonical_record":{"source":{"id":"2302.07912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-15T19:06:17Z","cross_cats_sorted":[],"title_canon_sha256":"b04ecf59796efd1385b21baa09a8a7f5370ddd6008e96d60a6095856cbb1238b","abstract_canon_sha256":"4ed3c5a2f758ceea07c6b680a93943db866ed757218b8ce12153f345bd0e5792"},"schema_version":"1.0"},"canonical_sha256":"be27334e0d4e5aafb749e51b427afd82ac63ea7f9cd42a33704e9480dc8cfb4e","source":{"kind":"arxiv","id":"2302.07912","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.07912","created_at":"2026-07-05T05:42:31Z"},{"alias_kind":"arxiv_version","alias_value":"2302.07912v1","created_at":"2026-07-05T05:42:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07912","created_at":"2026-07-05T05:42:31Z"},{"alias_kind":"pith_short_12","alias_value":"XYTTGTQNJZNK","created_at":"2026-07-05T05:42:31Z"},{"alias_kind":"pith_short_16","alias_value":"XYTTGTQNJZNK7N2J","created_at":"2026-07-05T05:42:31Z"},{"alias_kind":"pith_short_8","alias_value":"XYTTGTQN","created_at":"2026-07-05T05:42:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XYTTGTQNJZNK7N2J4UNUE6X5QK","target":"record","payload":{"canonical_record":{"source":{"id":"2302.07912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-15T19:06:17Z","cross_cats_sorted":[],"title_canon_sha256":"b04ecf59796efd1385b21baa09a8a7f5370ddd6008e96d60a6095856cbb1238b","abstract_canon_sha256":"4ed3c5a2f758ceea07c6b680a93943db866ed757218b8ce12153f345bd0e5792"},"schema_version":"1.0"},"canonical_sha256":"be27334e0d4e5aafb749e51b427afd82ac63ea7f9cd42a33704e9480dc8cfb4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:31.804760Z","signature_b64":"W7RaYw9URiGk6vEw0rCkRzy3zpL15YSLsgtUL/vLyhWtvNAmUyDlPzFX0t7ud599LVtX9Gk3tqq58IyeUHXFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be27334e0d4e5aafb749e51b427afd82ac63ea7f9cd42a33704e9480dc8cfb4e","last_reissued_at":"2026-07-05T05:42:31.804282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:31.804282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.07912","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":"2026-07-05T05:42:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gBEO6Jfoyagp+mMLLcqnKXH+Ih62ZLJs7D47tUGP8ECdOSKI/zJ9PfU+zvQpCh6jEi2Imsymei7AtdjEodfLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:59:04.435366Z"},"content_sha256":"dc1eaee3f3e722eaadd77117c96bd80b58b43c7e465762981ed32b96a83061fc","schema_version":"1.0","event_id":"sha256:dc1eaee3f3e722eaadd77117c96bd80b58b43c7e465762981ed32b96a83061fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XYTTGTQNJZNK7N2J4UNUE6X5QK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abteen Ebrahimi, Arturo Oncevay, Arya D. McCarthy, Gustavo A. Gim\\'enez-Lugo, John E. Ortega, Katharina Kann, Luis Chiruzzo, Rolando Coto-Solano","submitted_at":"2023-02-15T19:06:17Z","abstract_excerpt":"Large multilingual models have inspired a new class of word alignment methods, which work well for the model's pretraining languages. However, the languages most in need of automatic alignment are low-resource and, thus, not typically included in the pretraining data. In this work, we ask: How do modern aligners perform on unseen languages, and are they better than traditional methods? We contribute gold-standard alignments for Bribri--Spanish, Guarani--Spanish, Quechua--Spanish, and Shipibo-Konibo--Spanish. With these, we evaluate state-of-the-art aligners with and without model adaptation to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07912","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/2302.07912/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":"2026-07-05T05:42:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HJeNQrW4c/w/Ax1V9MbXy9plErrGH95RZUCMVoQWAZAOEvW+P4D3zsCZ6XMTaCYt/GA1Lv1kAxWZqib74Q4xDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:59:04.436387Z"},"content_sha256":"9ae76c7e85bc82c6230e688f37a3474c1c386fb5bf4f35f3e33a23f0da01a4b5","schema_version":"1.0","event_id":"sha256:9ae76c7e85bc82c6230e688f37a3474c1c386fb5bf4f35f3e33a23f0da01a4b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK/bundle.json","state_url":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK/