{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:B5GIKJUJVXHXJ7PRMZTJIPREH6","short_pith_number":"pith:B5GIKJUJ","canonical_record":{"source":{"id":"2504.08165","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T23:22:43Z","cross_cats_sorted":[],"title_canon_sha256":"651a4daadce8d85ef29e83d47eb4318de78bea1752c0b9e3a18788ab1539e4e5","abstract_canon_sha256":"9038097b56ee870d64c14506744488f7286020b85cdb9b04cbe006c2db52a383"},"schema_version":"1.0"},"canonical_sha256":"0f4c852689adcf74fdf16666943e243f9b9400dbaebf6ceda41dcbeded3d1d30","source":{"kind":"arxiv","id":"2504.08165","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08165","created_at":"2026-07-05T10:47:44Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08165v1","created_at":"2026-07-05T10:47:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08165","created_at":"2026-07-05T10:47:44Z"},{"alias_kind":"pith_short_12","alias_value":"B5GIKJUJVXHX","created_at":"2026-07-05T10:47:44Z"},{"alias_kind":"pith_short_16","alias_value":"B5GIKJUJVXHXJ7PR","created_at":"2026-07-05T10:47:44Z"},{"alias_kind":"pith_short_8","alias_value":"B5GIKJUJ","created_at":"2026-07-05T10:47:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:B5GIKJUJVXHXJ7PRMZTJIPREH6","target":"record","payload":{"canonical_record":{"source":{"id":"2504.08165","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T23:22:43Z","cross_cats_sorted":[],"title_canon_sha256":"651a4daadce8d85ef29e83d47eb4318de78bea1752c0b9e3a18788ab1539e4e5","abstract_canon_sha256":"9038097b56ee870d64c14506744488f7286020b85cdb9b04cbe006c2db52a383"},"schema_version":"1.0"},"canonical_sha256":"0f4c852689adcf74fdf16666943e243f9b9400dbaebf6ceda41dcbeded3d1d30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:44.171303Z","signature_b64":"nvxYSkWILKlhOtUPzCe+1kNNkm7XudPu7ETW7QyagRlBhRK5aZG9hyQGrHB/8DsSZJxNsNfMavns/mx0VjXJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f4c852689adcf74fdf16666943e243f9b9400dbaebf6ceda41dcbeded3d1d30","last_reissued_at":"2026-07-05T10:47:44.170851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:44.170851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.08165","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":"2026-07-05T10:47:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z/Cl4b9ilJTmtsPMHchWkXIrI9xIX1F4Dx9bkdRxonrkmYA6RhHAoKVW7fugSzUKp9j2Vd3QOoabsK4rGSmcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:50:48.600590Z"},"content_sha256":"55dda22036d29302d39b8dd04177089088bfa108e2fff9db636b9eabfb594e8f","schema_version":"1.0","event_id":"sha256:55dda22036d29302d39b8dd04177089088bfa108e2fff9db636b9eabfb594e8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:B5GIKJUJVXHXJ7PRMZTJIPREH6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Mueller, Adina Williams, Alex Warstadt, Bhargavi Paranjape, Chengxu Zhuang, Ethan Wilcox, Juan Ciro, Leshem Choshen, Rafael Mosquera, Ryan Cotterell, Tal Linzen","submitted_at":"2025-04-10T23:22:43Z","abstract_excerpt":"Children can acquire language from less than 100 million words of input. Large language models are far less data-efficient: they typically require 3 or 4 orders of magnitude more data and still do not perform as well as humans on many evaluations. These intensive resource demands limit the ability of researchers to train new models and use existing models as developmentally plausible cognitive models. The BabyLM Challenge is a communal effort in which participants compete to optimize language model training on a fixed data budget. Submissions are compared on various evaluation tasks targeting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08165","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/2504.08165/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":"2026-07-05T10:47:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3eBmdfH6m0ztmyx9WlGxgmrlQ7wfx6pgvapuij9Xpcjza94HYl/WFONDutc4jXrl3oYSnwrXzzGJM0RhHRKUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:50:48.601101Z"},"content_sha256":"2e228286c750209fb39f1810171dde6746a3e8ea329faedf68fd3bf164d0ffc0","schema_version":"1.0","event_id":"sha256:2e228286c750209fb39f1810171dde6746a3e8ea329faedf68fd3bf164d0ffc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B5GIKJUJVXHXJ7PRMZTJIPREH6/bundle.json","state_url":"https://pith.science/pith/B5GIKJUJVXHXJ7PRMZTJIPREH6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B5GIKJUJVXHXJ7PRMZTJIPREH6/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":"2026-08-04T13:50:48Z","links":{"resolver":"https://pith.science/pith/B5GIKJUJVXHXJ7PRMZTJIPREH6","bundle":"https://pith.science/pith/B5GIKJUJVXHXJ7PRMZTJIPREH6/bundle.json","state":"https://pith.science/pith/B5GIKJUJVXHXJ7PRMZTJIPREH6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B5GIKJUJVXHXJ7PRMZTJIPREH6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:B5GIKJUJVXHXJ7PRMZTJIPREH6","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":"9038097b56ee870d64c14506744488f7286020b85cdb9b04cbe006c2db52a383","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T23:22:43Z","title_canon_sha256":"651a4daadce8d85ef29e83d47eb4318de78bea1752c0b9e3a18788ab1539e4e5"},"schema_version":"1.0","source":{"id":"2504.08165","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.08165","created_at":"2026-07-05T10:47:44Z"},{"alias_kind":"arxiv_version","alias_value":"2504.08165v1","created_at":"2026-07-05T10:47:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08165","created_at":"2026-07-05T10:47:44Z"},{"alias_kind":"pith_short_12","alias_value":"B5GIKJUJVXHX","created_at":"2026-07-05T10:47:44Z"},{"alias_kind":"pith_short_16","alias_value":"B5GIKJUJVXHXJ7PR","created_at":"2026-07-05T10:47:44Z"},{"alias_kind":"pith_short_8","alias_value":"B5GIKJUJ","created_at":"2026-07-05T10:47:44Z"}],"graph_snapshots":[{"event_id":"sha256:2e228286c750209fb39f1810171dde6746a3e8ea329faedf68fd3bf164d0ffc0","target":"graph","created_at":"2026-07-05T10:47:44Z","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/2504.08165/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Children can acquire language from less than 100 million words of input. Large language models are far less data-efficient: they typically require 3 or 4 orders of magnitude more data and still do not perform as well as humans on many evaluations. These intensive resource demands limit the ability of researchers to train new models and use existing models as developmentally plausible cognitive models. The BabyLM Challenge is a communal effort in which participants compete to optimize language model training on a fixed data budget. Submissions are compared on various evaluation tasks targeting ","authors_text":"Aaron Mueller, Adina Williams, Alex Warstadt, Bhargavi Paranjape, Chengxu Zhuang, Ethan Wilcox, Juan Ciro, Leshem Choshen, Rafael Mosquera, Ryan Cotterell, Tal Linzen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T23:22:43Z","title":"Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08165","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":"sha256:55dda22036d29302d39b8dd04177089088bfa108e2fff9db636b9eabfb594e8f","target":"record","created_at":"2026-07-05T10:47:44Z","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":"9038097b56ee870d64c14506744488f7286020b85cdb9b04cbe006c2db52a383","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T23:22:43Z","title_canon_sha256":"651a4daadce8d85ef29e83d47eb4318de78bea1752c0b9e3a18788ab1539e4e5"},"schema_version":"1.0","source":{"id":"2504.08165","kind":"arxiv","version":1}},"canonical_sha256":"0f4c852689adcf74fdf16666943e243f9b9400dbaebf6ceda41dcbeded3d1d30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f4c852689adcf74fdf16666943e243f9b9400dbaebf6ceda41dcbeded3d1d30","first_computed_at":"2026-07-05T10:47:44.170851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:44.170851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nvxYSkWILKlhOtUPzCe+1kNNkm7XudPu7ETW7QyagRlBhRK5aZG9hyQGrHB/8DsSZJxNsNfMavns/mx0VjXJCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:44.171303Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.08165","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55dda22036d29302d39b8dd04177089088bfa108e2fff9db636b9eabfb594e8f","sha256:2e228286c750209fb39f1810171dde6746a3e8ea329faedf68fd3bf164d0ffc0"],"state_sha256":"058b3b4fe4f3433bd3fb234fe74f78897bba6210f5426e87a7053aea8b16008e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8tHvsLlYhomolOGeWhIydMGAi9rczObKwU8EeaH9ihCPTOUDybmsZoej3nXEYqRuLXVk4mB5HGHZLJaYmeJGAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:50:48.606165Z","bundle_sha256":"0bc7038e108860f2f0d1b8d685745d9cdc907afd935f90c03b303e570dc496f3"}}