{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FUSOKYNOIJIFBP4INZZOUTTPL3","short_pith_number":"pith:FUSOKYNO","canonical_record":{"source":{"id":"2407.04681","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-05T17:43:30Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"d728afab82fa9b56454ef60c8e9e50adfa41e8c785d618c1f07cef8425462909","abstract_canon_sha256":"ba103a78bb7cc81273eb35815ef12723d8e73c82f5f448d3838084bfb07b322f"},"schema_version":"1.0"},"canonical_sha256":"2d24e561ae425050bf886e72ea4e6f5ed163e23e81c3d6afb037640df5216c87","source":{"kind":"arxiv","id":"2407.04681","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04681","created_at":"2026-07-05T08:40:37Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04681v1","created_at":"2026-07-05T08:40:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04681","created_at":"2026-07-05T08:40:37Z"},{"alias_kind":"pith_short_12","alias_value":"FUSOKYNOIJIF","created_at":"2026-07-05T08:40:37Z"},{"alias_kind":"pith_short_16","alias_value":"FUSOKYNOIJIFBP4I","created_at":"2026-07-05T08:40:37Z"},{"alias_kind":"pith_short_8","alias_value":"FUSOKYNO","created_at":"2026-07-05T08:40:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FUSOKYNOIJIFBP4INZZOUTTPL3","target":"record","payload":{"canonical_record":{"source":{"id":"2407.04681","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-05T17:43:30Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"d728afab82fa9b56454ef60c8e9e50adfa41e8c785d618c1f07cef8425462909","abstract_canon_sha256":"ba103a78bb7cc81273eb35815ef12723d8e73c82f5f448d3838084bfb07b322f"},"schema_version":"1.0"},"canonical_sha256":"2d24e561ae425050bf886e72ea4e6f5ed163e23e81c3d6afb037640df5216c87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:37.262271Z","signature_b64":"9wXJMr3IxPEdhmaA0wFbFwQbuAteE3FEkY5ZIxjXRbX+eALJ4bVhT865Jl53tViWlcjACB84zK3R0V+S/lwVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d24e561ae425050bf886e72ea4e6f5ed163e23e81c3d6afb037640df5216c87","last_reissued_at":"2026-07-05T08:40:37.261831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:37.261831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.04681","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":"2026-07-05T08:40:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y4pb7MqNuUF9qb5ztqVQh9BXb9UH5qR6bmw7Do2NlvYEnTj1QlZt79NDMywrxuMDL+IsMYkNWL6g3uNO7CDMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:29:34.042803Z"},"content_sha256":"dddcecdfe9dbb156bbb93f076a12d36e6f0264d80d4585824fc0389be482f5d7","schema_version":"1.0","event_id":"sha256:dddcecdfe9dbb156bbb93f076a12d36e6f0264d80d4585824fc0389be482f5d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FUSOKYNOIJIFBP4INZZOUTTPL3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongdong Chen, Lu Yuan, Philip Torr, Ronald Clark, Weijian Xu, Yuanze Lin, Yunsheng Li","submitted_at":"2024-07-05T17:43:30Z","abstract_excerpt":"In recent years, multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets, enabling them to generally understand images well. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs, limiting their ability to answer questions requiring an understanding of detailed or localized visual elements. Drawing inspiration from the Retrieval-Augmented Generation (RAG) concept, this paper proposes a new visual prompt approach to integrate fine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04681","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/2407.04681/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":"2026-07-05T08:40:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3/ZYQUvYOL8bZBAMoSSRdkNyrYB+vLTkEkfPUT8YoeaJMGO3g4+PjqaUQVYIWqozqGzUbSpUof5Jgww7On5QAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:29:34.043320Z"},"content_sha256":"9f4795c1c2c4a7e8f3b1ea81b707ab3aa7fb9e2358f9cafa222f84ade179c8fc","schema_version":"1.0","event_id":"sha256:9f4795c1c2c4a7e8f3b1ea81b707ab3aa7fb9e2358f9cafa222f84ade179c8fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FUSOKYNOIJIFBP4INZZOUTTPL3/bundle.json","state_url":