{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BSRXRMZ24FCA4TTY67H7L3GCVJ","short_pith_number":"pith:BSRXRMZ2","canonical_record":{"source":{"id":"2405.05615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T08:23:20Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b55ebb46b9ff48daf74267121e5f5d9e24aa2191085ac3e5c17d059753eb6eab","abstract_canon_sha256":"cc66832efd3798b3851e6f3d146ca069cd80482670e2ca8064957ef4eb85690f"},"schema_version":"1.0"},"canonical_sha256":"0ca378b33ae1440e4e78f7cff5ecc2aa42728b88a5a945286e58cd75e5796434","source":{"kind":"arxiv","id":"2405.05615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.05615","created_at":"2026-07-05T08:17:20Z"},{"alias_kind":"arxiv_version","alias_value":"2405.05615v1","created_at":"2026-07-05T08:17:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05615","created_at":"2026-07-05T08:17:20Z"},{"alias_kind":"pith_short_12","alias_value":"BSRXRMZ24FCA","created_at":"2026-07-05T08:17:20Z"},{"alias_kind":"pith_short_16","alias_value":"BSRXRMZ24FCA4TTY","created_at":"2026-07-05T08:17:20Z"},{"alias_kind":"pith_short_8","alias_value":"BSRXRMZ2","created_at":"2026-07-05T08:17:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BSRXRMZ24FCA4TTY67H7L3GCVJ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.05615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T08:23:20Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b55ebb46b9ff48daf74267121e5f5d9e24aa2191085ac3e5c17d059753eb6eab","abstract_canon_sha256":"cc66832efd3798b3851e6f3d146ca069cd80482670e2ca8064957ef4eb85690f"},"schema_version":"1.0"},"canonical_sha256":"0ca378b33ae1440e4e78f7cff5ecc2aa42728b88a5a945286e58cd75e5796434","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:20.585502Z","signature_b64":"ptqv5uKXBUKPZEHFi2QTm3l1j1FqnIPFO9VgFKZeimjrhiQjaw6BBWzhh/0EgBNhPVdb//ASOjL6JYXNJLFKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ca378b33ae1440e4e78f7cff5ecc2aa42728b88a5a945286e58cd75e5796434","last_reissued_at":"2026-07-05T08:17:20.585075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:20.585075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.05615","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":"2026-07-05T08:17:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TK2FQakcFUCIVB6mxlYd80HRUqPoaVvi7covHyOgN3nJwbEiCsLllQ+ARKABl/9aX5srSqwpZTaoUSlDYBtoDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:06:58.953024Z"},"content_sha256":"f2060f351c305fe9cfee414a5c1dbff943a25d047ddf54b70ec6664ce7796f84","schema_version":"1.0","event_id":"sha256:f2060f351c305fe9cfee414a5c1dbff943a25d047ddf54b70ec6664ce7796f84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BSRXRMZ24FCA4TTY67H7L3GCVJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Kai Han, Ning Ding, Shibo Jie, Yehui Tang, Yunhe Wang, Zhi-Hong Deng","submitted_at":"2024-05-09T08:23:20Z","abstract_excerpt":"Current solutions for efficiently constructing large vision-language (VL) models follow a two-step paradigm: projecting the output of pre-trained vision encoders to the input space of pre-trained language models as visual prompts; and then transferring the models to downstream VL tasks via end-to-end parameter-efficient fine-tuning (PEFT). However, this paradigm still exhibits inefficiency since it significantly increases the input length of the language models. In this paper, in contrast to integrating visual prompts into inputs, we regard visual prompts as additional knowledge that facilitat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05615","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/2405.05615/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":"2026-07-05T08:17:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3hqI9NTa23faYc3Qwl6ESvWfeE+78ZytT/8ZM0s3Qeb7jw0qg8uRDuT5S7uGUtmHf0B4A2RYBAgDUb6lvj08Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:06:58.954011Z"},"content_sha256":"9a3edb60d0a3fa67066ddea80de8080283486cd837db6d2387b6292659e3b4f7","schema_version":"1.0","event_id":"sha256:9a3edb60d0a3fa67066ddea80de8080283486cd837db6d2387b6292659e3b4f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BSRXRMZ24FCA4TTY67H7L3GCVJ/bundle.json","state_url":"https://pith.science/pith/BSRXRMZ24FCA4TTY67H7L3GCVJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BSRXRMZ24FCA4TTY67H7L3GCVJ/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":"2026-08-06T19:06:58Z","links":{"resolver":"https://pith.science/pith/BSRXRMZ24FCA4TTY67H7L3GCVJ","bundle":"https://pith.science/pith/BSRXRMZ24FCA4TTY67H7L3GCVJ/bundle.json","state":"https://pith.science/pith/BSRXRMZ24FCA4TTY67H7L3GCVJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BSRXRMZ24FCA4TTY67H7L3GCVJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BSRXRMZ24FCA4TTY67H7L3GCVJ","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":"cc66832efd3798b3851e6f3d146ca069cd80482670e2ca8064957ef4eb85690f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T08:23:20Z","title_canon_sha256":"b55ebb46b9ff48daf74267121e5f5d9e24aa2191085ac3e5c17d059753eb6eab"},"schema_version":"1.0","source":{"id":"2405.05615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.05615","created_at":"2026-07-05T08:17:20Z"},{"alias_kind":"arxiv_version","alias_value":"2405.05615v1","created_at":"2026-07-05T08:17:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05615","created_at":"2026-07-05T08:17:20Z"},{"alias_kind":"pith_short_12","alias_value":"BSRXRMZ24FCA","created_at":"2026-07-05T08:17:20Z"},{"alias_kind":"pith_short_16","alias_value":"BSRXRMZ24FCA4TTY","created_at":"2026-07-05T08:17:20Z"},{"alias_kind":"pith_short_8","alias_value":"BSRXRMZ2","created_at":"2026-07-05T08:17:20Z"}],"graph_snapshots":[{"event_id":"sha256:9a3edb60d0a3fa67066ddea80de8080283486cd837db6d2387b6292659e3b4f7","target":"graph","created_at":"2026-07-05T08:17:20Z","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/2405.05615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current solutions for efficiently constructing large vision-language (VL) models follow a two-step paradigm: projecting the output of pre-trained vision encoders to the input space of pre-trained language models as visual prompts; and then transferring the models to downstream VL tasks via end-to-end parameter-efficient fine-tuning (PEFT). However, this paradigm still exhibits inefficiency since it significantly increases the input length of the language models. In this paper, in contrast to integrating visual prompts into inputs, we regard visual prompts as additional knowledge that facilitat","authors_text":"Kai Han, Ning Ding, Shibo Jie, Yehui Tang, Yunhe Wang, Zhi-Hong Deng","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T08:23:20Z","title":"Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05615","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:f2060f351c305fe9cfee414a5c1dbff943a25d047ddf54b70ec6664ce7796f84","target":"record","created_at":"2026-07-05T08:17:20Z","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":"cc66832efd3798b3851e6f3d146ca069cd80482670e2ca8064957ef4eb85690f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-09T08:23:20Z","title_canon_sha256":"b55ebb46b9ff48daf74267121e5f5d9e24aa2191085ac3e5c17d059753eb6eab"},"schema_version":"1.0","source":{"id":"2405.05615","kind":"arxiv","version":1}},"canonical_sha256":"0ca378b33ae1440e4e78f7cff5ecc2aa42728b88a5a945286e58cd75e5796434","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ca378b33ae1440e4e78f7cff5ecc2aa42728b88a5a945286e58cd75e5796434","first_computed_at":"2026-07-05T08:17:20.585075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:17:20.585075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ptqv5uKXBUKPZEHFi2QTm3l1j1FqnIPFO9VgFKZeimjrhiQjaw6BBWzhh/0EgBNhPVdb//ASOjL6JYXNJLFKAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:17:20.585502Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.05615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2060f351c305fe9cfee414a5c1dbff943a25d047ddf54b70ec6664ce7796f84","sha256:9a3edb60d0a3fa67066ddea80de8080283486cd837db6d2387b6292659e3b4f7"],"state_sha256":"8688ad1841bf0b83ce47b16dec7082cf9b3ce3c3b02c596895c55818c0801c31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ANwlhNuQYiSFK9m5cwSH0/IHU0gYcU99+NDQzovQIq4h/pA7oAZKForM8mBJeyXHQ57VF56hGSI3BhIWND7wCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:06:58.960473Z","bundle_sha256":"abbaab53c8b0c3f20bd59060e3a8c2172ec31c88d417eacf7f4193c3789892d4"}}