{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LHHRU6OOFR5WDN533N3DY7JDFJ","short_pith_number":"pith:LHHRU6OO","canonical_record":{"source":{"id":"2308.02019","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T20:20:01Z","cross_cats_sorted":[],"title_canon_sha256":"635f20b91ff663cf6852ee4887dddd1806daa81c92a30e7f09f0f38d390ab661","abstract_canon_sha256":"9c3eaf8881ac08c50d6d0e7115ac632c349fd84b887a63f9515bac2fdbab9951"},"schema_version":"1.0"},"canonical_sha256":"59cf1a79ce2c7b61b7bbdb763c7d232a471af6936db81bc8ed789a2fba2dad80","source":{"kind":"arxiv","id":"2308.02019","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.02019","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2308.02019v2","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02019","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"LHHRU6OOFR5W","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"LHHRU6OOFR5WDN53","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"LHHRU6OO","created_at":"2026-07-05T07:04:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LHHRU6OOFR5WDN533N3DY7JDFJ","target":"record","payload":{"canonical_record":{"source":{"id":"2308.02019","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T20:20:01Z","cross_cats_sorted":[],"title_canon_sha256":"635f20b91ff663cf6852ee4887dddd1806daa81c92a30e7f09f0f38d390ab661","abstract_canon_sha256":"9c3eaf8881ac08c50d6d0e7115ac632c349fd84b887a63f9515bac2fdbab9951"},"schema_version":"1.0"},"canonical_sha256":"59cf1a79ce2c7b61b7bbdb763c7d232a471af6936db81bc8ed789a2fba2dad80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:18.880657Z","signature_b64":"IrPAKt3Rf8Zc+do4vJiTCoXQQRKGtdqTgcsrOYeoqys0S+f0lcnvsoJkbB1Tr373dU6obtiIp1yN66vrNLwWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59cf1a79ce2c7b61b7bbdb763c7d232a471af6936db81bc8ed789a2fba2dad80","last_reissued_at":"2026-07-05T07:04:18.880189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:18.880189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.02019","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LJatseXCHosIL5F774mBsdTT7hSpiGw0wIie1Pv7mJul8B4nkDt1Q1tYnclxZvJKpby/r42RTxkJ5wKeRSexDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:18:16.222130Z"},"content_sha256":"956f5690ff1286214e1bb5726e80925f9730e64091a3f65911bd4e585460915d","schema_version":"1.0","event_id":"sha256:956f5690ff1286214e1bb5726e80925f9730e64091a3f65911bd4e585460915d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LHHRU6OOFR5WDN533N3DY7JDFJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Inar Timiryasov, Jean-Loup Tastet","submitted_at":"2023-08-03T20:20:01Z","abstract_excerpt":"We present our submission to the BabyLM challenge, whose goal was to improve the sample efficiency of language models. We trained an ensemble consisting of a GPT-2 and small LLaMA models on the developmentally-plausible, 10M-word BabyLM dataset, then distilled it into a small, 58M-parameter LLaMA model, which exceeds in performance both of its teachers as well as a similar model trained without distillation. This suggests that distillation can not only retain the full performance of the teacher model when the latter is trained on a sufficiently small dataset; it can exceed it, and lead to sign"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02019","kind":"arxiv","version":2},"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/2308.02019/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":"2026-07-05T07:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3fGeS7hVc7sOaMijsZDDyLGt/BQ5g3EyWml1Wzs5uyzSsd/6te99eGWJccuzOy5NrY/5cDNdazTgGX599+DCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:18:16.222660Z"},"content_sha256":"7ffa710ac6419370286a451f2b19b4321dfd1e57510186ffcaf4096422520fd8","schema_version":"1.0","event_id":"sha256:7ffa710ac6419370286a451f2b19b4321dfd1e57510186ffcaf4096422520fd8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LHHRU6OOFR5WDN533N3DY7JDFJ/bundle.json","state_url":"https://pith.science/pith/LHHRU6OOFR5WDN533N3DY7JDFJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LHHRU6OOFR5WDN533N3DY7JDFJ/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":"2026-08-08T10:18:16Z","links":{"resolver":"https://pith.science/pith/LHHRU6OOFR5WDN533N3DY7JDFJ","bundle":"https://pith.science/pith/LHHRU6OOFR5WDN533N3DY7JDFJ/bundle.json","state":"https://pith.science/pith/LHHRU6OOFR5WDN533N3DY7JDFJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LHHRU6OOFR5WDN533N3DY7JDFJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LHHRU6OOFR5WDN533N3DY7JDFJ","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":"9c3eaf8881ac08c50d6d0e7115ac632c349fd84b887a63f9515bac2fdbab9951","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T20:20:01Z","title_canon_sha256":"635f20b91ff663cf6852ee4887dddd1806daa81c92a30e7f09f0f38d390ab661"},"schema_version":"1.0","source":{"id":"2308.02019","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.02019","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2308.02019v2","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02019","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"LHHRU6OOFR5W","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"LHHRU6OOFR5WDN53","created_at":"2026-07-05T07:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"LHHRU6OO","created_at":"2026-07-05T07:04:18Z"}],"graph_snapshots":[{"event_id":"sha256:7ffa710ac6419370286a451f2b19b4321dfd1e57510186ffcaf4096422520fd8","target":"graph","created_at":"2026-07-05T07:04:18Z","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/2308.02019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present our submission to the BabyLM challenge, whose goal was to improve the sample efficiency of language models. We trained an ensemble consisting of a GPT-2 and small LLaMA models on the developmentally-plausible, 10M-word BabyLM dataset, then distilled it into a small, 58M-parameter LLaMA model, which exceeds in performance both of its teachers as well as a similar model trained without distillation. This suggests that distillation can not only retain the full performance of the teacher model when the latter is trained on a sufficiently small dataset; it can exceed it, and lead to sign","authors_text":"Inar Timiryasov, Jean-Loup Tastet","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T20:20:01Z","title":"Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02019","kind":"arxiv","version":2},"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":"sha256:956f5690ff1286214e1bb5726e80925f9730e64091a3f65911bd4e585460915d","target":"record","created_at":"2026-07-05T07:04:18Z","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":"9c3eaf8881ac08c50d6d0e7115ac632c349fd84b887a63f9515bac2fdbab9951","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T20:20:01Z","title_canon_sha256":"635f20b91ff663cf6852ee4887dddd1806daa81c92a30e7f09f0f38d390ab661"},"schema_version":"1.0","source":{"id":"2308.02019","kind":"arxiv","version":2}},"canonical_sha256":"59cf1a79ce2c7b61b7bbdb763c7d232a471af6936db81bc8ed789a2fba2dad80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59cf1a79ce2c7b61b7bbdb763c7d232a471af6936db81bc8ed789a2fba2dad80","first_computed_at":"2026-07-05T07:04:18.880189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:18.880189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IrPAKt3Rf8Zc+do4vJiTCoXQQRKGtdqTgcsrOYeoqys0S+f0lcnvsoJkbB1Tr373dU6obtiIp1yN66vrNLwWAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:18.880657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.02019","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:956f5690ff1286214e1bb5726e80925f9730e64091a3f65911bd4e585460915d","sha256:7ffa710ac6419370286a451f2b19b4321dfd1e57510186ffcaf4096422520fd8"],"state_sha256":"ac5c775f208e53063f47bffcc6854e8295442a2aaf619b3fed7bb851cafac998"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RQLiTOncCTkeXKhlCx2h6IDbpywyHVnzPiBuS/XPdQblVYhiWae7ng3l+7rh16FBJvgwayD+P61ELwBFXqL5Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:18:16.227649Z","bundle_sha256":"287877efe63fc84c92df16b7ee724e73e2bcb3c01abc60163e5c4c8905e894a0"}}