"https://pith.science/pith/FUSOKYNOIJIFBP4INZZOUTTPL3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FUSOKYNOIJIFBP4INZZOUTTPL3/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":"2026-08-13T21:29:34Z","links":{"resolver":"https://pith.science/pith/FUSOKYNOIJIFBP4INZZOUTTPL3","bundle":"https://pith.science/pith/FUSOKYNOIJIFBP4INZZOUTTPL3/bundle.json","state":"https://pith.science/pith/FUSOKYNOIJIFBP4INZZOUTTPL3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FUSOKYNOIJIFBP4INZZOUTTPL3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FUSOKYNOIJIFBP4INZZOUTTPL3","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":"ba103a78bb7cc81273eb35815ef12723d8e73c82f5f448d3838084bfb07b322f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-05T17:43:30Z","title_canon_sha256":"d728afab82fa9b56454ef60c8e9e50adfa41e8c785d618c1f07cef8425462909"},"schema_version":"1.0","source":{"id":"2407.04681","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04681","created_at":"2026-07-05T08:40:37Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04681v1","created_at":"2026-07-05T08:40:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04681","created_at":"2026-07-05T08:40:37Z"},{"alias_kind":"pith_short_12","alias_value":"FUSOKYNOIJIF","created_at":"2026-07-05T08:40:37Z"},{"alias_kind":"pith_short_16","alias_value":"FUSOKYNOIJIFBP4I","created_at":"2026-07-05T08:40:37Z"},{"alias_kind":"pith_short_8","alias_value":"FUSOKYNO","created_at":"2026-07-05T08:40:37Z"}],"graph_snapshots":[{"event_id":"sha256:9f4795c1c2c4a7e8f3b1ea81b707ab3aa7fb9e2358f9cafa222f84ade179c8fc","target":"graph","created_at":"2026-07-05T08:40:37Z","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/2407.04681/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets, enabling them to generally understand images well. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs, limiting their ability to answer questions requiring an understanding of detailed or localized visual elements. Drawing inspiration from the Retrieval-Augmented Generation (RAG) concept, this paper proposes a new visual prompt approach to integrate fine","authors_text":"Dongdong Chen, Lu Yuan, Philip Torr, Ronald Clark, Weijian Xu, Yuanze Lin, Yunsheng Li","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-05T17:43:30Z","title":"Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04681","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:dddcecdfe9dbb156bbb93f076a12d36e6f0264d80d4585824fc0389be482f5d7","target":"record","created_at":"2026-07-05T08:40:37Z","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":"ba103a78bb7cc81273eb35815ef12723d8e73c82f5f448d3838084bfb07b322f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-05T17:43:30Z","title_canon_sha256":"d728afab82fa9b56454ef60c8e9e50adfa41e8c785d618c1f07cef8425462909"},"schema_version":"1.0","source":{"id":"2407.04681","kind":"arxiv","version":1}},"canonical_sha256":"2d24e561ae425050bf886e72ea4e6f5ed163e23e81c3d6afb037640df5216c87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d24e561ae425050bf886e72ea4e6f5ed163e23e81c3d6afb037640df5216c87","first_computed_at":"2026-07-05T08:40:37.261831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:37.261831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9wXJMr3IxPEdhmaA0wFbFwQbuAteE3FEkY5ZIxjXRbX+eALJ4bVhT865Jl53tViWlcjACB84zK3R0V+S/lwVBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:37.262271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04681","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dddcecdfe9dbb156bbb93f076a12d36e6f0264d80d4585824fc0389be482f5d7","sha256:9f4795c1c2c4a7e8f3b1ea81b707ab3aa7fb9e2358f9cafa222f84ade179c8fc"],"state_sha256":"1cf7d87c62bbadda7bbed7fa4ab234b95fb27930351c0286ffe4ac8defdeabcf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QapzXscoraAwEB0qETNaE0NIbKcwSVsbmq6/TaNFc2pRmWLX9vTkbVF9TMoBo3DbLRSaHRu1JPVzkqvaBcX4BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T21:29:34.052259Z","bundle_sha256":"d3f73baf4859f55b81a24d2e4ca35e9cc9bfed32146963ad1a78377a4ed80352"}}