{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RUPCTBMR2LGNGQFHLIPINHP7RV","short_pith_number":"pith:RUPCTBMR","schema_version":"1.0","canonical_sha256":"8d1e298591d2ccd340a75a1e869dff8d5e9dcb422e7b1973973f80785fcae8c7","source":{"kind":"arxiv","id":"2301.11796","version":1},"attestation_state":"computed","paper":{"title":"Call for Papers -- The BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Mueller, Adina Williams, Alex Warstadt, Chengxu Zhuang, Ethan Wilcox, Leshem Choshen","submitted_at":"2023-01-27T15:52:50Z","abstract_excerpt":"We present the call for papers for the BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus. This shared task is intended for participants with an interest in small scale language modeling, human language acquisition, low-resource NLP, and cognitive modeling. In partnership with CoNLL and CMCL, we provide a platform for approaches to pretraining with a limited-size corpus sourced from data inspired by the input to children. The task has three tracks, two of which restrict the training data to pre-released datasets of 10M and 100M words and are dedicated to explo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.11796","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-27T15:52:50Z","cross_cats_sorted":[],"title_canon_sha256":"bf76c68e7920752b88ba63edfe5aa6b6e1f850beff9a1b772e072e78370913d8","abstract_canon_sha256":"3d49a0aefd428e11618407ce15572296a461fc277377416eae4d99f4473c0718"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:26.594488Z","signature_b64":"2p3g1DzO/PA7XIp6nheUGcgsOuFCPpo7Jl0Ti/zYDtTCEAWjqwNhTKQB7o4ndwkw6QP9IeRUO0XKUbHWtCYEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d1e298591d2ccd340a75a1e869dff8d5e9dcb422e7b1973973f80785fcae8c7","last_reissued_at":"2026-07-05T05:36:26.593989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:26.593989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Call for Papers -- The BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Mueller, Adina Williams, Alex Warstadt, Chengxu Zhuang, Ethan Wilcox, Leshem Choshen","submitted_at":"2023-01-27T15:52:50Z","abstract_excerpt":"We present the call for papers for the BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus. This shared task is intended for participants with an interest in small scale language modeling, human language acquisition, low-resource NLP, and cognitive modeling. In partnership with CoNLL and CMCL, we provide a platform for approaches to pretraining with a limited-size corpus sourced from data inspired by the input to children. The task has three tracks, two of which restrict the training data to pre-released datasets of 10M and 100M words and are dedicated to explo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11796","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/2301.11796/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.11796","created_at":"2026-07-05T05:36:26.594048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.11796v1","created_at":"2026-07-05T05:36:26.594048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11796","created_at":"2026-07-05T05:36:26.594048+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUPCTBMR2LGN","created_at":"2026-07-05T05:36:26.594048+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUPCTBMR2LGNGQFH","created_at":"2026-07-05T05:36:26.594048+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUPCTBMR","created_at":"2026-07-05T05:36:26.594048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05497","citing_title":"LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, \"Is Your VLM Smarter Than a 5th Grader?\")","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18563","citing_title":"Readers make targeted regressions to plausible errors in reanalysis of \"noisy-channel garden-path\" sentences","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10333","citing_title":"Zero-shot World Models Are Developmentally Efficient Learners","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUPCTBMR2LGNGQFHLIPINHP7RV","json":"https://pith.science/pith/RUPCTBMR2LGNGQFHLIPINHP7RV.json","graph_json":"https://pith.science/api/pith-number/RUPCTBMR2LGNGQFHLIPINHP7RV/graph.json","events_json":"https://pith.science/api/pith-number/RUPCTBMR2LGNGQFHLIPINHP7RV/events.json","paper":"https://pith.science/paper/RUPCTBMR"},"agent_actions":{"view_html":"https://pith.science/pith/RUPCTBMR2LGNGQFHLIPINHP7RV","download_json":"https://pith.science/pith/RUPCTBMR2LGNGQFHLIPINHP7RV.json","view_paper":"https://pith.science/paper/RUPCTBMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.11796&json=true","fetch_graph":"https://pith.science/api/pith-number/RUPCTBMR2LGNGQFHLIPINHP7RV/graph.json","fetch_events":"https://pith.science/api/pith-number/RUPCTBMR2LGNGQFHLIPINHP7RV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUPCTBMR2LGNGQFHLIPINHP7RV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUPCTBMR2LGNGQFHLIPINHP7RV/action/storage_attestation","attest_author":"https://pith.science/pith/RUPCTBMR2LGNGQFHLIPINHP7RV/action/author_attestation","sign_citation":"https://pith.science/pith/RUPCTBMR2LGNGQFHLIPINHP7RV/action/citation_signature","submit_replication":"https://pith.science/pith/RUPCTBMR2LGNGQFHLIPINHP7RV/action/replication_record"}},"created_at":"2026-07-05T05:36:26.594048+00:00","updated_at":"2026-07-05T05:36:26.594048+00:00"}