{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EY2KWIZGYYQ6D6QLXPSAXR22UD","short_pith_number":"pith:EY2KWIZG","canonical_record":{"source":{"id":"2310.19420","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T10:31:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"232c2211c82538f090d694b2a07a4ef08e5b0d40282161467b595741c71dffe5","abstract_canon_sha256":"f289058973e18b2db08b5f7666dcf1a0c95b7cac888407c0e9ea2951308b0cc3"},"schema_version":"1.0"},"canonical_sha256":"2634ab2326c621e1fa0bbbe40bc75aa0c742567b565cb5f3b979b8f98de9ff70","source":{"kind":"arxiv","id":"2310.19420","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19420","created_at":"2026-07-05T07:06:50Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19420v1","created_at":"2026-07-05T07:06:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19420","created_at":"2026-07-05T07:06:50Z"},{"alias_kind":"pith_short_12","alias_value":"EY2KWIZGYYQ6","created_at":"2026-07-05T07:06:50Z"},{"alias_kind":"pith_short_16","alias_value":"EY2KWIZGYYQ6D6QL","created_at":"2026-07-05T07:06:50Z"},{"alias_kind":"pith_short_8","alias_value":"EY2KWIZG","created_at":"2026-07-05T07:06:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EY2KWIZGYYQ6D6QLXPSAXR22UD","target":"record","payload":{"canonical_record":{"source":{"id":"2310.19420","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T10:31:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"232c2211c82538f090d694b2a07a4ef08e5b0d40282161467b595741c71dffe5","abstract_canon_sha256":"f289058973e18b2db08b5f7666dcf1a0c95b7cac888407c0e9ea2951308b0cc3"},"schema_version":"1.0"},"canonical_sha256":"2634ab2326c621e1fa0bbbe40bc75aa0c742567b565cb5f3b979b8f98de9ff70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:50.741421Z","signature_b64":"x4vRaSKTRXYG7D8VmGv9NVOlXA/b1BA9PqSmaxXPgUzRDSelVpw0l344hBZDZ/9/Az2Ei1q6eYw8A6hZ0bakDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2634ab2326c621e1fa0bbbe40bc75aa0c742567b565cb5f3b979b8f98de9ff70","last_reissued_at":"2026-07-05T07:06:50.740752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:50.740752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.19420","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":"2026-07-05T07:06:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H4DSxSqmU0YLopWLvyA/StzKYtt5GXyPcEhExLQXiG0yPYOz0lt29pItmfIDGPDB51wzGuL5uaHRkh1PzqJWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:15:58.498979Z"},"content_sha256":"36e64546783c1953f56e228881659dc69b614320338d1de8a5f77dcf9cbb530e","schema_version":"1.0","event_id":"sha256:36e64546783c1953f56e228881659dc69b614320338d1de8a5f77dcf9cbb530e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EY2KWIZGYYQ6D6QLXPSAXR22UD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mean BERTs make erratic language teachers: the effectiveness of latent bootstrapping in low-resource settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"David Samuel","submitted_at":"2023-10-30T10:31:32Z","abstract_excerpt":"This paper explores the use of latent bootstrapping, an alternative self-supervision technique, for pretraining language models. Unlike the typical practice of using self-supervision on discrete subwords, latent bootstrapping leverages contextualized embeddings for a richer supervision signal. We conduct experiments to assess how effective this approach is for acquiring linguistic knowledge from limited resources. Specifically, our experiments are based on the BabyLM shared task, which includes pretraining on two small curated corpora and an evaluation on four linguistic benchmarks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19420","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/2310.19420/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":"2026-07-05T07:06:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3UXX/hWQst+vbY8RiZ/yxW1u4BTS2NONja+qbbrnNFvqO+NSSLdaOtJNFVWNlXGSeq8ImWq9GZdm2Xd/76+RBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:15:58.499519Z"},"content_sha256":"898f3cf80bee350f1d1269c27085608f83e5e6e365022de99e6ae95ea6a60089","schema_version":"1.0","event_id":"sha256:898f3cf80bee350f1d1269c27085608f83e5e6e365022de99e6ae95ea6a60089"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EY2KWIZGYYQ6D6QLXPSAXR22UD/bundle.json","state_url":"https