{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3TVHQ5XHOMXNNYE3POV7KTOGD7","short_pith_number":"pith:3TVHQ5XH","canonical_record":{"source":{"id":"2206.07382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-15T08:45:21Z","cross_cats_sorted":[],"title_canon_sha256":"ead58ffbfdbb002af6b9c2dc998004c7f1bdb865aec35536b0eb2123a5968d33","abstract_canon_sha256":"731ec793cefaf71059ea648ab732656e662737656010a650c8ac1350b192ca8f"},"schema_version":"1.0"},"canonical_sha256":"dcea7876e7732ed6e09b7babf54dc61fe82004fef853ef87ddd5e2091ba91b88","source":{"kind":"arxiv","id":"2206.07382","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07382","created_at":"2026-07-05T04:32:04Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07382v1","created_at":"2026-07-05T04:32:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07382","created_at":"2026-07-05T04:32:04Z"},{"alias_kind":"pith_short_12","alias_value":"3TVHQ5XHOMXN","created_at":"2026-07-05T04:32:04Z"},{"alias_kind":"pith_short_16","alias_value":"3TVHQ5XHOMXNNYE3","created_at":"2026-07-05T04:32:04Z"},{"alias_kind":"pith_short_8","alias_value":"3TVHQ5XH","created_at":"2026-07-05T04:32:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3TVHQ5XHOMXNNYE3POV7KTOGD7","target":"record","payload":{"canonical_record":{"source":{"id":"2206.07382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-15T08:45:21Z","cross_cats_sorted":[],"title_canon_sha256":"ead58ffbfdbb002af6b9c2dc998004c7f1bdb865aec35536b0eb2123a5968d33","abstract_canon_sha256":"731ec793cefaf71059ea648ab732656e662737656010a650c8ac1350b192ca8f"},"schema_version":"1.0"},"canonical_sha256":"dcea7876e7732ed6e09b7babf54dc61fe82004fef853ef87ddd5e2091ba91b88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:04.115623Z","signature_b64":"yjxhSo3NFH+XAiJhG0IQjY2Ag44bD1i1tNcRJ9gTIzO06cbwpFZj4P1528p3ECteMgrCnCFVX3pzA8SWK8DfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcea7876e7732ed6e09b7babf54dc61fe82004fef853ef87ddd5e2091ba91b88","last_reissued_at":"2026-07-05T04:32:04.115182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:04.115182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.07382","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":"2026-07-05T04:32:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"40g/Xmsj1Lci9/T+5dWxgMMkE0+vTzMwdOYICtQRPYMQuRTafyrU4skIODSceQsorWgJdkZjfi1GJW1NngWpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:40:27.724365Z"},"content_sha256":"1c684c5b73fc5abd440ca270fd4edf5bdcf2bb98590bb2262154252b34ea3fbb","schema_version":"1.0","event_id":"sha256:1c684c5b73fc5abd440ca270fd4edf5bdcf2bb98590bb2262154252b34ea3fbb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3TVHQ5XHOMXNNYE3POV7KTOGD7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse Structure Search for Parameter-Efficient Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maosong Sun, Ning Ding, Shengding Hu, Yadao Wang, Yasheng Wang, Zhen Zhang, Zhiyuan Liu","submitted_at":"2022-06-15T08:45:21Z","abstract_excerpt":"Adapting large pre-trained models (PTMs) through fine-tuning imposes prohibitive computational and storage burdens. Recent studies of parameter-efficient tuning (PET) find that only optimizing a small portion of parameters conditioned on PTMs could yield on-par performance compared to conventional fine-tuning. Generally, PET methods exquisitely design parameter-efficient modules (PET modules) which could be applied to arbitrary fine-grained positions inside PTMs. However, the effectiveness of these fine-grained positions largely relies on sophisticated manual designation, thereby usually produ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07382","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/2206.07382/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":"2026-07-05T04:32:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J9OEaLOVOBgoqTdHlExpgV7uIqeNMupbHUtkrPM57VkMNmA0ZVAXcEwVCk5hY3AsGQa5DPyj8N0hNalX7tW/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:40:27.725268Z"},"content_sha256":"8defafad0875517c88642d33aa73412e17f0319dcde5f413001eaa83080dcdd6","schema_version":"1.0","event_id":"sha256:8defafad0875517c88642d33aa73412e17f0319dcde5f413001eaa83080dcdd6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3TVHQ5XHOMXNNYE3POV7KTOGD7/bundle.json","state_url":"https://pith.science