{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2CZEAAZV5J3K6P6O75ELGKIJD6","short_pith_number":"pith:2CZEAAZV","canonical_record":{"source":{"id":"2205.12453","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T02:51:57Z","cross_cats_sorted":[],"title_canon_sha256":"2953949a3641baf33b5289545b7b853b0d2df9303379a39ab2f3e49bbd25233c","abstract_canon_sha256":"471b6677af75a853a2ec1e4b264957a2b50c02dfe0b66576d82907826d54f42d"},"schema_version":"1.0"},"canonical_sha256":"d0b2400335ea76af3fceff48b329091f9b411ce15122e81a4fc4fa7d1853f036","source":{"kind":"arxiv","id":"2205.12453","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12453","created_at":"2026-07-05T05:23:31Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12453v2","created_at":"2026-07-05T05:23:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12453","created_at":"2026-07-05T05:23:31Z"},{"alias_kind":"pith_short_12","alias_value":"2CZEAAZV5J3K","created_at":"2026-07-05T05:23:31Z"},{"alias_kind":"pith_short_16","alias_value":"2CZEAAZV5J3K6P6O","created_at":"2026-07-05T05:23:31Z"},{"alias_kind":"pith_short_8","alias_value":"2CZEAAZV","created_at":"2026-07-05T05:23:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2CZEAAZV5J3K6P6O75ELGKIJD6","target":"record","payload":{"canonical_record":{"source":{"id":"2205.12453","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T02:51:57Z","cross_cats_sorted":[],"title_canon_sha256":"2953949a3641baf33b5289545b7b853b0d2df9303379a39ab2f3e49bbd25233c","abstract_canon_sha256":"471b6677af75a853a2ec1e4b264957a2b50c02dfe0b66576d82907826d54f42d"},"schema_version":"1.0"},"canonical_sha256":"d0b2400335ea76af3fceff48b329091f9b411ce15122e81a4fc4fa7d1853f036","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:31.555218Z","signature_b64":"SfTdWbstVzuo4cbrRNBu5pSsXGIa/ZaV5YNh9h2hk4l4AOe+UE2L9a9qvnftyzLI0itFxal4avkUAbl0Li+uAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0b2400335ea76af3fceff48b329091f9b411ce15122e81a4fc4fa7d1853f036","last_reissued_at":"2026-07-05T05:23:31.554785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:31.554785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.12453","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":"2026-07-05T05:23:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8SatHoyXtbo8NMH6+xxLxTynP+C+oCp2g+A7ig5xtuDgeTTWh2BreeE4ioxEajujFwA0O5Akqu2EQHZxzVHjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:31:08.136833Z"},"content_sha256":"b9ed6a87e12129f4a77b4cd7d3537d16e3879fa3dbf345677923af473d13dd24","schema_version":"1.0","event_id":"sha256:b9ed6a87e12129f4a77b4cd7d3537d16e3879fa3dbf345677923af473d13dd24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2CZEAAZV5J3K6P6O75ELGKIJD6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Know Where You're Going: Meta-Learning for Parameter-Efficient Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jonathan May, Mozhdeh Gheini, Xuezhe Ma","submitted_at":"2022-05-25T02:51:57Z","abstract_excerpt":"A recent family of techniques, dubbed lightweight fine-tuning methods, facilitates parameter-efficient transfer learning by updating only a small set of additional parameters while keeping the parameters of the pretrained language model frozen. While proven to be an effective method, there are no existing studies on if and how such knowledge of the downstream fine-tuning approach should affect the pretraining stage. In this work, we show that taking the ultimate choice of fine-tuning method into consideration boosts the performance of parameter-efficient fine-tuning. By relying on optimization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12453","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/2205.12453/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":"2026-07-05T05:23:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+vgV/rHxVvKDKjlkdPtgBXqqZeoyo9xZBPkLCAocPePXKoBtHErHHnv5oMA7S3vrubV0FJul+J99qyo952xtAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:31:08.137587Z"},"content_sha256":"51fffab6d4e4bc70ae94a2ec83bc3e79c3fb95cc2f32bc23378ccfa5c242e8d1","schema_version":"1.0","event_id":"sha256:51fffab6d4e4bc70ae94a2ec83bc3e79c3fb95cc2f32bc23378ccfa5c242e8d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2CZEAAZV5J3K6P6O75ELGKIJD6/bundle.json","state_url":"https://pith