{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:52BZ4UP4P2DWG3OGV4DRQTETFS","short_pith_number":"pith:52BZ4UP4","canonical_record":{"source":{"id":"2406.03303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T14:13:38Z","cross_cats_sorted":[],"title_canon_sha256":"bc6846b5fd1965dd5687917bd0c74f26a26af1c2a9af2ba19d90e074649feb6c","abstract_canon_sha256":"7155370963acabafd065869d6baf236feef92a84bfd906f275e9f62caeae9ade"},"schema_version":"1.0"},"canonical_sha256":"ee839e51fc7e87636dc6af07184c932c9884bd3d1de92b10175347fe5ffde407","source":{"kind":"arxiv","id":"2406.03303","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03303","created_at":"2026-07-05T08:27:54Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03303v1","created_at":"2026-07-05T08:27:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03303","created_at":"2026-07-05T08:27:54Z"},{"alias_kind":"pith_short_12","alias_value":"52BZ4UP4P2DW","created_at":"2026-07-05T08:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"52BZ4UP4P2DWG3OG","created_at":"2026-07-05T08:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"52BZ4UP4","created_at":"2026-07-05T08:27:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:52BZ4UP4P2DWG3OGV4DRQTETFS","target":"record","payload":{"canonical_record":{"source":{"id":"2406.03303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T14:13:38Z","cross_cats_sorted":[],"title_canon_sha256":"bc6846b5fd1965dd5687917bd0c74f26a26af1c2a9af2ba19d90e074649feb6c","abstract_canon_sha256":"7155370963acabafd065869d6baf236feef92a84bfd906f275e9f62caeae9ade"},"schema_version":"1.0"},"canonical_sha256":"ee839e51fc7e87636dc6af07184c932c9884bd3d1de92b10175347fe5ffde407","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:54.678630Z","signature_b64":"grkbkZGd/fIq7ihZzIOE7PCqyOotgScN1+EQ66mN78GGIZ8qtwIh+27lrZD1He4ZRPayzTV2Tl5GRqwnP0F1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee839e51fc7e87636dc6af07184c932c9884bd3d1de92b10175347fe5ffde407","last_reissued_at":"2026-07-05T08:27:54.678160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:54.678160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.03303","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":"2026-07-05T08:27:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V3B+Y/7z7BZlL42WF4mSCKHhK+y3rtCrCLdSnWVXQOikjMdYcPMS0F2+V8MeO5+GKwortWdsXJE7plczLrXXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:35:14.106176Z"},"content_sha256":"3337c17797cf94580c90e698b8738143b5d02445c90abcc2a1d4340e0b4627f0","schema_version":"1.0","event_id":"sha256:3337c17797cf94580c90e698b8738143b5d02445c90abcc2a1d4340e0b4627f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:52BZ4UP4P2DWG3OGV4DRQTETFS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Visual Prompts for Guiding the Attention of Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashkan Khakzar, Daniel Rueckert, Jindong Gu, Masoud Jalili Sabet, Philip Torr, Razieh Rezaei","submitted_at":"2024-06-05T14:13:38Z","abstract_excerpt":"Visual prompting infuses visual information into the input image to adapt models toward specific predictions and tasks. Recently, manually crafted markers such as red circles are shown to guide the model to attend to a target region on the image. However, these markers only work on models trained with data containing those markers. Moreover, finding these prompts requires guesswork or prior knowledge of the domain on which the model is trained. This work circumvents manual design constraints by proposing to learn the visual prompts for guiding the attention of vision transformers. The learned "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03303","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/2406.03303/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":"2026-07-05T08:27:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YKiTP6Aa0WK247zlZ2ks5x6aqpTO5vMhwFOgnbsoERQtteMR6QfcGRZ/uCgKeGObROdSNlsgKgQKPP2J+0aeAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:35:14.106675Z"},"content_sha256":"62327b3d9db5d8656f1328e625b411a5d8bc640ab0c42446b75fc83e6ece79d5","schema_version":"1.0","event_id":"sha256:62327b3d9db5d8656f1328e625b411a5d8bc640ab0c42446b75fc83e6ece79d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/52BZ4UP4P2DWG3OGV4DRQTETFS/bundle.json","state_url":"https://pith.science/pith