{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DPMIBQCWNXYOG55KJ2ERRUU4Z3","short_pith_number":"pith:DPMIBQCW","canonical_record":{"source":{"id":"2404.01151","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T14:53:36Z","cross_cats_sorted":[],"title_canon_sha256":"a729f21c123a806267e61288b62d7676e94ac83a2458c8a6c3fd5352cef328eb","abstract_canon_sha256":"2d3d5d9314eda2f30697d6ceef5a5a60471993134c1e091e2fee015a08180ec9"},"schema_version":"1.0"},"canonical_sha256":"1bd880c0566df0e377aa4e8918d29cced3678f3eb8283789af17ef3310a3265c","source":{"kind":"arxiv","id":"2404.01151","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01151","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01151v1","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01151","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"DPMIBQCWNXYO","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"DPMIBQCWNXYOG55K","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"DPMIBQCW","created_at":"2026-07-05T08:03:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DPMIBQCWNXYOG55KJ2ERRUU4Z3","target":"record","payload":{"canonical_record":{"source":{"id":"2404.01151","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T14:53:36Z","cross_cats_sorted":[],"title_canon_sha256":"a729f21c123a806267e61288b62d7676e94ac83a2458c8a6c3fd5352cef328eb","abstract_canon_sha256":"2d3d5d9314eda2f30697d6ceef5a5a60471993134c1e091e2fee015a08180ec9"},"schema_version":"1.0"},"canonical_sha256":"1bd880c0566df0e377aa4e8918d29cced3678f3eb8283789af17ef3310a3265c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:01.641457Z","signature_b64":"Edh3tap97qzLfkHdkWXypBE3HH/hClyLBGW+EZNP8pDoRWi2zhEXc3hL6+fJRmFl+wV3AkW81n4lYW64vQgICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bd880c0566df0e377aa4e8918d29cced3678f3eb8283789af17ef3310a3265c","last_reissued_at":"2026-07-05T08:03:01.640984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:01.640984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.01151","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":"2026-07-05T08:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Mghtg3DTfUuSBmkU/PrPE4+dnc0EdL6WUQaOfl7RQsh6jGcvT79aVymfkKDkQiDwr76fkCYPyMXpkDAYG08AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:43:38.328477Z"},"content_sha256":"faf7c194aa2317d1103bd0349f512c073b5f44847edd8e9098cb0a8b89a46dc1","schema_version":"1.0","event_id":"sha256:faf7c194aa2317d1103bd0349f512c073b5f44847edd8e9098cb0a8b89a46dc1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DPMIBQCWNXYOG55KJ2ERRUU4Z3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detect2Interact: Localizing Object Key Field in Visual Question Answering (VQA) with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Honglei Li, Jialou Wang, Longzhi Yang, Manli Zhu, Wai Lok Woo, Yulei Li","submitted_at":"2024-04-01T14:53:36Z","abstract_excerpt":"Localization plays a crucial role in enhancing the practicality and precision of VQA systems. By enabling fine-grained identification and interaction with specific parts of an object, it significantly improves the system's ability to provide contextually relevant and spatially accurate responses, crucial for applications in dynamic environments like robotics and augmented reality. However, traditional systems face challenges in accurately mapping objects within images to generate nuanced and spatially aware responses. In this work, we introduce \"Detect2Interact\", which addresses these challeng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01151","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/2404.01151/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":"2026-07-05T08:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IyW3LK1WFCeQj+SJ3R5srjH/tJx7xArcHOlXGMeCw8dYHMQDUPqrLG9Z6XAGlxgczSpfsM2DbkgSt+3acSFwBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:43:38.328858Z"},"content_sha256":"8a3d9e1f770425c546dae60a506c35ec1667903bf55ba981f2a90409dd974069","schema_version":"1.0","event_id":"sha256:8a3d9e1f770425c546dae60a506c35ec1667903bf55ba981f2a90409dd974069"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DPMIBQCWNXYOG55KJ2ERRUU4Z3/bundle.json","state_url":"https://pith