{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OGWUAGYN7KMV7JKT3PWBUTXX7P","short_pith_number":"pith:OGWUAGYN","canonical_record":{"source":{"id":"2404.09371","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-14T22:22:58Z","cross_cats_sorted":[],"title_canon_sha256":"6b6a93b9facaaa3f704ef557a71499967a3aee9f9cf074be69bd0985507d79a2","abstract_canon_sha256":"77d0dc95c6128a413dd1fd03ceea469d9c6eb5ed5c9cead8a5c14f4c78540c5b"},"schema_version":"1.0"},"canonical_sha256":"71ad401b0dfa995fa553dbec1a4ef7fbe85a6a06334fa0a5a76acbdfbbaa0439","source":{"kind":"arxiv","id":"2404.09371","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09371","created_at":"2026-07-05T08:08:05Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09371v1","created_at":"2026-07-05T08:08:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09371","created_at":"2026-07-05T08:08:05Z"},{"alias_kind":"pith_short_12","alias_value":"OGWUAGYN7KMV","created_at":"2026-07-05T08:08:05Z"},{"alias_kind":"pith_short_16","alias_value":"OGWUAGYN7KMV7JKT","created_at":"2026-07-05T08:08:05Z"},{"alias_kind":"pith_short_8","alias_value":"OGWUAGYN","created_at":"2026-07-05T08:08:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OGWUAGYN7KMV7JKT3PWBUTXX7P","target":"record","payload":{"canonical_record":{"source":{"id":"2404.09371","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-14T22:22:58Z","cross_cats_sorted":[],"title_canon_sha256":"6b6a93b9facaaa3f704ef557a71499967a3aee9f9cf074be69bd0985507d79a2","abstract_canon_sha256":"77d0dc95c6128a413dd1fd03ceea469d9c6eb5ed5c9cead8a5c14f4c78540c5b"},"schema_version":"1.0"},"canonical_sha256":"71ad401b0dfa995fa553dbec1a4ef7fbe85a6a06334fa0a5a76acbdfbbaa0439","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:05.528343Z","signature_b64":"NnxuySI4KkcwR6PMYNbXmZIdI0dpRnHQ0smgs2Au2+ONkvblmNqabTaGIVdt64MnpPJthPJHSuRcHw5PCLvIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71ad401b0dfa995fa553dbec1a4ef7fbe85a6a06334fa0a5a76acbdfbbaa0439","last_reissued_at":"2026-07-05T08:08:05.527853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:05.527853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.09371","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":"2026-07-05T08:08:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eh9Fs/umGHTvIw0weV7cA+ClkscgBg9HIeK/MM7PoF3hcuyC9b5BBD1eXsdQixc9JZCUDoT+RYkVMGu1F6jfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:48:55.507136Z"},"content_sha256":"4734073e49cf8a497251b297280f3689d0b36d2562232401915f49cc5a995068","schema_version":"1.0","event_id":"sha256:4734073e49cf8a497251b297280f3689d0b36d2562232401915f49cc5a995068"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OGWUAGYN7KMV7JKT3PWBUTXX7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Effect of Data Partitioning Strategy on Model Generalizability: A Case Study of Morphological Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bonnie J. Dorr, Zoey Liu","submitted_at":"2024-04-14T22:22:58Z","abstract_excerpt":"Recent work to enhance data partitioning strategies for more realistic model evaluation face challenges in providing a clear optimal choice. This study addresses these challenges, focusing on morphological segmentation and synthesizing limitations related to language diversity, adoption of multiple datasets and splits, and detailed model comparisons. Our study leverages data from 19 languages, including ten indigenous or endangered languages across 10 language families with diverse morphological systems (polysynthetic, fusional, and agglutinative) and different degrees of data availability. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09371","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/2404.09371/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":"2026-07-05T08:08:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZbU1r6zjfQImUwmbBOaUmujK2+22Mp01ulJItCT9BC0DE4fMjB4ilQk9unT8djOAJrxkm3QiR97TGepaogcACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:48:55.508057Z"},"content_sha256":"4a86a63815f1c5794b45c594023149674120e9b2bb165bfce676e9b927b5ce6d","schema_version":"1.0","event_id":"sha256:4a86a63815f1c5794b45c594023149674120e9b2bb165bfce676e9b927b5ce6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OGWUAGYN7KMV7JKT3PWBUTXX7P/bundle.json","state_url":"https://pith