/52BZ4UP4P2DWG3OGV4DRQTETFS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/52BZ4UP4P2DWG3OGV4DRQTETFS/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":"2026-08-05T17:35:14Z","links":{"resolver":"https://pith.science/pith/52BZ4UP4P2DWG3OGV4DRQTETFS","bundle":"https://pith.science/pith/52BZ4UP4P2DWG3OGV4DRQTETFS/bundle.json","state":"https://pith.science/pith/52BZ4UP4P2DWG3OGV4DRQTETFS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/52BZ4UP4P2DWG3OGV4DRQTETFS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:52BZ4UP4P2DWG3OGV4DRQTETFS","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":"7155370963acabafd065869d6baf236feef92a84bfd906f275e9f62caeae9ade","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T14:13:38Z","title_canon_sha256":"bc6846b5fd1965dd5687917bd0c74f26a26af1c2a9af2ba19d90e074649feb6c"},"schema_version":"1.0","source":{"id":"2406.03303","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03303","created_at":"2026-07-05T08:27:54Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03303v1","created_at":"2026-07-05T08:27:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03303","created_at":"2026-07-05T08:27:54Z"},{"alias_kind":"pith_short_12","alias_value":"52BZ4UP4P2DW","created_at":"2026-07-05T08:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"52BZ4UP4P2DWG3OG","created_at":"2026-07-05T08:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"52BZ4UP4","created_at":"2026-07-05T08:27:54Z"}],"graph_snapshots":[{"event_id":"sha256:62327b3d9db5d8656f1328e625b411a5d8bc640ab0c42446b75fc83e6ece79d5","target":"graph","created_at":"2026-07-05T08:27:54Z","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/2406.03303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual prompting infuses visual information into the input image to adapt models toward specific predictions and tasks. Recently, manually crafted markers such as red circles are shown to guide the model to attend to a target region on the image. However, these markers only work on models trained with data containing those markers. Moreover, finding these prompts requires guesswork or prior knowledge of the domain on which the model is trained. This work circumvents manual design constraints by proposing to learn the visual prompts for guiding the attention of vision transformers. The learned ","authors_text":"Ashkan Khakzar, Daniel Rueckert, Jindong Gu, Masoud Jalili Sabet, Philip Torr, Razieh Rezaei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T14:13:38Z","title":"Learning Visual Prompts for Guiding the Attention of Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03303","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":"sha256:3337c17797cf94580c90e698b8738143b5d02445c90abcc2a1d4340e0b4627f0","target":"record","created_at":"2026-07-05T08:27:54Z","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":"7155370963acabafd065869d6baf236feef92a84bfd906f275e9f62caeae9ade","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T14:13:38Z","title_canon_sha256":"bc6846b5fd1965dd5687917bd0c74f26a26af1c2a9af2ba19d90e074649feb6c"},"schema_version":"1.0","source":{"id":"2406.03303","kind":"arxiv","version":1}},"canonical_sha256":"ee839e51fc7e87636dc6af07184c932c9884bd3d1de92b10175347fe5ffde407","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee839e51fc7e87636dc6af07184c932c9884bd3d1de92b10175347fe5ffde407","first_computed_at":"2026-07-05T08:27:54.678160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:54.678160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"grkbkZGd/fIq7ihZzIOE7PCqyOotgScN1+EQ66mN78GGIZ8qtwIh+27lrZD1He4ZRPayzTV2Tl5GRqwnP0F1CA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:54.678630Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03303","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3337c17797cf94580c90e698b8738143b5d02445c90abcc2a1d4340e0b4627f0","sha256:62327b3d9db5d8656f1328e625b411a5d8bc640ab0c42446b75fc83e6ece79d5"],"state_sha256":"9883279be85913c6bbb99c6bcfe391bc0e3666f6ee86eee389152fa21ed13199"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/vofkLjrIuWGOcKB9ABf6US7N2bpMD0ggrDMfL/yV8L1TdVOWiFmK8bD43YO8syKMWgeD6oqkhdFcmsxDjiqBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:35:14.110594Z","bundle_sha256":"87776838823e5e5ad1280db6679b8c5a4f517c425c6d0059d3e260cd8061dd52"}}