.science/pith/DPMIBQCWNXYOG55KJ2ERRUU4Z3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DPMIBQCWNXYOG55KJ2ERRUU4Z3/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":"2026-07-07T03:43:38Z","links":{"resolver":"https://pith.science/pith/DPMIBQCWNXYOG55KJ2ERRUU4Z3","bundle":"https://pith.science/pith/DPMIBQCWNXYOG55KJ2ERRUU4Z3/bundle.json","state":"https://pith.science/pith/DPMIBQCWNXYOG55KJ2ERRUU4Z3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DPMIBQCWNXYOG55KJ2ERRUU4Z3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DPMIBQCWNXYOG55KJ2ERRUU4Z3","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":"2d3d5d9314eda2f30697d6ceef5a5a60471993134c1e091e2fee015a08180ec9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T14:53:36Z","title_canon_sha256":"a729f21c123a806267e61288b62d7676e94ac83a2458c8a6c3fd5352cef328eb"},"schema_version":"1.0","source":{"id":"2404.01151","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01151","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01151v1","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01151","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"DPMIBQCWNXYO","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"DPMIBQCWNXYOG55K","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"DPMIBQCW","created_at":"2026-07-05T08:03:01Z"}],"graph_snapshots":[{"event_id":"sha256:8a3d9e1f770425c546dae60a506c35ec1667903bf55ba981f2a90409dd974069","target":"graph","created_at":"2026-07-05T08:03:01Z","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/2404.01151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Localization plays a crucial role in enhancing the practicality and precision of VQA systems. By enabling fine-grained identification and interaction with specific parts of an object, it significantly improves the system's ability to provide contextually relevant and spatially accurate responses, crucial for applications in dynamic environments like robotics and augmented reality. However, traditional systems face challenges in accurately mapping objects within images to generate nuanced and spatially aware responses. In this work, we introduce \"Detect2Interact\", which addresses these challeng","authors_text":"Honglei Li, Jialou Wang, Longzhi Yang, Manli Zhu, Wai Lok Woo, Yulei Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T14:53:36Z","title":"Detect2Interact: Localizing Object Key Field in Visual Question Answering (VQA) with LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01151","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:faf7c194aa2317d1103bd0349f512c073b5f44847edd8e9098cb0a8b89a46dc1","target":"record","created_at":"2026-07-05T08:03:01Z","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":"2d3d5d9314eda2f30697d6ceef5a5a60471993134c1e091e2fee015a08180ec9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T14:53:36Z","title_canon_sha256":"a729f21c123a806267e61288b62d7676e94ac83a2458c8a6c3fd5352cef328eb"},"schema_version":"1.0","source":{"id":"2404.01151","kind":"arxiv","version":1}},"canonical_sha256":"1bd880c0566df0e377aa4e8918d29cced3678f3eb8283789af17ef3310a3265c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bd880c0566df0e377aa4e8918d29cced3678f3eb8283789af17ef3310a3265c","first_computed_at":"2026-07-05T08:03:01.640984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:01.640984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Edh3tap97qzLfkHdkWXypBE3HH/hClyLBGW+EZNP8pDoRWi2zhEXc3hL6+fJRmFl+wV3AkW81n4lYW64vQgICg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:01.641457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01151","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:faf7c194aa2317d1103bd0349f512c073b5f44847edd8e9098cb0a8b89a46dc1","sha256:8a3d9e1f770425c546dae60a506c35ec1667903bf55ba981f2a90409dd974069"],"state_sha256":"8471c415acf7656ac70243944d65a4b82b2da332f854f61dd505d5ac5ce36665"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zCRfi0ozYuSflcpOpfqEEDphCH1evuWCwLC8rxFzK4ftJ7feT8CTIyl1fjXbumKdbxkjUijvt1AC9TZ7HmbqAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:43:38.330761Z","bundle_sha256":"e6a4955b27da465e239319e0a095d8c16001ad6896ffc382701c1c9d3cb0936c"}}