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":"2026-08-15T18:59:04Z","links":{"resolver":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK","bundle":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK/bundle.json","state":"https://pith.science/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XYTTGTQNJZNK7N2J4UNUE6X5QK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XYTTGTQNJZNK7N2J4UNUE6X5QK","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":"4ed3c5a2f758ceea07c6b680a93943db866ed757218b8ce12153f345bd0e5792","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-15T19:06:17Z","title_canon_sha256":"b04ecf59796efd1385b21baa09a8a7f5370ddd6008e96d60a6095856cbb1238b"},"schema_version":"1.0","source":{"id":"2302.07912","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.07912","created_at":"2026-07-05T05:42:31Z"},{"alias_kind":"arxiv_version","alias_value":"2302.07912v1","created_at":"2026-07-05T05:42:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07912","created_at":"2026-07-05T05:42:31Z"},{"alias_kind":"pith_short_12","alias_value":"XYTTGTQNJZNK","created_at":"2026-07-05T05:42:31Z"},{"alias_kind":"pith_short_16","alias_value":"XYTTGTQNJZNK7N2J","created_at":"2026-07-05T05:42:31Z"},{"alias_kind":"pith_short_8","alias_value":"XYTTGTQN","created_at":"2026-07-05T05:42:31Z"}],"graph_snapshots":[{"event_id":"sha256:9ae76c7e85bc82c6230e688f37a3474c1c386fb5bf4f35f3e33a23f0da01a4b5","target":"graph","created_at":"2026-07-05T05:42:31Z","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/2302.07912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large multilingual models have inspired a new class of word alignment methods, which work well for the model's pretraining languages. However, the languages most in need of automatic alignment are low-resource and, thus, not typically included in the pretraining data. In this work, we ask: How do modern aligners perform on unseen languages, and are they better than traditional methods? We contribute gold-standard alignments for Bribri--Spanish, Guarani--Spanish, Quechua--Spanish, and Shipibo-Konibo--Spanish. With these, we evaluate state-of-the-art aligners with and without model adaptation to","authors_text":"Abteen Ebrahimi, Arturo Oncevay, Arya D. McCarthy, Gustavo A. Gim\\'enez-Lugo, John E. Ortega, Katharina Kann, Luis Chiruzzo, Rolando Coto-Solano","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-15T19:06:17Z","title":"Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07912","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:dc1eaee3f3e722eaadd77117c96bd80b58b43c7e465762981ed32b96a83061fc","target":"record","created_at":"2026-07-05T05:42:31Z","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":"4ed3c5a2f758ceea07c6b680a93943db866ed757218b8ce12153f345bd0e5792","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-15T19:06:17Z","title_canon_sha256":"b04ecf59796efd1385b21baa09a8a7f5370ddd6008e96d60a6095856cbb1238b"},"schema_version":"1.0","source":{"id":"2302.07912","kind":"arxiv","version":1}},"canonical_sha256":"be27334e0d4e5aafb749e51b427afd82ac63ea7f9cd42a33704e9480dc8cfb4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be27334e0d4e5aafb749e51b427afd82ac63ea7f9cd42a33704e9480dc8cfb4e","first_computed_at":"2026-07-05T05:42:31.804282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:42:31.804282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W7RaYw9URiGk6vEw0rCkRzy3zpL15YSLsgtUL/vLyhWtvNAmUyDlPzFX0t7ud599LVtX9Gk3tqq58IyeUHXFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:42:31.804760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.07912","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc1eaee3f3e722eaadd77117c96bd80b58b43c7e465762981ed32b96a83061fc","sha256:9ae76c7e85bc82c6230e688f37a3474c1c386fb5bf4f35f3e33a23f0da01a4b5"],"state_sha256":"442a01e2588b119563e4d50a148e57b5c64402b53c9f46db57c3b5ce20783931"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HW3h9mSCU3oDeiDgYpniM14o7KTzQgbF72ywy1I94bLJ9DRwu2lXVdW4ouurm8Z0uzqF5KDjEAVriFU5lWC9Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T18:59:04.513500Z","bundle_sha256":"2a0ed689770e83294257aef0d2debfc7831f9fda3baa765378ee907adce6dfe0"}}