.science/pith/OGWUAGYN7KMV7JKT3PWBUTXX7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OGWUAGYN7KMV7JKT3PWBUTXX7P/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":"2026-08-05T01:48:55Z","links":{"resolver":"https://pith.science/pith/OGWUAGYN7KMV7JKT3PWBUTXX7P","bundle":"https://pith.science/pith/OGWUAGYN7KMV7JKT3PWBUTXX7P/bundle.json","state":"https://pith.science/pith/OGWUAGYN7KMV7JKT3PWBUTXX7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OGWUAGYN7KMV7JKT3PWBUTXX7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OGWUAGYN7KMV7JKT3PWBUTXX7P","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":"77d0dc95c6128a413dd1fd03ceea469d9c6eb5ed5c9cead8a5c14f4c78540c5b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-14T22:22:58Z","title_canon_sha256":"6b6a93b9facaaa3f704ef557a71499967a3aee9f9cf074be69bd0985507d79a2"},"schema_version":"1.0","source":{"id":"2404.09371","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09371","created_at":"2026-07-05T08:08:05Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09371v1","created_at":"2026-07-05T08:08:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09371","created_at":"2026-07-05T08:08:05Z"},{"alias_kind":"pith_short_12","alias_value":"OGWUAGYN7KMV","created_at":"2026-07-05T08:08:05Z"},{"alias_kind":"pith_short_16","alias_value":"OGWUAGYN7KMV7JKT","created_at":"2026-07-05T08:08:05Z"},{"alias_kind":"pith_short_8","alias_value":"OGWUAGYN","created_at":"2026-07-05T08:08:05Z"}],"graph_snapshots":[{"event_id":"sha256:4a86a63815f1c5794b45c594023149674120e9b2bb165bfce676e9b927b5ce6d","target":"graph","created_at":"2026-07-05T08:08:05Z","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/2404.09371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work to enhance data partitioning strategies for more realistic model evaluation face challenges in providing a clear optimal choice. This study addresses these challenges, focusing on morphological segmentation and synthesizing limitations related to language diversity, adoption of multiple datasets and splits, and detailed model comparisons. Our study leverages data from 19 languages, including ten indigenous or endangered languages across 10 language families with diverse morphological systems (polysynthetic, fusional, and agglutinative) and different degrees of data availability. We","authors_text":"Bonnie J. Dorr, Zoey Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-14T22:22:58Z","title":"The Effect of Data Partitioning Strategy on Model Generalizability: A Case Study of Morphological Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09371","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":"sha256:4734073e49cf8a497251b297280f3689d0b36d2562232401915f49cc5a995068","target":"record","created_at":"2026-07-05T08:08:05Z","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":"77d0dc95c6128a413dd1fd03ceea469d9c6eb5ed5c9cead8a5c14f4c78540c5b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-14T22:22:58Z","title_canon_sha256":"6b6a93b9facaaa3f704ef557a71499967a3aee9f9cf074be69bd0985507d79a2"},"schema_version":"1.0","source":{"id":"2404.09371","kind":"arxiv","version":1}},"canonical_sha256":"71ad401b0dfa995fa553dbec1a4ef7fbe85a6a06334fa0a5a76acbdfbbaa0439","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71ad401b0dfa995fa553dbec1a4ef7fbe85a6a06334fa0a5a76acbdfbbaa0439","first_computed_at":"2026-07-05T08:08:05.527853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:05.527853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NnxuySI4KkcwR6PMYNbXmZIdI0dpRnHQ0smgs2Au2+ONkvblmNqabTaGIVdt64MnpPJthPJHSuRcHw5PCLvIAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:05.528343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09371","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4734073e49cf8a497251b297280f3689d0b36d2562232401915f49cc5a995068","sha256:4a86a63815f1c5794b45c594023149674120e9b2bb165bfce676e9b927b5ce6d"],"state_sha256":"3b4ab55644cad965c22ef0abbec6f6dabefebfa9029ca97cef22c6ff9b67d4df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QBpERtSPwsLyx8s2DJUolD5+TvNQrN1zKrLDoWGN/82pJ+GHjwanxl8LgewIhtsjeOUZkFb0pVNIZ5UhvYysAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:48:55.514669Z","bundle_sha256":"a1578e1b1e830ff036b4939feea9c2dd1248dbc44787274d5c132205ddda7ab1"}}