{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XGKXILTHFIVDVP4GTY32T3U22J","short_pith_number":"pith:XGKXILTH","canonical_record":{"source":{"id":"2501.03855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T15:13:45Z","cross_cats_sorted":[],"title_canon_sha256":"d2a31a6a268e69432e37fb7b93ba6a8d652aecf3772dd3fa45b8669a76ec3235","abstract_canon_sha256":"9c237a39d1057979cf7159e6f9b24e356c2b2ffd62d66efb0619f64d3106c24f"},"schema_version":"1.0"},"canonical_sha256":"b995742e672a2a3abf869e37a9ee9ad24bbab27b28083d98dc849d471832e2e0","source":{"kind":"arxiv","id":"2501.03855","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03855","created_at":"2026-07-05T09:58:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03855v1","created_at":"2026-07-05T09:58:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03855","created_at":"2026-07-05T09:58:01Z"},{"alias_kind":"pith_short_12","alias_value":"XGKXILTHFIVD","created_at":"2026-07-05T09:58:01Z"},{"alias_kind":"pith_short_16","alias_value":"XGKXILTHFIVDVP4G","created_at":"2026-07-05T09:58:01Z"},{"alias_kind":"pith_short_8","alias_value":"XGKXILTH","created_at":"2026-07-05T09:58:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XGKXILTHFIVDVP4GTY32T3U22J","target":"record","payload":{"canonical_record":{"source":{"id":"2501.03855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T15:13:45Z","cross_cats_sorted":[],"title_canon_sha256":"d2a31a6a268e69432e37fb7b93ba6a8d652aecf3772dd3fa45b8669a76ec3235","abstract_canon_sha256":"9c237a39d1057979cf7159e6f9b24e356c2b2ffd62d66efb0619f64d3106c24f"},"schema_version":"1.0"},"canonical_sha256":"b995742e672a2a3abf869e37a9ee9ad24bbab27b28083d98dc849d471832e2e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:01.391399Z","signature_b64":"VGm5iPP9OSWh1zFbN3f3e7MMLVZKlTsu2GpdBrqiTfWqv5WvFj4SyXMl6UJgwbguBWEcFju6GDD/K3XYtllWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b995742e672a2a3abf869e37a9ee9ad24bbab27b28083d98dc849d471832e2e0","last_reissued_at":"2026-07-05T09:58:01.390918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:01.390918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.03855","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":"2026-07-05T09:58:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"knhLC+3uxct82HVUHk36/LB1o2iR7kjuUmkHScGtelByQOH+QsiYbWFDeLuaAl8uCBT5wWtNmxVAeu07suLeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T14:41:29.996802Z"},"content_sha256":"f7bfae7806b39e3bbde23aaced0647ff5c63fdaf4efe1ef818f4300fe65297e3","schema_version":"1.0","event_id":"sha256:f7bfae7806b39e3bbde23aaced0647ff5c63fdaf4efe1ef818f4300fe65297e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XGKXILTHFIVDVP4GTY32T3U22J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BabyLMs for isiXhosa: Data-Efficient Language Modelling in a Low-Resource Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Matzopoulos, Charl Hendriks, Francois Meyer, Hishaam Mahomed","submitted_at":"2025-01-07T15:13:45Z","abstract_excerpt":"The BabyLM challenge called on participants to develop sample-efficient language models. Submissions were pretrained on a fixed English corpus, limited to the amount of words children are exposed to in development (<100m). The challenge produced new architectures for data-efficient language modelling, which outperformed models trained on trillions of words. This is promising for low-resource languages, where available corpora are limited to much less than 100m words. In this paper, we explore the potential of BabyLMs for low-resource languages, using the isiXhosa language as a case study. We p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03855","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/2501.03855/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":"2026-07-05T09:58:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iOPJW/lSQiLMkPPO+XsJmyn8+abnTP/bd+Z+oxH4+iiA+z5qjHDMFiNiF4cEyerREnxdr4s1lvjzLGkBuJx4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T14:41:29.997495Z"},"content_sha256":"5682c2fe78e300d0e6963ccc98d79622c9ac124c12fec6e3950da0ff33370dbf","schema_version":"1.0","event_id":"sha256:5682c2fe78e300d0e6963ccc98d79622c9ac124c12fec6e3950da0ff33370dbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XGKXILTHFIVDVP4GTY32T3U22J/bundle.json