{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6TCFVRS275T2PRI6P37B4THHJ4","short_pith_number":"pith:6TCFVRS2","canonical_record":{"source":{"id":"2310.01843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-03T07:17:58Z","cross_cats_sorted":[],"title_canon_sha256":"ad70e0de7f1375b43ac9c799b07c35bee92d8e1bed4f2a77905e6ff9e8dec55b","abstract_canon_sha256":"cac13475de6c8a318b93cfa9b306a2d054618810df1ced479877e2c325e80149"},"schema_version":"1.0"},"canonical_sha256":"f4c45ac65aff67a7c51e7efe1e4ce74f111fa3ec753562a06374971e843cb8a6","source":{"kind":"arxiv","id":"2310.01843","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01843","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01843v1","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01843","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"pith_short_12","alias_value":"6TCFVRS275T2","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"pith_short_16","alias_value":"6TCFVRS275T2PRI6","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"pith_short_8","alias_value":"6TCFVRS2","created_at":"2026-07-05T06:56:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6TCFVRS275T2PRI6P37B4THHJ4","target":"record","payload":{"canonical_record":{"source":{"id":"2310.01843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-03T07:17:58Z","cross_cats_sorted":[],"title_canon_sha256":"ad70e0de7f1375b43ac9c799b07c35bee92d8e1bed4f2a77905e6ff9e8dec55b","abstract_canon_sha256":"cac13475de6c8a318b93cfa9b306a2d054618810df1ced479877e2c325e80149"},"schema_version":"1.0"},"canonical_sha256":"f4c45ac65aff67a7c51e7efe1e4ce74f111fa3ec753562a06374971e843cb8a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:46.607802Z","signature_b64":"UHOdqkq4EIDSE2pAPBrJZFsA3A3PBZPrlxIhHi4n+GfRZH2PGvnNDlVwY0Hzj7bG04qZQzT98nC+61YPSTIjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4c45ac65aff67a7c51e7efe1e4ce74f111fa3ec753562a06374971e843cb8a6","last_reissued_at":"2026-07-05T06:56:46.607292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:46.607292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.01843","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":"2026-07-05T06:56:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xRMTz014VkeJPs4mRY6IKxLkGEx+8V8yPyBSJKdg+FZlDsCsnq7n0DFhrtSI2MgWzJ/dvz5caPg8OsaTOH4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:42:32.415270Z"},"content_sha256":"486bd03bafd48d9f3cf99d856c111fc761f65759090ab7f1c35db544f881fe6d","schema_version":"1.0","event_id":"sha256:486bd03bafd48d9f3cf99d856c111fc761f65759090ab7f1c35db544f881fe6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6TCFVRS275T2PRI6P37B4THHJ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Selective Feature Adapter for Dense Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Linjie Yang, Peng Wang, Qi Fan, Xiaojie Jin, Xueqing Deng","submitted_at":"2023-10-03T07:17:58Z","abstract_excerpt":"Fine-tuning pre-trained transformer models, e.g., Swin Transformer, are successful in numerous downstream for dense prediction vision tasks. However, one major issue is the cost/storage of their huge amount of parameters, which becomes increasingly challenging to handle with the growing amount of vision tasks. In this paper, we propose an effective approach to alleviate the issue, namely selective feature adapter (SFA). It achieves state-of-the-art (SoTA) performance under any given budget of trainable parameters, and demonstrates comparable or better performance than fully fine-tuned models a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01843","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/2310.01843/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":"2026-07-05T06:56:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4bI3d6ceAlqCYvmzORbAC8u8Q1/SiuOZEPX+XandbYWegg5HA7yvc5PoCRLLhOhht7VSXu7UjvU1md1nbgRmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:42:32.415654Z"},"content_sha256":"cf4e1b41c45a6b8aa49cc170f1debaf61b414b41f2f9bbf21d841edbd2cfe0bd","schema_version":"1.0","event_id":"sha256:cf4e1b41c45a6b8aa49cc170f1debaf61b414b41f2f9bbf21d841edbd2cfe0bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TCFVRS275T2PRI6P37B4THHJ4/bundle.json","state_url":"https://pith.science/pith/6TCFVRS275T2PRI6P37B4THHJ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TCFVRS275T2PRI6P37B4THHJ4/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":"2026-08-05T21:42:32Z","links":{"resolver":"https://pith.science/pith/6TCFVRS275T2PRI6P37B4THHJ4","bundle":"https://pith.science/pith/6TCFVRS275T2PRI6P37B4THHJ4/bundle.json","state":"https://pith.science/pith/6TCFVRS275T2PRI6P37B4THHJ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TCFVRS275T2PRI6P37B4THHJ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6TCFVRS275T2PRI6P37B4THHJ4","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":"cac13475de6c8a318b93cfa9b306a2d054618810df1ced479877e2c325e80149","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-03T07:17:58Z","title_canon_sha256":"ad70e0de7f1375b43ac9c799b07c35bee92d8e1bed4f2a77905e6ff9e8dec55b"},"schema_version":"1.0","source":{"id":"2310.01843","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.01843","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.01843v1","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01843","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"pith_short_12","alias_value":"6TCFVRS275T2","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"pith_short_16","alias_value":"6TCFVRS275T2PRI6","created_at":"2026-07-05T06:56:46Z"},{"alias_kind":"pith_short_8","alias_value":"6TCFVRS2","created_at":"2026-07-05T06:56:46Z"}],"graph_snapshots":[{"event_id":"sha256:cf4e1b41c45a6b8aa49cc170f1debaf61b414b41f2f9bbf21d841edbd2cfe0bd","target":"graph","created_at":"2026-07-05T06:56:46Z","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/2310.01843/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning pre-trained transformer models, e.g., Swin Transformer, are successful in numerous downstream for dense prediction vision tasks. However, one major issue is the cost/storage of their huge amount of parameters, which becomes increasingly challenging to handle with the growing amount of vision tasks. In this paper, we propose an effective approach to alleviate the issue, namely selective feature adapter (SFA). It achieves state-of-the-art (SoTA) performance under any given budget of trainable parameters, and demonstrates comparable or better performance than fully fine-tuned models a","authors_text":"Linjie Yang, Peng Wang, Qi Fan, Xiaojie Jin, Xueqing Deng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-03T07:17:58Z","title":"Selective Feature Adapter for Dense Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01843","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":"sha256:486bd03bafd48d9f3cf99d856c111fc761f65759090ab7f1c35db544f881fe6d","target":"record","created_at":"2026-07-05T06:56:46Z","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":"cac13475de6c8a318b93cfa9b306a2d054618810df1ced479877e2c325e80149","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-03T07:17:58Z","title_canon_sha256":"ad70e0de7f1375b43ac9c799b07c35bee92d8e1bed4f2a77905e6ff9e8dec55b"},"schema_version":"1.0","source":{"id":"2310.01843","kind":"arxiv","version":1}},"canonical_sha256":"f4c45ac65aff67a7c51e7efe1e4ce74f111fa3ec753562a06374971e843cb8a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4c45ac65aff67a7c51e7efe1e4ce74f111fa3ec753562a06374971e843cb8a6","first_computed_at":"2026-07-05T06:56:46.607292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:56:46.607292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UHOdqkq4EIDSE2pAPBrJZFsA3A3PBZPrlxIhHi4n+GfRZH2PGvnNDlVwY0Hzj7bG04qZQzT98nC+61YPSTIjAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:56:46.607802Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.01843","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:486bd03bafd48d9f3cf99d856c111fc761f65759090ab7f1c35db544f881fe6d","sha256:cf4e1b41c45a6b8aa49cc170f1debaf61b414b41f2f9bbf21d841edbd2cfe0bd"],"state_sha256":"1e5a6f003d14e53c0098c303e5584ffe289fc630a95de8cfbc3ffb1f58f6ada0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MdexIHyTaCk99Xh8jF7vt+nIcl8ViyF6uaD3LBynqSHVtO90bGcqE79BNnjt0NN+hZryUlln+vzl1XXzOJRlDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T21:42:32.419123Z","bundle_sha256":"1f9550a94ab99f7a5aef844bde345d196680936bf6679a2618e4cb4480a10041"}}