{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SLG3QZK7QS75UWXFGMQN4RC722","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":"260fba68a82c97b564fdb8b906895e338a6ee1ff0fec968e7c687d9ad5da9496","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T14:50:00Z","title_canon_sha256":"55ad4143416bf28ae4f2f071290dbb1ff8ecf0b967d9c11ad62feb08939b0c58"},"schema_version":"1.0","source":{"id":"2311.01955","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01955","created_at":"2026-07-05T07:08:47Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01955v1","created_at":"2026-07-05T07:08:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01955","created_at":"2026-07-05T07:08:47Z"},{"alias_kind":"pith_short_12","alias_value":"SLG3QZK7QS75","created_at":"2026-07-05T07:08:47Z"},{"alias_kind":"pith_short_16","alias_value":"SLG3QZK7QS75UWXF","created_at":"2026-07-05T07:08:47Z"},{"alias_kind":"pith_short_8","alias_value":"SLG3QZK7","created_at":"2026-07-05T07:08:47Z"}],"graph_snapshots":[{"event_id":"sha256:9f397bbc5d4fef9634d0c8a14f91cc6dc0f3d180ade61e1a504b651b40d813a9","target":"graph","created_at":"2026-07-05T07:08:47Z","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/2311.01955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper details the work of the University of Groningen for the BabyLM Challenge. We follow the idea that, like babies, language models should be introduced to simpler concepts first and build off of that knowledge to understand more complex concepts. We examine this strategy of simple-then-complex through a variety of lenses, namely context size, vocabulary, and overall linguistic complexity of the data. We find that only one, context size, is truly beneficial to training a language model. However this simple change to context size gives us improvements of 2 points on average on (Super)GLU","authors_text":"Lisa Bylinina, Lukas Edman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T14:50:00Z","title":"Too Much Information: Keeping Training Simple for BabyLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01955","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:be91ebb38f323b197e528fd6f9fcd34d0a0c544af78f3e84e52524bfb3085059","target":"record","created_at":"2026-07-05T07:08:47Z","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":"260fba68a82c97b564fdb8b906895e338a6ee1ff0fec968e7c687d9ad5da9496","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T14:50:00Z","title_canon_sha256":"55ad4143416bf28ae4f2f071290dbb1ff8ecf0b967d9c11ad62feb08939b0c58"},"schema_version":"1.0","source":{"id":"2311.01955","kind":"arxiv","version":1}},"canonical_sha256":"92cdb8655f84bfda5ae53320de445fd6aae6d6ccdb9e4b56b834e27158b82bf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92cdb8655f84bfda5ae53320de445fd6aae6d6ccdb9e4b56b834e27158b82bf1","first_computed_at":"2026-07-05T07:08:47.920756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:47.920756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m86R7YFMPuSS5VmaDklg367/dABsMiUQ2xl3vKEnPyB6xhmDauu2FYi/751bcnUDdTaL3sAd3e+iP1PsVeBMAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:47.921234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01955","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be91ebb38f323b197e528fd6f9fcd34d0a0c544af78f3e84e52524bfb3085059","sha256:9f397bbc5d4fef9634d0c8a14f91cc6dc0f3d180ade61e1a504b651b40d813a9"],"state_sha256":"de42465b010dd1a081cc38bff60b330030ac5068066905ab805ca0fb13574ef3"}