/pith/3TVHQ5XHOMXNNYE3POV7KTOGD7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3TVHQ5XHOMXNNYE3POV7KTOGD7/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":"2026-08-10T19:40:27Z","links":{"resolver":"https://pith.science/pith/3TVHQ5XHOMXNNYE3POV7KTOGD7","bundle":"https://pith.science/pith/3TVHQ5XHOMXNNYE3POV7KTOGD7/bundle.json","state":"https://pith.science/pith/3TVHQ5XHOMXNNYE3POV7KTOGD7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3TVHQ5XHOMXNNYE3POV7KTOGD7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3TVHQ5XHOMXNNYE3POV7KTOGD7","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":"731ec793cefaf71059ea648ab732656e662737656010a650c8ac1350b192ca8f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-15T08:45:21Z","title_canon_sha256":"ead58ffbfdbb002af6b9c2dc998004c7f1bdb865aec35536b0eb2123a5968d33"},"schema_version":"1.0","source":{"id":"2206.07382","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07382","created_at":"2026-07-05T04:32:04Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07382v1","created_at":"2026-07-05T04:32:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07382","created_at":"2026-07-05T04:32:04Z"},{"alias_kind":"pith_short_12","alias_value":"3TVHQ5XHOMXN","created_at":"2026-07-05T04:32:04Z"},{"alias_kind":"pith_short_16","alias_value":"3TVHQ5XHOMXNNYE3","created_at":"2026-07-05T04:32:04Z"},{"alias_kind":"pith_short_8","alias_value":"3TVHQ5XH","created_at":"2026-07-05T04:32:04Z"}],"graph_snapshots":[{"event_id":"sha256:8defafad0875517c88642d33aa73412e17f0319dcde5f413001eaa83080dcdd6","target":"graph","created_at":"2026-07-05T04:32:04Z","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/2206.07382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adapting large pre-trained models (PTMs) through fine-tuning imposes prohibitive computational and storage burdens. Recent studies of parameter-efficient tuning (PET) find that only optimizing a small portion of parameters conditioned on PTMs could yield on-par performance compared to conventional fine-tuning. Generally, PET methods exquisitely design parameter-efficient modules (PET modules) which could be applied to arbitrary fine-grained positions inside PTMs. However, the effectiveness of these fine-grained positions largely relies on sophisticated manual designation, thereby usually produ","authors_text":"Maosong Sun, Ning Ding, Shengding Hu, Yadao Wang, Yasheng Wang, Zhen Zhang, Zhiyuan Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-15T08:45:21Z","title":"Sparse Structure Search for Parameter-Efficient Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07382","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":"sha256:1c684c5b73fc5abd440ca270fd4edf5bdcf2bb98590bb2262154252b34ea3fbb","target":"record","created_at":"2026-07-05T04:32:04Z","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":"731ec793cefaf71059ea648ab732656e662737656010a650c8ac1350b192ca8f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-15T08:45:21Z","title_canon_sha256":"ead58ffbfdbb002af6b9c2dc998004c7f1bdb865aec35536b0eb2123a5968d33"},"schema_version":"1.0","source":{"id":"2206.07382","kind":"arxiv","version":1}},"canonical_sha256":"dcea7876e7732ed6e09b7babf54dc61fe82004fef853ef87ddd5e2091ba91b88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcea7876e7732ed6e09b7babf54dc61fe82004fef853ef87ddd5e2091ba91b88","first_computed_at":"2026-07-05T04:32:04.115182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:04.115182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yjxhSo3NFH+XAiJhG0IQjY2Ag44bD1i1tNcRJ9gTIzO06cbwpFZj4P1528p3ECteMgrCnCFVX3pzA8SWK8DfDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:04.115623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.07382","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c684c5b73fc5abd440ca270fd4edf5bdcf2bb98590bb2262154252b34ea3fbb","sha256:8defafad0875517c88642d33aa73412e17f0319dcde5f413001eaa83080dcdd6"],"state_sha256":"66cace7775067b8f39311d90e34b4a255fcb7bf3dd199997d507853ac78f97b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iqdLfJzkhdJDfhrTOlHcjungaZE//VT3GnqY3m4wMf8Xxsx/DGc2yrbWIn/of0237UgL+vWkNzP3+tUROKSVCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T19:40:27.732357Z","bundle_sha256":"c576c1d6060cf7248272925be891400e31ee23b24c1cc71232d596a5d2d18403"}}