{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YBPYMZDX5LQHG3LKCHKX72HPWN","short_pith_number":"pith:YBPYMZDX","canonical_record":{"source":{"id":"2209.14389","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-28T19:28:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5cec3daee1b0319c866d5f36ec225a9c01e63c5f90b1860825f5e73d51ac4280","abstract_canon_sha256":"a5de17431b08bc64fb0e487511b53700fb817cb55b1d396a1a49b42d78a75dcc"},"schema_version":"1.0"},"canonical_sha256":"c05f866477eae0736d6a11d57fe8efb3568cc29e022824335655c3f43eb4f84e","source":{"kind":"arxiv","id":"2209.14389","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14389","created_at":"2026-07-05T06:14:05Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14389v2","created_at":"2026-07-05T06:14:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14389","created_at":"2026-07-05T06:14:05Z"},{"alias_kind":"pith_short_12","alias_value":"YBPYMZDX5LQH","created_at":"2026-07-05T06:14:05Z"},{"alias_kind":"pith_short_16","alias_value":"YBPYMZDX5LQHG3LK","created_at":"2026-07-05T06:14:05Z"},{"alias_kind":"pith_short_8","alias_value":"YBPYMZDX","created_at":"2026-07-05T06:14:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YBPYMZDX5LQHG3LKCHKX72HPWN","target":"record","payload":{"canonical_record":{"source":{"id":"2209.14389","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-28T19:28:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5cec3daee1b0319c866d5f36ec225a9c01e63c5f90b1860825f5e73d51ac4280","abstract_canon_sha256":"a5de17431b08bc64fb0e487511b53700fb817cb55b1d396a1a49b42d78a75dcc"},"schema_version":"1.0"},"canonical_sha256":"c05f866477eae0736d6a11d57fe8efb3568cc29e022824335655c3f43eb4f84e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:05.320962Z","signature_b64":"kWK56nEeIFUS+rQ8xh25zXcizdF4LY76wwnHHHdQ5YvYiKZQwKBOaWx5Wi3aNz0q38cZnCtzbFuuFySfJ9GrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c05f866477eae0736d6a11d57fe8efb3568cc29e022824335655c3f43eb4f84e","last_reissued_at":"2026-07-05T06:14:05.320473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:05.320473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.14389","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":"2026-07-05T06:14:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2lniK+pffDf7OzjvsX38OkaC18A9oavba8pXpWGOXYHnohgb2w8MgVoVNeBKpySq+tD1ipih8f4zIfuOP9mkBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:14:08.346452Z"},"content_sha256":"62ceee5fc7c6072bb228531abba46123f4ae712f061be3ed11d6f7166442d2c6","schema_version":"1.0","event_id":"sha256:62ceee5fc7c6072bb228531abba46123f4ae712f061be3ed11d6f7166442d2c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YBPYMZDX5LQHG3LKCHKX72HPWN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Downstream Datasets Make Surprisingly Good Pretraining Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jeffrey P. Bigham, Kundan Krishna, Saurabh Garg, Zachary C. Lipton","submitted_at":"2022-09-28T19:28:43Z","abstract_excerpt":"For most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e.g., BERT) using smaller downstream datasets. Despite the success of this approach, it remains unclear to what extent these gains are attributable to the massive background corpora employed for pretraining versus to the pretraining objectives themselves. This paper introduces a large-scale study of self-pretraining, where the same (downstream) training data is used for both pretraining and finetuning. In experiments addressing both ELECTRA and RoBERTa models and 10 distinct do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14389","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/2209.14389/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":"2026-07-05T06:14:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xByTWkci5SSGSgAlW7jGx8Y6yx7g4r7Z/fBznlKf5IqQ1QjAxFUuiaXiudgVNAZPB4JzXqzuSfvCLBTECqVDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:14:08.346807Z"},"content_sha256":"0c25d3e47b42872ecf5bfcba695f742399d2600019bde7b916d816f36d86da40","schema_version":"1.0","event_id":"sha256:0c25d3e47b42872ecf5bfcba695f742399d2600019bde7b916d816f36d86da40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBPYMZDX5LQHG3LKCHKX72HPWN/bundle.json