{"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"}