{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:T6FLQ2HRCBY2VFREYX56W53IHY","short_pith_number":"pith:T6FLQ2HR","canonical_record":{"source":{"id":"2201.01845","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-05T22:19:10Z","cross_cats_sorted":[],"title_canon_sha256":"d3e217d98df614651f839180b7d158f6cd8f29bd3a289778a4b41e022c3f478b","abstract_canon_sha256":"63c1b8d328335110ac9bf862f0093cb3bf2b7b55de6429fbc6afbfcbf28dcc04"},"schema_version":"1.0"},"canonical_sha256":"9f8ab868f11071aa9624c5fbeb77683e1b7a8e5a971fede10d182b18106a3ea5","source":{"kind":"arxiv","id":"2201.01845","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.01845","created_at":"2026-07-05T04:13:12Z"},{"alias_kind":"arxiv_version","alias_value":"2201.01845v2","created_at":"2026-07-05T04:13:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01845","created_at":"2026-07-05T04:13:12Z"},{"alias_kind":"pith_short_12","alias_value":"T6FLQ2HRCBY2","created_at":"2026-07-05T04:13:12Z"},{"alias_kind":"pith_short_16","alias_value":"T6FLQ2HRCBY2VFRE","created_at":"2026-07-05T04:13:12Z"},{"alias_kind":"pith_short_8","alias_value":"T6FLQ2HR","created_at":"2026-07-05T04:13:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:T6FLQ2HRCBY2VFREYX56W53IHY","target":"record","payload":{"canonical_record":{"source":{"id":"2201.01845","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-05T22:19:10Z","cross_cats_sorted":[],"title_canon_sha256":"d3e217d98df614651f839180b7d158f6cd8f29bd3a289778a4b41e022c3f478b","abstract_canon_sha256":"63c1b8d328335110ac9bf862f0093cb3bf2b7b55de6429fbc6afbfcbf28dcc04"},"schema_version":"1.0"},"canonical_sha256":"9f8ab868f11071aa9624c5fbeb77683e1b7a8e5a971fede10d182b18106a3ea5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:12.099468Z","signature_b64":"gxe2mb5XFonWzrx2ozFRrseF/75QGL3kYxML1PBP9JvCXS8P2DwX7kyAK+s8oqBuxbsRG1vQ6YJKgtCqTVI8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f8ab868f11071aa9624c5fbeb77683e1b7a8e5a971fede10d182b18106a3ea5","last_reissued_at":"2026-07-05T04:13:12.099114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:12.099114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.01845","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":"2026-07-05T04:13:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zJxLT4Rs4CYx5C9uGSLcFYMg3XXMS4YniRmUD3cxWEGaBKAGwM0ZdpjUkyaDd80Lupz83KktwV3TtTFnafUxAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T05:27:56.424727Z"},"content_sha256":"4135f6cbd0df0d0a4bc7e512a45efd312c51cd6a6db62f85c86717c4851f7f4b","schema_version":"1.0","event_id":"sha256:4135f6cbd0df0d0a4bc7e512a45efd312c51cd6a6db62f85c86717c4851f7f4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:T6FLQ2HRCBY2VFREYX56W53IHY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emily Prud'hommeaux, Zoey Liu","submitted_at":"2022-01-05T22:19:10Z","abstract_excerpt":"Common designs of model evaluation typically focus on monolingual settings, where different models are compared according to their performance on a single data set that is assumed to be representative of all possible data for the task at hand. While this may be reasonable for a large data set, this assumption is difficult to maintain in low-resource scenarios, where artifacts of the data collection can yield data sets that are outliers, potentially making conclusions about model performance coincidental. To address these concerns, we investigate model generalizability in crosslinguistic low-re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01845","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/2201.01845/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":"2026-07-05T04:13:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZxpDbGDp9lgnnEdu32VG5AF7fg3x/eMK9YLXI7rdO2ds0+lno2kfb8crSdFKse6UR+0DucNrERYBuHZmR92gCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T05:27:56.425087Z"},"content_sha256":"d58a500905b12c51514d5119f14d76f990e928d3e50b744886fa386fc2917d37","schema_version":"1.0","event_id":"sha256:d58a500905b12c51514d5119f14d76f990e928d3e50b744886fa386fc2917d37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T6FLQ2HRCBY2VFREYX56W53IHY/bundle.json","state_url":"https://pith.science/pith/T6FLQ2HRCBY2VFREYX56W53IHY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T6FLQ2HRCBY2VFREYX56W53IHY/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":"2026-07-17T05:27:56Z","links":{"resolver":"https://pith.science/pith/T6FLQ2HRCBY2VFREYX56W53IHY","bundle":"https://pith.science/pith/T6FLQ2HRCBY2VFREYX56W53IHY/bundle.json","state":"https://pith.science/pith/T6FLQ2HRCBY2VFREYX56W53IHY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T6FLQ2HRCBY2VFREYX56W53IHY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:T6FLQ2HRCBY2VFREYX56W53IHY","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":"63c1b8d328335110ac9bf862f0093cb3bf2b7b55de6429fbc6afbfcbf28dcc04","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-05T22:19:10Z","title_canon_sha256":"d3e217d98df614651f839180b7d158f6cd8f29bd3a289778a4b41e022c3f478b"},"schema_version":"1.0","source":{"id":"2201.01845","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.01845","created_at":"2026-07-05T04:13:12Z"},{"alias_kind":"arxiv_version","alias_value":"2201.01845v2","created_at":"2026-07-05T04:13:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01845","created_at":"2026-07-05T04:13:12Z"},{"alias_kind":"pith_short_12","alias_value":"T6FLQ2HRCBY2","created_at":"2026-07-05T04:13:12Z"},{"alias_kind":"pith_short_16","alias_value":"T6FLQ2HRCBY2VFRE","created_at":"2026-07-05T04:13:12Z"},{"alias_kind":"pith_short_8","alias_value":"T6FLQ2HR","created_at":"2026-07-05T04:13:12Z"}],"graph_snapshots":[{"event_id":"sha256:d58a500905b12c51514d5119f14d76f990e928d3e50b744886fa386fc2917d37","target":"graph","created_at":"2026-07-05T04:13:12Z","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/2201.01845/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Common designs of model evaluation typically focus on monolingual settings, where different models are compared according to their performance on a single data set that is assumed to be representative of all possible data for the task at hand. While this may be reasonable for a large data set, this assumption is difficult to maintain in low-resource scenarios, where artifacts of the data collection can yield data sets that are outliers, potentially making conclusions about model performance coincidental. To address these concerns, we investigate model generalizability in crosslinguistic low-re","authors_text":"Emily Prud'hommeaux, Zoey Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-05T22:19:10Z","title":"Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01845","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":"sha256:4135f6cbd0df0d0a4bc7e512a45efd312c51cd6a6db62f85c86717c4851f7f4b","target":"record","created_at":"2026-07-05T04:13:12Z","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":"63c1b8d328335110ac9bf862f0093cb3bf2b7b55de6429fbc6afbfcbf28dcc04","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-05T22:19:10Z","title_canon_sha256":"d3e217d98df614651f839180b7d158f6cd8f29bd3a289778a4b41e022c3f478b"},"schema_version":"1.0","source":{"id":"2201.01845","kind":"arxiv","version":2}},"canonical_sha256":"9f8ab868f11071aa9624c5fbeb77683e1b7a8e5a971fede10d182b18106a3ea5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f8ab868f11071aa9624c5fbeb77683e1b7a8e5a971fede10d182b18106a3ea5","first_computed_at":"2026-07-05T04:13:12.099114Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:13:12.099114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gxe2mb5XFonWzrx2ozFRrseF/75QGL3kYxML1PBP9JvCXS8P2DwX7kyAK+s8oqBuxbsRG1vQ6YJKgtCqTVI8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:13:12.099468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.01845","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4135f6cbd0df0d0a4bc7e512a45efd312c51cd6a6db62f85c86717c4851f7f4b","sha256:d58a500905b12c51514d5119f14d76f990e928d3e50b744886fa386fc2917d37"],"state_sha256":"0a11a47e46e68f3b23cc6e23fe1aaaec67b91bf06a768f9655878d738b6d6b54"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nPLACEDRgyLVyd/X52pbzkg8pJwJujBFzh2adxRi64/NjsrBTxqbq01zYkgrVUO1U8diL8JoWhKiq92yNnvhAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T05:27:56.427483Z","bundle_sha256":"bf7530a52c3967389aefa498e608503ca1d0a09dbebc3502d15ace3ff5cd69c9"}}