","state_url":"https://pith.science/pith/YBPYMZDX5LQHG3LKCHKX72HPWN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBPYMZDX5LQHG3LKCHKX72HPWN/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":"2026-08-04T16:14:08Z","links":{"resolver":"https://pith.science/pith/YBPYMZDX5LQHG3LKCHKX72HPWN","bundle":"https://pith.science/pith/YBPYMZDX5LQHG3LKCHKX72HPWN/bundle.json","state":"https://pith.science/pith/YBPYMZDX5LQHG3LKCHKX72HPWN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBPYMZDX5LQHG3LKCHKX72HPWN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YBPYMZDX5LQHG3LKCHKX72HPWN","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":"a5de17431b08bc64fb0e487511b53700fb817cb55b1d396a1a49b42d78a75dcc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-28T19:28:43Z","title_canon_sha256":"5cec3daee1b0319c866d5f36ec225a9c01e63c5f90b1860825f5e73d51ac4280"},"schema_version":"1.0","source":{"id":"2209.14389","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14389","created_at":"2026-07-05T06:14:05Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14389v2","created_at":"2026-07-05T06:14:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14389","created_at":"2026-07-05T06:14:05Z"},{"alias_kind":"pith_short_12","alias_value":"YBPYMZDX5LQH","created_at":"2026-07-05T06:14:05Z"},{"alias_kind":"pith_short_16","alias_value":"YBPYMZDX5LQHG3LK","created_at":"2026-07-05T06:14:05Z"},{"alias_kind":"pith_short_8","alias_value":"YBPYMZDX","created_at":"2026-07-05T06:14:05Z"}],"graph_snapshots":[{"event_id":"sha256:0c25d3e47b42872ecf5bfcba695f742399d2600019bde7b916d816f36d86da40","target":"graph","created_at":"2026-07-05T06:14:05Z","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/2209.14389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e.g., BERT) using smaller downstream datasets. Despite the success of this approach, it remains unclear to what extent these gains are attributable to the massive background corpora employed for pretraining versus to the pretraining objectives themselves. This paper introduces a large-scale study of self-pretraining, where the same (downstream) training data is used for both pretraining and finetuning. In experiments addressing both ELECTRA and RoBERTa models and 10 distinct do","authors_text":"Jeffrey P. Bigham, Kundan Krishna, Saurabh Garg, Zachary C. Lipton","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-28T19:28:43Z","title":"Downstream Datasets Make Surprisingly Good Pretraining Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14389","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":"sha256:62ceee5fc7c6072bb228531abba46123f4ae712f061be3ed11d6f7166442d2c6","target":"record","created_at":"2026-07-05T06:14:05Z","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":"a5de17431b08bc64fb0e487511b53700fb817cb55b1d396a1a49b42d78a75dcc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-28T19:28:43Z","title_canon_sha256":"5cec3daee1b0319c866d5f36ec225a9c01e63c5f90b1860825f5e73d51ac4280"},"schema_version":"1.0","source":{"id":"2209.14389","kind":"arxiv","version":2}},"canonical_sha256":"c05f866477eae0736d6a11d57fe8efb3568cc29e022824335655c3f43eb4f84e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c05f866477eae0736d6a11d57fe8efb3568cc29e022824335655c3f43eb4f84e","first_computed_at":"2026-07-05T06:14:05.320473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:05.320473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kWK56nEeIFUS+rQ8xh25zXcizdF4LY76wwnHHHdQ5YvYiKZQwKBOaWx5Wi3aNz0q38cZnCtzbFuuFySfJ9GrAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:05.320962Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14389","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62ceee5fc7c6072bb228531abba46123f4ae712f061be3ed11d6f7166442d2c6","sha256:0c25d3e47b42872ecf5bfcba695f742399d2600019bde7b916d816f36d86da40"],"state_sha256":"cf6846c5bb77f8a797c294256b4d190b78fb67af329df6d35b4b9cd0ea052200"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L7BzJxI7lqMcmZAELtGSinKW6Mozbisrak+zi7EM6mFQO2QIqRWI5bCHXZoyat9G2qy/17D7k07vV1rdG0R1Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:14:08.350486Z","bundle_sha256":"cc1da0b959ea7da80a25758d8f91cdc9b5037e50ac154d7af2a17a6b2a954daa"}}