{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:EYCV5NY64RXW6X7L5YGLJJMDC3","short_pith_number":"pith:EYCV5NY6","canonical_record":{"source":{"id":"2110.04366","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-08T20:22:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"85ed685b1bed952763a6c8880ff93e7e21473016ac6f63992fe614d83ba38104","abstract_canon_sha256":"2a28b0a046af80af58f98e3aff4aab57c8faaf7d446cfb9c06f15ce4c6c5df6a"},"schema_version":"1.0"},"canonical_sha256":"26055eb71ee46f6f5febee0cb4a58316f407f530f42fd944f95103099728cd2b","source":{"kind":"arxiv","id":"2110.04366","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04366","created_at":"2026-07-05T03:53:38Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04366v3","created_at":"2026-07-05T03:53:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04366","created_at":"2026-07-05T03:53:38Z"},{"alias_kind":"pith_short_12","alias_value":"EYCV5NY64RXW","created_at":"2026-07-05T03:53:38Z"},{"alias_kind":"pith_short_16","alias_value":"EYCV5NY64RXW6X7L","created_at":"2026-07-05T03:53:38Z"},{"alias_kind":"pith_short_8","alias_value":"EYCV5NY6","created_at":"2026-07-05T03:53:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:EYCV5NY64RXW6X7L5YGLJJMDC3","target":"record","payload":{"canonical_record":{"source":{"id":"2110.04366","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-08T20:22:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"85ed685b1bed952763a6c8880ff93e7e21473016ac6f63992fe614d83ba38104","abstract_canon_sha256":"2a28b0a046af80af58f98e3aff4aab57c8faaf7d446cfb9c06f15ce4c6c5df6a"},"schema_version":"1.0"},"canonical_sha256":"26055eb71ee46f6f5febee0cb4a58316f407f530f42fd944f95103099728cd2b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:53:38.243915Z","signature_b64":"2Ioj3v9h4+S0yCj25od4xlL/ErU5x5AXi6+Ag+kgDvSYFV2eypWwIVf/7zq6PEXMW+2kEsgZG1CBYDsrZnphBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26055eb71ee46f6f5febee0cb4a58316f407f530f42fd944f95103099728cd2b","last_reissued_at":"2026-07-05T03:53:38.243372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:53:38.243372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.04366","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:53:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ovCsm9vnK0uKMjQdLEXfX5jTDtq9hY0dCL38z4wdiGuzz7+DfuQeyZNvhmImsYfFNgCdGfSx58k+Qd1HcdiDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:43:32.627581Z"},"content_sha256":"539554eac75134437eb8f43702adf06648e8d5489d53e0dce39a45c8f4f1ee87","schema_version":"1.0","event_id":"sha256:539554eac75134437eb8f43702adf06648e8d5489d53e0dce39a45c8f4f1ee87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:EYCV5NY64RXW6X7L5YGLJJMDC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards a Unified View of Parameter-Efficient Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chunting Zhou, Graham Neubig, Junxian He, Taylor Berg-Kirkpatrick, Xuezhe Ma","submitted_at":"2021-10-08T20:22:26Z","abstract_excerpt":"Fine-tuning large pre-trained language models on downstream tasks has become the de-facto learning paradigm in NLP. However, conventional approaches fine-tune all the parameters of the pre-trained model, which becomes prohibitive as the model size and the number of tasks grow. Recent work has proposed a variety of parameter-efficient transfer learning methods that only fine-tune a small number of (extra) parameters to attain strong performance. While effective, the critical ingredients for success and the connections among the various methods are poorly understood. In this paper, we break down"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04366","kind":"arxiv","version":3},"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/2110.04366/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":"2026-07-05T03:53:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7PbgDz41L9mNw9kRdF44Y6wHYSPgt1EAjlacFraJOOihqgYhHtD5vQzI3mUb2LsvTmk3TX59iYmRUJCpXZLeBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:43:32.628439Z"},"content_sha256":"5eb121ebd37c4008eccb8bba7d8a9dc02ee0af60e1205595239829ada5b69436","schema_version":"1.0","event_id":"sha256:5eb121ebd37c4008eccb8bba7d8a9dc02ee0af60e1205595239829ada5b69436"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EYCV5NY64RXW6X7L5YGLJJMDC3/bundle.json","state_url":"https://pith.science