{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SELBH277SOR5BL2JOKVW3JANH7","short_pith_number":"pith:SELBH277","canonical_record":{"source":{"id":"2409.13999","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-21T03:25:18Z","cross_cats_sorted":[],"title_canon_sha256":"2aee9cf43a0cb04b61db781d3929be853def94eb1a279a0a4b5eb824d9e7f8b2","abstract_canon_sha256":"a68d4a414860fac719aefc86690beab311d8789d7df50afd7f97fc196c56c30d"},"schema_version":"1.0"},"canonical_sha256":"911613ebff93a3d0af4972ab6da40d3fe0772a41fbb6ba076ab09397d1554fc8","source":{"kind":"arxiv","id":"2409.13999","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13999","created_at":"2026-07-05T09:10:10Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13999v1","created_at":"2026-07-05T09:10:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13999","created_at":"2026-07-05T09:10:10Z"},{"alias_kind":"pith_short_12","alias_value":"SELBH277SOR5","created_at":"2026-07-05T09:10:10Z"},{"alias_kind":"pith_short_16","alias_value":"SELBH277SOR5BL2J","created_at":"2026-07-05T09:10:10Z"},{"alias_kind":"pith_short_8","alias_value":"SELBH277","created_at":"2026-07-05T09:10:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SELBH277SOR5BL2JOKVW3JANH7","target":"record","payload":{"canonical_record":{"source":{"id":"2409.13999","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-21T03:25:18Z","cross_cats_sorted":[],"title_canon_sha256":"2aee9cf43a0cb04b61db781d3929be853def94eb1a279a0a4b5eb824d9e7f8b2","abstract_canon_sha256":"a68d4a414860fac719aefc86690beab311d8789d7df50afd7f97fc196c56c30d"},"schema_version":"1.0"},"canonical_sha256":"911613ebff93a3d0af4972ab6da40d3fe0772a41fbb6ba076ab09397d1554fc8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:10.219995Z","signature_b64":"J4U2FfcGPXnOmVPPDrkfvaFj2PkXdgab7pbYrO1dqUlt7C/vp6lTp37wpyVGjOm+lHf7P05dpy6B771ywlsrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"911613ebff93a3d0af4972ab6da40d3fe0772a41fbb6ba076ab09397d1554fc8","last_reissued_at":"2026-07-05T09:10:10.219535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:10.219535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.13999","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":"2026-07-05T09:10:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FJn1KaYcdXOlxGN5Z+5Fn/n7u5lplOivGOhsJrSRRPMxEFSD8zLwUef+4HY0QcocbTnUhvOwo1kgWofTFMXZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:44:03.727493Z"},"content_sha256":"985314f08113b97e58f0768fdaf15a6d71a85a89f275945b619ecf095124085d","schema_version":"1.0","event_id":"sha256:985314f08113b97e58f0768fdaf15a6d71a85a89f275945b619ecf095124085d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SELBH277SOR5BL2JOKVW3JANH7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multiple-Exit Tuning: Towards Inference-Efficient Adaptation for Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gao Huang, Jinchao Zhu, Nannan Li, Zheng Liu","submitted_at":"2024-09-21T03:25:18Z","abstract_excerpt":"Parameter-efficient transfer learning (PETL) has shown great potential in adapting a vision transformer (ViT) pre-trained on large-scale datasets to various downstream tasks. Existing studies primarily focus on minimizing the number of learnable parameters. Although these methods are storage-efficient, they allocate excessive computational resources to easy samples, leading to inefficient inference. To address this issue, we introduce an inference-efficient tuning method termed multiple-exit tuning (MET). MET integrates multiple exits into the pre-trained ViT backbone. Since the predictions in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13999","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/2409.13999/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":"2026-07-05T09:10:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qg4iwyfJc1kq0g76zZFT9bc5av2Z6YFNoXMdYtmCWFUTZGaX3CluEMwOZjx7C8XoUSP9M52jyIe2HfVrOey3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:44:03.728365Z"},"content_sha256":"e5163686d3a0bab329150183592c3fb70549e547235fae8752f2f430c3302495","schema_version":"1.0","event_id":"sha256:e5163686d3a0bab329150183592c3fb70549e547235fae8752f2f430c3302495"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SELBH277SOR5BL2JOKVW3JANH7/bundle.json","state_url":"https://pith.science