.science/pith/2CZEAAZV5J3K6P6O75ELGKIJD6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2CZEAAZV5J3K6P6O75ELGKIJD6/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":"2026-08-20T15:31:08Z","links":{"resolver":"https://pith.science/pith/2CZEAAZV5J3K6P6O75ELGKIJD6","bundle":"https://pith.science/pith/2CZEAAZV5J3K6P6O75ELGKIJD6/bundle.json","state":"https://pith.science/pith/2CZEAAZV5J3K6P6O75ELGKIJD6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2CZEAAZV5J3K6P6O75ELGKIJD6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2CZEAAZV5J3K6P6O75ELGKIJD6","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":"471b6677af75a853a2ec1e4b264957a2b50c02dfe0b66576d82907826d54f42d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T02:51:57Z","title_canon_sha256":"2953949a3641baf33b5289545b7b853b0d2df9303379a39ab2f3e49bbd25233c"},"schema_version":"1.0","source":{"id":"2205.12453","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12453","created_at":"2026-07-05T05:23:31Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12453v2","created_at":"2026-07-05T05:23:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12453","created_at":"2026-07-05T05:23:31Z"},{"alias_kind":"pith_short_12","alias_value":"2CZEAAZV5J3K","created_at":"2026-07-05T05:23:31Z"},{"alias_kind":"pith_short_16","alias_value":"2CZEAAZV5J3K6P6O","created_at":"2026-07-05T05:23:31Z"},{"alias_kind":"pith_short_8","alias_value":"2CZEAAZV","created_at":"2026-07-05T05:23:31Z"}],"graph_snapshots":[{"event_id":"sha256:51fffab6d4e4bc70ae94a2ec83bc3e79c3fb95cc2f32bc23378ccfa5c242e8d1","target":"graph","created_at":"2026-07-05T05:23:31Z","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/2205.12453/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A recent family of techniques, dubbed lightweight fine-tuning methods, facilitates parameter-efficient transfer learning by updating only a small set of additional parameters while keeping the parameters of the pretrained language model frozen. While proven to be an effective method, there are no existing studies on if and how such knowledge of the downstream fine-tuning approach should affect the pretraining stage. In this work, we show that taking the ultimate choice of fine-tuning method into consideration boosts the performance of parameter-efficient fine-tuning. By relying on optimization","authors_text":"Jonathan May, Mozhdeh Gheini, Xuezhe Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T02:51:57Z","title":"Know Where You're Going: Meta-Learning for Parameter-Efficient Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12453","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:b9ed6a87e12129f4a77b4cd7d3537d16e3879fa3dbf345677923af473d13dd24","target":"record","created_at":"2026-07-05T05:23:31Z","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":"471b6677af75a853a2ec1e4b264957a2b50c02dfe0b66576d82907826d54f42d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T02:51:57Z","title_canon_sha256":"2953949a3641baf33b5289545b7b853b0d2df9303379a39ab2f3e49bbd25233c"},"schema_version":"1.0","source":{"id":"2205.12453","kind":"arxiv","version":2}},"canonical_sha256":"d0b2400335ea76af3fceff48b329091f9b411ce15122e81a4fc4fa7d1853f036","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0b2400335ea76af3fceff48b329091f9b411ce15122e81a4fc4fa7d1853f036","first_computed_at":"2026-07-05T05:23:31.554785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:23:31.554785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SfTdWbstVzuo4cbrRNBu5pSsXGIa/ZaV5YNh9h2hk4l4AOe+UE2L9a9qvnftyzLI0itFxal4avkUAbl0Li+uAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:23:31.555218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.12453","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9ed6a87e12129f4a77b4cd7d3537d16e3879fa3dbf345677923af473d13dd24","sha256:51fffab6d4e4bc70ae94a2ec83bc3e79c3fb95cc2f32bc23378ccfa5c242e8d1"],"state_sha256":"cf4b32b59378eb0733e405ea5753a6fe98e85d223e9d50af4cb10e8bc074c5c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NwvX84vXejGNC4AbHekSLMLKd5YhGRSWsVdfXIrUG8hsKAaDbqVoV12bBiB+QoaaH3QHNvTft/VCCaxoG4LaDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T15:31:08.143707Z","bundle_sha256":"0040c641356936189f7f29c61d0082dbc3ca2d0f5632a463c693a2067e7b07e7"}}