/pith/EYCV5NY64RXW6X7L5YGLJJMDC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EYCV5NY64RXW6X7L5YGLJJMDC3/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":"2026-08-03T17:43:32Z","links":{"resolver":"https://pith.science/pith/EYCV5NY64RXW6X7L5YGLJJMDC3","bundle":"https://pith.science/pith/EYCV5NY64RXW6X7L5YGLJJMDC3/bundle.json","state":"https://pith.science/pith/EYCV5NY64RXW6X7L5YGLJJMDC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EYCV5NY64RXW6X7L5YGLJJMDC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EYCV5NY64RXW6X7L5YGLJJMDC3","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":"2a28b0a046af80af58f98e3aff4aab57c8faaf7d446cfb9c06f15ce4c6c5df6a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-08T20:22:26Z","title_canon_sha256":"85ed685b1bed952763a6c8880ff93e7e21473016ac6f63992fe614d83ba38104"},"schema_version":"1.0","source":{"id":"2110.04366","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.04366","created_at":"2026-07-05T03:53:38Z"},{"alias_kind":"arxiv_version","alias_value":"2110.04366v3","created_at":"2026-07-05T03:53:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04366","created_at":"2026-07-05T03:53:38Z"},{"alias_kind":"pith_short_12","alias_value":"EYCV5NY64RXW","created_at":"2026-07-05T03:53:38Z"},{"alias_kind":"pith_short_16","alias_value":"EYCV5NY64RXW6X7L","created_at":"2026-07-05T03:53:38Z"},{"alias_kind":"pith_short_8","alias_value":"EYCV5NY6","created_at":"2026-07-05T03:53:38Z"}],"graph_snapshots":[{"event_id":"sha256:5eb121ebd37c4008eccb8bba7d8a9dc02ee0af60e1205595239829ada5b69436","target":"graph","created_at":"2026-07-05T03:53:38Z","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/2110.04366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning large pre-trained language models on downstream tasks has become the de-facto learning paradigm in NLP. However, conventional approaches fine-tune all the parameters of the pre-trained model, which becomes prohibitive as the model size and the number of tasks grow. Recent work has proposed a variety of parameter-efficient transfer learning methods that only fine-tune a small number of (extra) parameters to attain strong performance. While effective, the critical ingredients for success and the connections among the various methods are poorly understood. In this paper, we break down","authors_text":"Chunting Zhou, Graham Neubig, Junxian He, Taylor Berg-Kirkpatrick, Xuezhe Ma","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-08T20:22:26Z","title":"Towards a Unified View of Parameter-Efficient Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04366","kind":"arxiv","version":3},"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":"sha256:539554eac75134437eb8f43702adf06648e8d5489d53e0dce39a45c8f4f1ee87","target":"record","created_at":"2026-07-05T03:53:38Z","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":"2a28b0a046af80af58f98e3aff4aab57c8faaf7d446cfb9c06f15ce4c6c5df6a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-08T20:22:26Z","title_canon_sha256":"85ed685b1bed952763a6c8880ff93e7e21473016ac6f63992fe614d83ba38104"},"schema_version":"1.0","source":{"id":"2110.04366","kind":"arxiv","version":3}},"canonical_sha256":"26055eb71ee46f6f5febee0cb4a58316f407f530f42fd944f95103099728cd2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26055eb71ee46f6f5febee0cb4a58316f407f530f42fd944f95103099728cd2b","first_computed_at":"2026-07-05T03:53:38.243372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:53:38.243372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Ioj3v9h4+S0yCj25od4xlL/ErU5x5AXi6+Ag+kgDvSYFV2eypWwIVf/7zq6PEXMW+2kEsgZG1CBYDsrZnphBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:53:38.243915Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.04366","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:539554eac75134437eb8f43702adf06648e8d5489d53e0dce39a45c8f4f1ee87","sha256:5eb121ebd37c4008eccb8bba7d8a9dc02ee0af60e1205595239829ada5b69436"],"state_sha256":"88287a881512621497db4cdb7a4ded14b41c13280624a528f1e6cf1d82570ae4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BOFshJIP70aHx062l0o75dsQ4LvsABwLUZpbabFsS5D35U0YqptIf0T96X0Ap44Aizq9vsFGgMsqrqD+3R9iCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:43:32.634274Z","bundle_sha256":"5b4e2ba8e4aa12b062f8e522d2acacf3d137cd2a4c96dfd33de5c16ee647cc0d"}}