{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:P6SBCWNH72CQAHIQQU7XNDWJUV","short_pith_number":"pith:P6SBCWNH","canonical_record":{"source":{"id":"2111.01754","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-02T17:26:50Z","cross_cats_sorted":[],"title_canon_sha256":"c1ccd957254c32857513ddfd911b06b6a2e225a1722214bdd13c2a0ffb58d6e2","abstract_canon_sha256":"c2892e4173ec035e29581ca72384643f8b793f629d7e608eed4a82f336fd56da"},"schema_version":"1.0"},"canonical_sha256":"7fa41159a7fe85001d10853f768ec9a55540378cb8be32128fb6f1902446076b","source":{"kind":"arxiv","id":"2111.01754","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.01754","created_at":"2026-07-05T03:28:32Z"},{"alias_kind":"arxiv_version","alias_value":"2111.01754v1","created_at":"2026-07-05T03:28:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01754","created_at":"2026-07-05T03:28:32Z"},{"alias_kind":"pith_short_12","alias_value":"P6SBCWNH72CQ","created_at":"2026-07-05T03:28:32Z"},{"alias_kind":"pith_short_16","alias_value":"P6SBCWNH72CQAHIQ","created_at":"2026-07-05T03:28:32Z"},{"alias_kind":"pith_short_8","alias_value":"P6SBCWNH","created_at":"2026-07-05T03:28:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:P6SBCWNH72CQAHIQQU7XNDWJUV","target":"record","payload":{"canonical_record":{"source":{"id":"2111.01754","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-02T17:26:50Z","cross_cats_sorted":[],"title_canon_sha256":"c1ccd957254c32857513ddfd911b06b6a2e225a1722214bdd13c2a0ffb58d6e2","abstract_canon_sha256":"c2892e4173ec035e29581ca72384643f8b793f629d7e608eed4a82f336fd56da"},"schema_version":"1.0"},"canonical_sha256":"7fa41159a7fe85001d10853f768ec9a55540378cb8be32128fb6f1902446076b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:28:32.565019Z","signature_b64":"uvwk2JTIRylOahs4TdyZMcFadL8/Us81S3YW1M/OVFCCvwrUfb3W5EhC+YH41msEAJuzJmdHsKKKjAKQvIKpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fa41159a7fe85001d10853f768ec9a55540378cb8be32128fb6f1902446076b","last_reissued_at":"2026-07-05T03:28:32.564439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:28:32.564439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.01754","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":"2026-07-05T03:28:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LE2uT+a+9oO63CZme+EpUe3e9KZw4NnriHNtiOIlXgR8d2mpEZTKfmUYYZBU6a/Xr0myP9YUXrvRCPW9a1cnBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:40:30.033552Z"},"content_sha256":"b548031c407fe8e9b21c664e4969ef594ae24169c312c1e171598f5949c99a19","schema_version":"1.0","event_id":"sha256:b548031c407fe8e9b21c664e4969ef594ae24169c312c1e171598f5949c99a19"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:P6SBCWNH72CQAHIQQU7XNDWJUV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Learning to Improve Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aniruddh Raghu, David Duvenaud, Jonathan Lorraine, Matthew McDermott, Simon Kornblith","submitted_at":"2021-11-02T17:26:50Z","abstract_excerpt":"Pre-training (PT) followed by fine-tuning (FT) is an effective method for training neural networks, and has led to significant performance improvements in many domains. PT can incorporate various design choices such as task and data reweighting strategies, augmentation policies, and noise models, all of which can significantly impact the quality of representations learned. The hyperparameters introduced by these strategies therefore must be tuned appropriately. However, setting the values of these hyperparameters is challenging. Most existing methods either struggle to scale to high dimensions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01754","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/2111.01754/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":"2026-07-05T03:28:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CXxL2bLYruYQ4b9079gBYyFDTgNZXlkpBgFzjk4UQuOB6EZAVoIbGgmh7tvDg9U/Z/eUqeQ1qhE8pGuj1S2kDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:40:30.033924Z"},"content_sha256":"a8a5075383075b11ef91bc061c5ed41644b1b8b5a1282f3ba7e04b92b6024fea","schema_version":"1.0","event_id":"sha256:a8a5075383075b11ef91bc061c5ed41644b1b8b5a1282f3ba7e04b92b6024fea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P6SBCWNH72CQAHIQQU7XNDWJUV/bundle.json","state_url":"https://pith.science/pith/P6SBCWNH72CQAHIQQU7XNDWJUV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P6SBCWNH72CQAHIQQU7XNDWJUV/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":"2026-07-07T15:40:30Z","links":{"resolver":"https://pith.science/pith/P6SBCWNH72CQAHIQQU7XNDWJUV","bundle":"https://pith.science/pith/P6SBCWNH72CQAHIQQU7XNDWJUV/bundle.json","state":"https://pith.science/pith/P6SBCWNH72CQAHIQQU7XNDWJUV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P6SBCWNH72CQAHIQQU7XNDWJUV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:P6SBCWNH72CQAHIQQU7XNDWJUV","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":"c2892e4173ec035e29581ca72384643f8b793f629d7e608eed4a82f336fd56da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-02T17:26:50Z","title_canon_sha256":"c1ccd957254c32857513ddfd911b06b6a2e225a1722214bdd13c2a0ffb58d6e2"},"schema_version":"1.0","source":{"id":"2111.01754","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.01754","created_at":"2026-07-05T03:28:32Z"},{"alias_kind":"arxiv_version","alias_value":"2111.01754v1","created_at":"2026-07-05T03:28:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01754","created_at":"2026-07-05T03:28:32Z"},{"alias_kind":"pith_short_12","alias_value":"P6SBCWNH72CQ","created_at":"2026-07-05T03:28:32Z"},{"alias_kind":"pith_short_16","alias_value":"P6SBCWNH72CQAHIQ","created_at":"2026-07-05T03:28:32Z"},{"alias_kind":"pith_short_8","alias_value":"P6SBCWNH","created_at":"2026-07-05T03:28:32Z"}],"graph_snapshots":[{"event_id":"sha256:a8a5075383075b11ef91bc061c5ed41644b1b8b5a1282f3ba7e04b92b6024fea","target":"graph","created_at":"2026-07-05T03:28:32Z","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/2111.01754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training (PT) followed by fine-tuning (FT) is an effective method for training neural networks, and has led to significant performance improvements in many domains. PT can incorporate various design choices such as task and data reweighting strategies, augmentation policies, and noise models, all of which can significantly impact the quality of representations learned. The hyperparameters introduced by these strategies therefore must be tuned appropriately. However, setting the values of these hyperparameters is challenging. Most existing methods either struggle to scale to high dimensions","authors_text":"Aniruddh Raghu, David Duvenaud, Jonathan Lorraine, Matthew McDermott, Simon Kornblith","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-02T17:26:50Z","title":"Meta-Learning to Improve Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01754","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:b548031c407fe8e9b21c664e4969ef594ae24169c312c1e171598f5949c99a19","target":"record","created_at":"2026-07-05T03:28:32Z","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":"c2892e4173ec035e29581ca72384643f8b793f629d7e608eed4a82f336fd56da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-02T17:26:50Z","title_canon_sha256":"c1ccd957254c32857513ddfd911b06b6a2e225a1722214bdd13c2a0ffb58d6e2"},"schema_version":"1.0","source":{"id":"2111.01754","kind":"arxiv","version":1}},"canonical_sha256":"7fa41159a7fe85001d10853f768ec9a55540378cb8be32128fb6f1902446076b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fa41159a7fe85001d10853f768ec9a55540378cb8be32128fb6f1902446076b","first_computed_at":"2026-07-05T03:28:32.564439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:28:32.564439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uvwk2JTIRylOahs4TdyZMcFadL8/Us81S3YW1M/OVFCCvwrUfb3W5EhC+YH41msEAJuzJmdHsKKKjAKQvIKpBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:28:32.565019Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.01754","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b548031c407fe8e9b21c664e4969ef594ae24169c312c1e171598f5949c99a19","sha256:a8a5075383075b11ef91bc061c5ed41644b1b8b5a1282f3ba7e04b92b6024fea"],"state_sha256":"0c4e06f1a6a8ace41d8947ff7db4b9e02dc17d98ffdefd4c1d0657e7122566e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GTyH4O2f2Z34GynYWh01GVSeJLJOXwjlcXSUlmPiw/E/nSPlRCXir92zeyirYNFSKBnUisWXkIczxEAHeTYnAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:40:30.036093Z","bundle_sha256":"709878546c074a38c9827dae3f6b49e6300559e1c85f80596823c7a6de12721e"}}