","state_url":"https://pith.science/pith/XGKXILTHFIVDVP4GTY32T3U22J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XGKXILTHFIVDVP4GTY32T3U22J/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":"2026-08-20T14:41:30Z","links":{"resolver":"https://pith.science/pith/XGKXILTHFIVDVP4GTY32T3U22J","bundle":"https://pith.science/pith/XGKXILTHFIVDVP4GTY32T3U22J/bundle.json","state":"https://pith.science/pith/XGKXILTHFIVDVP4GTY32T3U22J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XGKXILTHFIVDVP4GTY32T3U22J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XGKXILTHFIVDVP4GTY32T3U22J","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":"9c237a39d1057979cf7159e6f9b24e356c2b2ffd62d66efb0619f64d3106c24f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T15:13:45Z","title_canon_sha256":"d2a31a6a268e69432e37fb7b93ba6a8d652aecf3772dd3fa45b8669a76ec3235"},"schema_version":"1.0","source":{"id":"2501.03855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03855","created_at":"2026-07-05T09:58:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03855v1","created_at":"2026-07-05T09:58:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03855","created_at":"2026-07-05T09:58:01Z"},{"alias_kind":"pith_short_12","alias_value":"XGKXILTHFIVD","created_at":"2026-07-05T09:58:01Z"},{"alias_kind":"pith_short_16","alias_value":"XGKXILTHFIVDVP4G","created_at":"2026-07-05T09:58:01Z"},{"alias_kind":"pith_short_8","alias_value":"XGKXILTH","created_at":"2026-07-05T09:58:01Z"}],"graph_snapshots":[{"event_id":"sha256:5682c2fe78e300d0e6963ccc98d79622c9ac124c12fec6e3950da0ff33370dbf","target":"graph","created_at":"2026-07-05T09:58:01Z","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/2501.03855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The BabyLM challenge called on participants to develop sample-efficient language models. Submissions were pretrained on a fixed English corpus, limited to the amount of words children are exposed to in development (<100m). The challenge produced new architectures for data-efficient language modelling, which outperformed models trained on trillions of words. This is promising for low-resource languages, where available corpora are limited to much less than 100m words. In this paper, we explore the potential of BabyLMs for low-resource languages, using the isiXhosa language as a case study. We p","authors_text":"Alexis Matzopoulos, Charl Hendriks, Francois Meyer, Hishaam Mahomed","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T15:13:45Z","title":"BabyLMs for isiXhosa: Data-Efficient Language Modelling in a Low-Resource Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03855","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:f7bfae7806b39e3bbde23aaced0647ff5c63fdaf4efe1ef818f4300fe65297e3","target":"record","created_at":"2026-07-05T09:58:01Z","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":"9c237a39d1057979cf7159e6f9b24e356c2b2ffd62d66efb0619f64d3106c24f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-07T15:13:45Z","title_canon_sha256":"d2a31a6a268e69432e37fb7b93ba6a8d652aecf3772dd3fa45b8669a76ec3235"},"schema_version":"1.0","source":{"id":"2501.03855","kind":"arxiv","version":1}},"canonical_sha256":"b995742e672a2a3abf869e37a9ee9ad24bbab27b28083d98dc849d471832e2e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b995742e672a2a3abf869e37a9ee9ad24bbab27b28083d98dc849d471832e2e0","first_computed_at":"2026-07-05T09:58:01.390918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:01.390918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VGm5iPP9OSWh1zFbN3f3e7MMLVZKlTsu2GpdBrqiTfWqv5WvFj4SyXMl6UJgwbguBWEcFju6GDD/K3XYtllWCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:01.391399Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7bfae7806b39e3bbde23aaced0647ff5c63fdaf4efe1ef818f4300fe65297e3","sha256:5682c2fe78e300d0e6963ccc98d79622c9ac124c12fec6e3950da0ff33370dbf"],"state_sha256":"5ee59a7257d08f1f23754894a4b9a57b3d8d6b6fe15c33aba341dc26ac2c7b84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1yYRXsh5RgF/4SGiaifrGmr7kVpmDm2HPctLsAWDK1OfCdXSJwPzmLmBdyY53ee4fgNzM7OotO3E00QKuaaNDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T14:41:30.006020Z","bundle_sha256":"011ebf88abf489b0675db5f3a4ad8578a5579bb40e6c00855f026dcc1570c797"}}