/pith/SELBH277SOR5BL2JOKVW3JANH7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SELBH277SOR5BL2JOKVW3JANH7/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":"2026-08-01T05:44:03Z","links":{"resolver":"https://pith.science/pith/SELBH277SOR5BL2JOKVW3JANH7","bundle":"https://pith.science/pith/SELBH277SOR5BL2JOKVW3JANH7/bundle.json","state":"https://pith.science/pith/SELBH277SOR5BL2JOKVW3JANH7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SELBH277SOR5BL2JOKVW3JANH7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SELBH277SOR5BL2JOKVW3JANH7","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":"a68d4a414860fac719aefc86690beab311d8789d7df50afd7f97fc196c56c30d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-21T03:25:18Z","title_canon_sha256":"2aee9cf43a0cb04b61db781d3929be853def94eb1a279a0a4b5eb824d9e7f8b2"},"schema_version":"1.0","source":{"id":"2409.13999","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13999","created_at":"2026-07-05T09:10:10Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13999v1","created_at":"2026-07-05T09:10:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13999","created_at":"2026-07-05T09:10:10Z"},{"alias_kind":"pith_short_12","alias_value":"SELBH277SOR5","created_at":"2026-07-05T09:10:10Z"},{"alias_kind":"pith_short_16","alias_value":"SELBH277SOR5BL2J","created_at":"2026-07-05T09:10:10Z"},{"alias_kind":"pith_short_8","alias_value":"SELBH277","created_at":"2026-07-05T09:10:10Z"}],"graph_snapshots":[{"event_id":"sha256:e5163686d3a0bab329150183592c3fb70549e547235fae8752f2f430c3302495","target":"graph","created_at":"2026-07-05T09:10:10Z","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/2409.13999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Parameter-efficient transfer learning (PETL) has shown great potential in adapting a vision transformer (ViT) pre-trained on large-scale datasets to various downstream tasks. Existing studies primarily focus on minimizing the number of learnable parameters. Although these methods are storage-efficient, they allocate excessive computational resources to easy samples, leading to inefficient inference. To address this issue, we introduce an inference-efficient tuning method termed multiple-exit tuning (MET). MET integrates multiple exits into the pre-trained ViT backbone. Since the predictions in","authors_text":"Gao Huang, Jinchao Zhu, Nannan Li, Zheng Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-21T03:25:18Z","title":"Multiple-Exit Tuning: Towards Inference-Efficient Adaptation for Vision Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13999","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":"sha256:985314f08113b97e58f0768fdaf15a6d71a85a89f275945b619ecf095124085d","target":"record","created_at":"2026-07-05T09:10:10Z","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":"a68d4a414860fac719aefc86690beab311d8789d7df50afd7f97fc196c56c30d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-21T03:25:18Z","title_canon_sha256":"2aee9cf43a0cb04b61db781d3929be853def94eb1a279a0a4b5eb824d9e7f8b2"},"schema_version":"1.0","source":{"id":"2409.13999","kind":"arxiv","version":1}},"canonical_sha256":"911613ebff93a3d0af4972ab6da40d3fe0772a41fbb6ba076ab09397d1554fc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"911613ebff93a3d0af4972ab6da40d3fe0772a41fbb6ba076ab09397d1554fc8","first_computed_at":"2026-07-05T09:10:10.219535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:10.219535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J4U2FfcGPXnOmVPPDrkfvaFj2PkXdgab7pbYrO1dqUlt7C/vp6lTp37wpyVGjOm+lHf7P05dpy6B771ywlsrAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:10.219995Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13999","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:985314f08113b97e58f0768fdaf15a6d71a85a89f275945b619ecf095124085d","sha256:e5163686d3a0bab329150183592c3fb70549e547235fae8752f2f430c3302495"],"state_sha256":"f562b0ffdaa2178f84b9697fab7eec09b1968377365fca92aaa97572491ce5f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u5T10TrHvwqRuN9V+Pxk4KqH5gEWmBH7jksg4r38KbYVlD1raHKOmnyI7TTwEpKqNVWmeHrhqY3h/lRxfyK1BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T05:44:03.735777Z","bundle_sha256":"a25fc969400312db082103d51dc81db412d2ab1958600dbccfec1d4f9aa6ed74"}}