{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FZSEDXRXK2TZDWJWPJY6CONVBP","short_pith_number":"pith:FZSEDXRX","canonical_record":{"source":{"id":"2305.17266","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T21:22:10Z","cross_cats_sorted":[],"title_canon_sha256":"3ba1cea0757bfbc88fbd2b1bb593be38f721ad1f8673dfa62191cd28ced7aa1d","abstract_canon_sha256":"602ac3b7c8bd374c8b660e7f9211eb6fdb10e2cff90a4b5d9e01fe3de6de27bb"},"schema_version":"1.0"},"canonical_sha256":"2e6441de3756a791d9367a71e139b50bc2ee60c4918732b6dd9dfe411c7f319f","source":{"kind":"arxiv","id":"2305.17266","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17266","created_at":"2026-07-05T06:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17266v2","created_at":"2026-07-05T06:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17266","created_at":"2026-07-05T06:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"FZSEDXRXK2TZ","created_at":"2026-07-05T06:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"FZSEDXRXK2TZDWJW","created_at":"2026-07-05T06:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"FZSEDXRX","created_at":"2026-07-05T06:15:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FZSEDXRXK2TZDWJWPJY6CONVBP","target":"record","payload":{"canonical_record":{"source":{"id":"2305.17266","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T21:22:10Z","cross_cats_sorted":[],"title_canon_sha256":"3ba1cea0757bfbc88fbd2b1bb593be38f721ad1f8673dfa62191cd28ced7aa1d","abstract_canon_sha256":"602ac3b7c8bd374c8b660e7f9211eb6fdb10e2cff90a4b5d9e01fe3de6de27bb"},"schema_version":"1.0"},"canonical_sha256":"2e6441de3756a791d9367a71e139b50bc2ee60c4918732b6dd9dfe411c7f319f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:47.844046Z","signature_b64":"2CMaPdXWJHbMWI6xE2+1L4fok+WLX+u6MWIoGxcEifRYEYqikcJSpdtD0qYlOw8doi7rHX58z6sR6b+ExXNwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e6441de3756a791d9367a71e139b50bc2ee60c4918732b6dd9dfe411c7f319f","last_reissued_at":"2026-07-05T06:15:47.843611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:47.843611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.17266","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":"2026-07-05T06:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RPpmEG9glKyKZ1AY4bOuNLK55BdTz+wtvNr8Iw2wC4sWiVTmXYRNKrYzWYvh0tRNMTeaHY0HH4dUt2ZYZbUqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:08:12.134364Z"},"content_sha256":"6de261383278bd6a0aaa8045ee690d00bcf97599ec92c4d8e2474dc273d84a85","schema_version":"1.0","event_id":"sha256:6de261383278bd6a0aaa8045ee690d00bcf97599ec92c4d8e2474dc273d84a85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FZSEDXRXK2TZDWJWPJY6CONVBP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Rumshisky, Dan Pechi, Shree Thatte, Vijeta Deshpande, Vladislav Lialin","submitted_at":"2023-05-26T21:22:10Z","abstract_excerpt":"In recent years, language models have drastically grown in size, and the abilities of these models have been shown to improve with scale. The majority of recent scaling laws studies focused on high-compute high-parameter count settings, leaving the question of when these abilities begin to emerge largely unanswered. In this paper, we investigate whether the effects of pre-training can be observed when the problem size is reduced, modeling a smaller, reduced-vocabulary language. We show the benefits of pre-training with masked language modeling (MLM) objective in models as small as 1.25M parame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17266","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/2305.17266/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":"2026-07-05T06:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c6rFnqAJzNvBqhUraTfv9BlhPfDBupzfN6wH0ZmURPGxYkSu9ViPlWs1RhG5BJlc+6GhBOaZWGmevyZRKKBcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:08:12.134898Z"},"content_sha256":"88e5980a063a0ce7f2bb13c3e49cd7412dddc0126e45f2a5b89211a96c320208","schema_version":"1.0","event_id":"sha256:88e5980a063a0ce7f2bb13c3e49cd7412dddc0126e45f2a5b89211a96c320208"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FZSEDXRXK2TZDWJWPJY6CONVBP/bundle.json","state_url":"https://pith.science/pith/FZSEDXRXK2TZDWJWPJY6CONVBP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FZSEDXRXK2TZDWJWPJY6CONVBP/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":"2026-08-03T17:08:12Z","links":{"resolver":"https://pith.science/pith/FZSEDXRXK2TZDWJWPJY6CONVBP","bundle":"https://pith.science/pith/FZSEDXRXK2TZDWJWPJY6CONVBP/bundle.json","state":"https://pith.science/pith/FZSEDXRXK2TZDWJWPJY6CONVBP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FZSEDXRXK2TZDWJWPJY6CONVBP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FZSEDXRXK2TZDWJWPJY6CONVBP","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":"602ac3b7c8bd374c8b660e7f9211eb6fdb10e2cff90a4b5d9e01fe3de6de27bb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T21:22:10Z","title_canon_sha256":"3ba1cea0757bfbc88fbd2b1bb593be38f721ad1f8673dfa62191cd28ced7aa1d"},"schema_version":"1.0","source":{"id":"2305.17266","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17266","created_at":"2026-07-05T06:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17266v2","created_at":"2026-07-05T06:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17266","created_at":"2026-07-05T06:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"FZSEDXRXK2TZ","created_at":"2026-07-05T06:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"FZSEDXRXK2TZDWJW","created_at":"2026-07-05T06:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"FZSEDXRX","created_at":"2026-07-05T06:15:47Z"}],"graph_snapshots":[{"event_id":"sha256:88e5980a063a0ce7f2bb13c3e49cd7412dddc0126e45f2a5b89211a96c320208","target":"graph","created_at":"2026-07-05T06:15:47Z","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/2305.17266/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, language models have drastically grown in size, and the abilities of these models have been shown to improve with scale. The majority of recent scaling laws studies focused on high-compute high-parameter count settings, leaving the question of when these abilities begin to emerge largely unanswered. In this paper, we investigate whether the effects of pre-training can be observed when the problem size is reduced, modeling a smaller, reduced-vocabulary language. We show the benefits of pre-training with masked language modeling (MLM) objective in models as small as 1.25M parame","authors_text":"Anna Rumshisky, Dan Pechi, Shree Thatte, Vijeta Deshpande, Vladislav Lialin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T21:22:10Z","title":"Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17266","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":"sha256:6de261383278bd6a0aaa8045ee690d00bcf97599ec92c4d8e2474dc273d84a85","target":"record","created_at":"2026-07-05T06:15:47Z","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":"602ac3b7c8bd374c8b660e7f9211eb6fdb10e2cff90a4b5d9e01fe3de6de27bb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T21:22:10Z","title_canon_sha256":"3ba1cea0757bfbc88fbd2b1bb593be38f721ad1f8673dfa62191cd28ced7aa1d"},"schema_version":"1.0","source":{"id":"2305.17266","kind":"arxiv","version":2}},"canonical_sha256":"2e6441de3756a791d9367a71e139b50bc2ee60c4918732b6dd9dfe411c7f319f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e6441de3756a791d9367a71e139b50bc2ee60c4918732b6dd9dfe411c7f319f","first_computed_at":"2026-07-05T06:15:47.843611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:47.843611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2CMaPdXWJHbMWI6xE2+1L4fok+WLX+u6MWIoGxcEifRYEYqikcJSpdtD0qYlOw8doi7rHX58z6sR6b+ExXNwBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:47.844046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17266","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6de261383278bd6a0aaa8045ee690d00bcf97599ec92c4d8e2474dc273d84a85","sha256:88e5980a063a0ce7f2bb13c3e49cd7412dddc0126e45f2a5b89211a96c320208"],"state_sha256":"16c8f1fb1700e0c5a4fb944def767bdae44ad7406d25e0cea4374b5dcbb23c20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HPfBAbHg0abRskK5lAcioMknS9gm7H5dACjmcb5rbZKIVefsLJhIvv67CqAMc6yOOillIXmXwu1yU1Rv//3hAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:08:12.139008Z","bundle_sha256":"956245ab4500f679318e6e5c40bed45c30cce69683c04a845c4056bdb8a95065"}}