{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OKODLXQ55GAEVACP5O54IHQHQJ","short_pith_number":"pith:OKODLXQ5","canonical_record":{"source":{"id":"2404.04514","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-06T05:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"b4fd2f429b731c82552c9683a597cc93377d901f8cbf9194ff9baf3299fbfcb9","abstract_canon_sha256":"0ceb6b3d5123f9ef510e03097011f937b310513fbd06cd239bdee71007d93ccc"},"schema_version":"1.0"},"canonical_sha256":"729c35de1de9804a804febbbc41e07827bd8e6c77923c4684397708f95d5915f","source":{"kind":"arxiv","id":"2404.04514","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04514","created_at":"2026-07-05T08:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04514v1","created_at":"2026-07-05T08:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04514","created_at":"2026-07-05T08:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"OKODLXQ55GAE","created_at":"2026-07-05T08:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"OKODLXQ55GAEVACP","created_at":"2026-07-05T08:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"OKODLXQ5","created_at":"2026-07-05T08:05:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OKODLXQ55GAEVACP5O54IHQHQJ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.04514","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-06T05:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"b4fd2f429b731c82552c9683a597cc93377d901f8cbf9194ff9baf3299fbfcb9","abstract_canon_sha256":"0ceb6b3d5123f9ef510e03097011f937b310513fbd06cd239bdee71007d93ccc"},"schema_version":"1.0"},"canonical_sha256":"729c35de1de9804a804febbbc41e07827bd8e6c77923c4684397708f95d5915f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:17.823395Z","signature_b64":"P6/zteE6GclZAZyMzKY6t81+40+8ft6zUeCyFR3DH1ccnhdR9v11umjC3H7Sd+9xLYMqyOTaCyKHR+9Vb7JFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"729c35de1de9804a804febbbc41e07827bd8e6c77923c4684397708f95d5915f","last_reissued_at":"2026-07-05T08:05:17.822979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:17.822979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.04514","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":"2026-07-05T08:05:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o9Po/a+OVDUELojKQ83CSFcRlcNFwdfQyEDbbTXTfXi4JjyrI5K+GSB5PPATSQ4Q++Vex5J83MW9BoFoVDRXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:45:30.681875Z"},"content_sha256":"5e8b436ccbe974009f7baa2fdae04d76181bc82718d683681a1704d819484960","schema_version":"1.0","event_id":"sha256:5e8b436ccbe974009f7baa2fdae04d76181bc82718d683681a1704d819484960"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OKODLXQ55GAEVACP5O54IHQHQJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenyi Zhou, Jian Wu, Songtao Jiang, Yang Feng, Yan Zhang, Yeying Jin, Zuozhu Liu","submitted_at":"2024-04-06T05:59:02Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) such as GPT-4V and Gemini Pro face challenges in achieving human-level perception in Visual Question Answering (VQA), particularly in object-oriented perception tasks which demand fine-grained understanding of object identities, locations or attributes, as indicated by empirical findings. This is mainly due to their limited capability to effectively integrate complex visual cues with textual information and potential object hallucinations. In this paper, we present a novel approach, Joint Visual and Text Prompting (VTPrompt), that employs fine-grained v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04514","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/2404.04514/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":"2026-07-05T08:05:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lu0bfh7CW7+Ku6fBOlEcn4HPWSxivS44ND3ZwkKUva+gRusfrzhSrb5aZy6MvJSoB8yUY6qrDHrUPU0zbAQnAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:45:30.682506Z"},"content_sha256":"1cc9bb25123fce851e78946110d3cc681a860d73b52a34e86d1a341e927b0ff5","schema_version":"1.0","event_id":"sha256:1cc9bb25123fce851e78946110d3cc681a860d73b52a34e86d1a341e927b0ff5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OKODLXQ55GAEVACP5O54IHQHQJ/bundle.json","state_url":"https://pith.science/pith/OKODLXQ55GAEVACP5O54IHQHQJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OKODLXQ55GAEVACP5O54IHQHQJ/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":"2026-08-18T20:45:30Z","links":{"resolver":"https://pith.science/pith/OKODLXQ55GAEVACP5O54IHQHQJ","bundle":"https://pith.science/pith/OKODLXQ55GAEVACP5O54IHQHQJ/bundle.json","state":"https://pith.science/pith/OKODLXQ55GAEVACP5O54IHQHQJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OKODLXQ55GAEVACP5O54IHQHQJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OKODLXQ55GAEVACP5O54IHQHQJ","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":"0ceb6b3d5123f9ef510e03097011f937b310513fbd06cd239bdee71007d93ccc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-06T05:59:02Z","title_canon_sha256":"b4fd2f429b731c82552c9683a597cc93377d901f8cbf9194ff9baf3299fbfcb9"},"schema_version":"1.0","source":{"id":"2404.04514","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04514","created_at":"2026-07-05T08:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04514v1","created_at":"2026-07-05T08:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04514","created_at":"2026-07-05T08:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"OKODLXQ55GAE","created_at":"2026-07-05T08:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"OKODLXQ55GAEVACP","created_at":"2026-07-05T08:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"OKODLXQ5","created_at":"2026-07-05T08:05:17Z"}],"graph_snapshots":[{"event_id":"sha256:1cc9bb25123fce851e78946110d3cc681a860d73b52a34e86d1a341e927b0ff5","target":"graph","created_at":"2026-07-05T08:05:17Z","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/2404.04514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) such as GPT-4V and Gemini Pro face challenges in achieving human-level perception in Visual Question Answering (VQA), particularly in object-oriented perception tasks which demand fine-grained understanding of object identities, locations or attributes, as indicated by empirical findings. This is mainly due to their limited capability to effectively integrate complex visual cues with textual information and potential object hallucinations. In this paper, we present a novel approach, Joint Visual and Text Prompting (VTPrompt), that employs fine-grained v","authors_text":"Chenyi Zhou, Jian Wu, Songtao Jiang, Yang Feng, Yan Zhang, Yeying Jin, Zuozhu Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-06T05:59:02Z","title":"Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04514","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":"sha256:5e8b436ccbe974009f7baa2fdae04d76181bc82718d683681a1704d819484960","target":"record","created_at":"2026-07-05T08:05:17Z","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":"0ceb6b3d5123f9ef510e03097011f937b310513fbd06cd239bdee71007d93ccc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-06T05:59:02Z","title_canon_sha256":"b4fd2f429b731c82552c9683a597cc93377d901f8cbf9194ff9baf3299fbfcb9"},"schema_version":"1.0","source":{"id":"2404.04514","kind":"arxiv","version":1}},"canonical_sha256":"729c35de1de9804a804febbbc41e07827bd8e6c77923c4684397708f95d5915f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"729c35de1de9804a804febbbc41e07827bd8e6c77923c4684397708f95d5915f","first_computed_at":"2026-07-05T08:05:17.822979Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:17.822979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P6/zteE6GclZAZyMzKY6t81+40+8ft6zUeCyFR3DH1ccnhdR9v11umjC3H7Sd+9xLYMqyOTaCyKHR+9Vb7JFCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:17.823395Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.04514","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e8b436ccbe974009f7baa2fdae04d76181bc82718d683681a1704d819484960","sha256:1cc9bb25123fce851e78946110d3cc681a860d73b52a34e86d1a341e927b0ff5"],"state_sha256":"e16b3b2814f3dc157dea00f8db01194663720901d8b6a6bdca3153629c60fbc7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lpjFO9qg7YAQnbDWR0MVkHhwHJxYoqCOFaHnEHe8oxYUP0RvVFfYjnkfkYIU1ThBLw3nYmhztwDq9Z/WrfyzAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:45:30.687342Z","bundle_sha256":"fc1c588251875714da8060a3061ca59a4d1a7580e036bea8cb9d3c0cb457e70b"}}