://pith.science/pith/EY2KWIZGYYQ6D6QLXPSAXR22UD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EY2KWIZGYYQ6D6QLXPSAXR22UD/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":"2026-08-22T23:15:58Z","links":{"resolver":"https://pith.science/pith/EY2KWIZGYYQ6D6QLXPSAXR22UD","bundle":"https://pith.science/pith/EY2KWIZGYYQ6D6QLXPSAXR22UD/bundle.json","state":"https://pith.science/pith/EY2KWIZGYYQ6D6QLXPSAXR22UD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EY2KWIZGYYQ6D6QLXPSAXR22UD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EY2KWIZGYYQ6D6QLXPSAXR22UD","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":"f289058973e18b2db08b5f7666dcf1a0c95b7cac888407c0e9ea2951308b0cc3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T10:31:32Z","title_canon_sha256":"232c2211c82538f090d694b2a07a4ef08e5b0d40282161467b595741c71dffe5"},"schema_version":"1.0","source":{"id":"2310.19420","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19420","created_at":"2026-07-05T07:06:50Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19420v1","created_at":"2026-07-05T07:06:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19420","created_at":"2026-07-05T07:06:50Z"},{"alias_kind":"pith_short_12","alias_value":"EY2KWIZGYYQ6","created_at":"2026-07-05T07:06:50Z"},{"alias_kind":"pith_short_16","alias_value":"EY2KWIZGYYQ6D6QL","created_at":"2026-07-05T07:06:50Z"},{"alias_kind":"pith_short_8","alias_value":"EY2KWIZG","created_at":"2026-07-05T07:06:50Z"}],"graph_snapshots":[{"event_id":"sha256:898f3cf80bee350f1d1269c27085608f83e5e6e365022de99e6ae95ea6a60089","target":"graph","created_at":"2026-07-05T07:06:50Z","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/2310.19420/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores the use of latent bootstrapping, an alternative self-supervision technique, for pretraining language models. Unlike the typical practice of using self-supervision on discrete subwords, latent bootstrapping leverages contextualized embeddings for a richer supervision signal. We conduct experiments to assess how effective this approach is for acquiring linguistic knowledge from limited resources. Specifically, our experiments are based on the BabyLM shared task, which includes pretraining on two small curated corpora and an evaluation on four linguistic benchmarks.","authors_text":"David Samuel","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T10:31:32Z","title":"Mean BERTs make erratic language teachers: the effectiveness of latent bootstrapping in low-resource settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19420","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":"sha256:36e64546783c1953f56e228881659dc69b614320338d1de8a5f77dcf9cbb530e","target":"record","created_at":"2026-07-05T07:06:50Z","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":"f289058973e18b2db08b5f7666dcf1a0c95b7cac888407c0e9ea2951308b0cc3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T10:31:32Z","title_canon_sha256":"232c2211c82538f090d694b2a07a4ef08e5b0d40282161467b595741c71dffe5"},"schema_version":"1.0","source":{"id":"2310.19420","kind":"arxiv","version":1}},"canonical_sha256":"2634ab2326c621e1fa0bbbe40bc75aa0c742567b565cb5f3b979b8f98de9ff70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2634ab2326c621e1fa0bbbe40bc75aa0c742567b565cb5f3b979b8f98de9ff70","first_computed_at":"2026-07-05T07:06:50.740752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:50.740752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x4vRaSKTRXYG7D8VmGv9NVOlXA/b1BA9PqSmaxXPgUzRDSelVpw0l344hBZDZ/9/Az2Ei1q6eYw8A6hZ0bakDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:50.741421Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19420","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36e64546783c1953f56e228881659dc69b614320338d1de8a5f77dcf9cbb530e","sha256:898f3cf80bee350f1d1269c27085608f83e5e6e365022de99e6ae95ea6a60089"],"state_sha256":"feafa15be20c5e9433b1511908bc9125906a2bece7a201c759f65dbb80e3b0ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PbZmUMsvTUuGICgvrUv1TyObDlY5oh3nsnAsNOiamoLAgagIlImNgy+jjFHk/hDTXDiLBFMHEHBD3JG9Y+ZIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T23:15:58.505251Z","bundle_sha256":"0cf246380e7fa9f9bfdb62687e882ddf7773add3bfd079f532deb85bff4cd064"}}