{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VY7NEKAEBMQZRKS7FGGXQ42D6S","short_pith_number":"pith:VY7NEKAE","canonical_record":{"source":{"id":"2208.07463","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-15T22:51:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b2d7f793805c4aef8f2327ec146629021c8139e856dede5ec1d5265733c9809","abstract_canon_sha256":"1e68bfc3a490fe81674db20f1399ecea6ca5f1880658ed0d09832c42bce07c0b"},"schema_version":"1.0"},"canonical_sha256":"ae3ed228040b2198aa5f298d787343f4a85c43a6c5195b7438626fc4ec117913","source":{"kind":"arxiv","id":"2208.07463","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.07463","created_at":"2026-07-05T08:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2208.07463v4","created_at":"2026-07-05T08:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.07463","created_at":"2026-07-05T08:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"VY7NEKAEBMQZ","created_at":"2026-07-05T08:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"VY7NEKAEBMQZRKS7","created_at":"2026-07-05T08:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"VY7NEKAE","created_at":"2026-07-05T08:07:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VY7NEKAEBMQZRKS7FGGXQ42D6S","target":"record","payload":{"canonical_record":{"source":{"id":"2208.07463","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-15T22:51:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b2d7f793805c4aef8f2327ec146629021c8139e856dede5ec1d5265733c9809","abstract_canon_sha256":"1e68bfc3a490fe81674db20f1399ecea6ca5f1880658ed0d09832c42bce07c0b"},"schema_version":"1.0"},"canonical_sha256":"ae3ed228040b2198aa5f298d787343f4a85c43a6c5195b7438626fc4ec117913","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:07.902003Z","signature_b64":"Hko1UEo4upRMZMQsZtxhmUvA3lGiVv82KykmnIcTv4E37yX2Eu1va/xLa6OODxhsN0i6EOp1rXLzUk5F5+AnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae3ed228040b2198aa5f298d787343f4a85c43a6c5195b7438626fc4ec117913","last_reissued_at":"2026-07-05T08:07:07.901499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:07.901499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.07463","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:07:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K4MOA/NzuHwuRlLtyuqVJYcO5bhP7+eWPKEw9SXskOJqMTs1qotrgao5rGbKohf0m+dj0j0FXuD2vczv2UaJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:39:11.164305Z"},"content_sha256":"a82703506eada9aab17db0f66b8820292ca0e7b77ecbc7c3c8bd1187376e266a","schema_version":"1.0","event_id":"sha256:a82703506eada9aab17db0f66b8820292ca0e7b77ecbc7c3c8bd1187376e266a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VY7NEKAEBMQZRKS7FGGXQ42D6S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guosheng Hu, Han Zhang, Hao Chen, Jindong Wang, Marios Savvides, Ran Tao, Wei Ye, Xiang Li, Yidong Wang","submitted_at":"2022-08-15T22:51:23Z","abstract_excerpt":"While parameter efficient tuning (PET) methods have shown great potential with transformer architecture on Natural Language Processing (NLP) tasks, their effectiveness with large-scale ConvNets is still under-studied on Computer Vision (CV) tasks. This paper proposes Conv-Adapter, a PET module designed for ConvNets. Conv-Adapter is light-weight, domain-transferable, and architecture-agnostic with generalized performance on different tasks. When transferring on downstream tasks, Conv-Adapter learns tasks-specific feature modulation to the intermediate representations of backbones while keeping "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.07463","kind":"arxiv","version":4},"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/2208.07463/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":"2026-07-05T08:07:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y9Nt9psLNflwRt17lSXoBHq+YfpnGcH5RSIodCIsohb8Fv2TDOflPlx4om/kCPU45RnzuMCH37PuPwkKcMdKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:39:11.164996Z"},"content_sha256":"d1fb2b4270421068107842d67ba2cb48b384e684f05e98a60e596740d3b6386a","schema_version":"1.0","event_id":"sha256:d1fb2b4270421068107842d67ba2cb48b384e684f05e98a60e596740d3b6386a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VY7NEKAEBMQZRKS7FGGXQ42D6S/bundle.json","state_url":"https://pith.science/pith/VY7NEKAEBMQZRKS7FGGXQ42D6S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VY7NEKAEBMQZRKS7FGGXQ42D6S/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":"2026-08-05T15:39:11Z","links":{"resolver":"https://pith.science/pith/VY7NEKAEBMQZRKS7FGGXQ42D6S","bundle":"https://pith.science/pith/VY7NEKAEBMQZRKS7FGGXQ42D6S/bundle.json","state":"https://pith.science/pith/VY7NEKAEBMQZRKS7FGGXQ42D6S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VY7NEKAEBMQZRKS7FGGXQ42D6S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VY7NEKAEBMQZRKS7FGGXQ42D6S","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":"1e68bfc3a490fe81674db20f1399ecea6ca5f1880658ed0d09832c42bce07c0b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-15T22:51:23Z","title_canon_sha256":"7b2d7f793805c4aef8f2327ec146629021c8139e856dede5ec1d5265733c9809"},"schema_version":"1.0","source":{"id":"2208.07463","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.07463","created_at":"2026-07-05T08:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2208.07463v4","created_at":"2026-07-05T08:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.07463","created_at":"2026-07-05T08:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"VY7NEKAEBMQZ","created_at":"2026-07-05T08:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"VY7NEKAEBMQZRKS7","created_at":"2026-07-05T08:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"VY7NEKAE","created_at":"2026-07-05T08:07:07Z"}],"graph_snapshots":[{"event_id":"sha256:d1fb2b4270421068107842d67ba2cb48b384e684f05e98a60e596740d3b6386a","target":"graph","created_at":"2026-07-05T08:07:07Z","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/2208.07463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While parameter efficient tuning (PET) methods have shown great potential with transformer architecture on Natural Language Processing (NLP) tasks, their effectiveness with large-scale ConvNets is still under-studied on Computer Vision (CV) tasks. This paper proposes Conv-Adapter, a PET module designed for ConvNets. Conv-Adapter is light-weight, domain-transferable, and architecture-agnostic with generalized performance on different tasks. When transferring on downstream tasks, Conv-Adapter learns tasks-specific feature modulation to the intermediate representations of backbones while keeping ","authors_text":"Guosheng Hu, Han Zhang, Hao Chen, Jindong Wang, Marios Savvides, Ran Tao, Wei Ye, Xiang Li, Yidong Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-15T22:51:23Z","title":"Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.07463","kind":"arxiv","version":4},"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:a82703506eada9aab17db0f66b8820292ca0e7b77ecbc7c3c8bd1187376e266a","target":"record","created_at":"2026-07-05T08:07:07Z","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":"1e68bfc3a490fe81674db20f1399ecea6ca5f1880658ed0d09832c42bce07c0b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-15T22:51:23Z","title_canon_sha256":"7b2d7f793805c4aef8f2327ec146629021c8139e856dede5ec1d5265733c9809"},"schema_version":"1.0","source":{"id":"2208.07463","kind":"arxiv","version":4}},"canonical_sha256":"ae3ed228040b2198aa5f298d787343f4a85c43a6c5195b7438626fc4ec117913","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae3ed228040b2198aa5f298d787343f4a85c43a6c5195b7438626fc4ec117913","first_computed_at":"2026-07-05T08:07:07.901499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:07.901499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hko1UEo4upRMZMQsZtxhmUvA3lGiVv82KykmnIcTv4E37yX2Eu1va/xLa6OODxhsN0i6EOp1rXLzUk5F5+AnDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:07.902003Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.07463","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a82703506eada9aab17db0f66b8820292ca0e7b77ecbc7c3c8bd1187376e266a","sha256:d1fb2b4270421068107842d67ba2cb48b384e684f05e98a60e596740d3b6386a"],"state_sha256":"866da70136ed1ddb9591ea1a597edbb57b07aa0e08fd5d9aeb14c45c998c2693"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"45ISYj+uC66SmG0Z3tc6WLYDOqI0J4hVcWDyeHcFzEUuLosIpYGKgUTFFa4JF7QEbyPISC8TGKKl+gJeD1oFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:39:11.170891Z","bundle_sha256":"317acd10d66a10e42cebf1ca5a5475fb72d11b3ebce47ce42a0828fe2326d021"}}