{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CXBCW3QW4SQ6WGOR3CHHETBTC5","short_pith_number":"pith:CXBCW3QW","canonical_record":{"source":{"id":"2405.17104","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T12:23:08Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"eab52b543285e60b73b84ea112e622def953f60250f21cf6459414abe192140d","abstract_canon_sha256":"bfb0f70073995e9833a2d53b07747a15935cbb98f74a6b80990dde1670c24e47"},"schema_version":"1.0"},"canonical_sha256":"15c22b6e16e4a1eb19d1d88e724c33175a6de1c987abe20c8c411d6dc1037f4d","source":{"kind":"arxiv","id":"2405.17104","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17104","created_at":"2026-07-05T08:24:07Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17104v2","created_at":"2026-07-05T08:24:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17104","created_at":"2026-07-05T08:24:07Z"},{"alias_kind":"pith_short_12","alias_value":"CXBCW3QW4SQ6","created_at":"2026-07-05T08:24:07Z"},{"alias_kind":"pith_short_16","alias_value":"CXBCW3QW4SQ6WGOR","created_at":"2026-07-05T08:24:07Z"},{"alias_kind":"pith_short_8","alias_value":"CXBCW3QW","created_at":"2026-07-05T08:24:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CXBCW3QW4SQ6WGOR3CHHETBTC5","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17104","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T12:23:08Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"eab52b543285e60b73b84ea112e622def953f60250f21cf6459414abe192140d","abstract_canon_sha256":"bfb0f70073995e9833a2d53b07747a15935cbb98f74a6b80990dde1670c24e47"},"schema_version":"1.0"},"canonical_sha256":"15c22b6e16e4a1eb19d1d88e724c33175a6de1c987abe20c8c411d6dc1037f4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:07.372412Z","signature_b64":"B1bJ4GMbp3KMbwIN7WcDIi8Bc8yzYzlhAb4VTswLje8g1kD4swm7ih3d9j0QztomE6/+UrAdk8ge0TjmGAK0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15c22b6e16e4a1eb19d1d88e724c33175a6de1c987abe20c8c411d6dc1037f4d","last_reissued_at":"2026-07-05T08:24:07.371866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:07.371866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17104","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:24:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nBUrTDiNVEPVXV9OkQAmTAYfUgg9n0cYbAPlBahbqDq4HP6cuSEee2VBhms92GcJh0p61Yh3+4054qnVha/DDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T06:46:19.046711Z"},"content_sha256":"f5085e1f45b2195b7e45e5393ecf5d1529f11b024fb834ea44b1073c2aecd84e","schema_version":"1.0","event_id":"sha256:f5085e1f45b2195b7e45e5393ecf5d1529f11b024fb834ea44b1073c2aecd84e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CXBCW3QW4SQ6WGOR3CHHETBTC5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-Optic: Unveiling the Capabilities of Large Language Models for Universal Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Haoyu Zhao, Wenhang Ge, Ying-Cong Chen","submitted_at":"2024-05-27T12:23:08Z","abstract_excerpt":"Visual grounding is an essential tool that links user-provided text queries with query-specific regions within an image. Despite advancements in visual grounding models, their ability to comprehend complex queries remains limited. To overcome this limitation, we introduce LLM-Optic, an innovative method that utilizes Large Language Models (LLMs) as an optical lens to enhance existing visual grounding models in comprehending complex text queries involving intricate text structures, multiple objects, or object spatial relationships, situations that current models struggle with. LLM-Optic first e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17104","kind":"arxiv","version":2},"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/2405.17104/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":"2026-07-05T08:24:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+L+k15i4Wg5usIQmF6riNQpnQzK08o4MDNbpdQA0k/JFIhiXADB8BEbZwvlngGhDA8NoT1EB35iREUrq2bFcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T06:46:19.047394Z"},"content_sha256":"3df71f1d4d4b09c2d5f68005d25fe9b5fc1baa727c088b0e8b7e420e1d5230e6","schema_version":"1.0","event_id":"sha256:3df71f1d4d4b09c2d5f68005d25fe9b5fc1baa727c088b0e8b7e420e1d5230e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CXBCW3QW4SQ6WGOR3CHHETBTC5/bundle.json","state_url":"https://pith.science/pith/CXBCW3QW4SQ6WGOR3CHHETBTC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CXBCW3QW4SQ6WGOR3CHHETBTC5/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":"2026-08-19T06:46:19Z","links":{"resolver":"https://pith.science/pith/CXBCW3QW4SQ6WGOR3CHHETBTC5","bundle":"https://pith.science/pith/CXBCW3QW4SQ6WGOR3CHHETBTC5/bundle.json","state":"https://pith.science/pith/CXBCW3QW4SQ6WGOR3CHHETBTC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CXBCW3QW4SQ6WGOR3CHHETBTC5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CXBCW3QW4SQ6WGOR3CHHETBTC5","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":"bfb0f70073995e9833a2d53b07747a15935cbb98f74a6b80990dde1670c24e47","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T12:23:08Z","title_canon_sha256":"eab52b543285e60b73b84ea112e622def953f60250f21cf6459414abe192140d"},"schema_version":"1.0","source":{"id":"2405.17104","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17104","created_at":"2026-07-05T08:24:07Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17104v2","created_at":"2026-07-05T08:24:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17104","created_at":"2026-07-05T08:24:07Z"},{"alias_kind":"pith_short_12","alias_value":"CXBCW3QW4SQ6","created_at":"2026-07-05T08:24:07Z"},{"alias_kind":"pith_short_16","alias_value":"CXBCW3QW4SQ6WGOR","created_at":"2026-07-05T08:24:07Z"},{"alias_kind":"pith_short_8","alias_value":"CXBCW3QW","created_at":"2026-07-05T08:24:07Z"}],"graph_snapshots":[{"event_id":"sha256:3df71f1d4d4b09c2d5f68005d25fe9b5fc1baa727c088b0e8b7e420e1d5230e6","target":"graph","created_at":"2026-07-05T08:24:07Z","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/2405.17104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding is an essential tool that links user-provided text queries with query-specific regions within an image. Despite advancements in visual grounding models, their ability to comprehend complex queries remains limited. To overcome this limitation, we introduce LLM-Optic, an innovative method that utilizes Large Language Models (LLMs) as an optical lens to enhance existing visual grounding models in comprehending complex text queries involving intricate text structures, multiple objects, or object spatial relationships, situations that current models struggle with. LLM-Optic first e","authors_text":"Haoyu Zhao, Wenhang Ge, Ying-Cong Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T12:23:08Z","title":"LLM-Optic: Unveiling the Capabilities of Large Language Models for Universal Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17104","kind":"arxiv","version":2},"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:f5085e1f45b2195b7e45e5393ecf5d1529f11b024fb834ea44b1073c2aecd84e","target":"record","created_at":"2026-07-05T08:24:07Z","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":"bfb0f70073995e9833a2d53b07747a15935cbb98f74a6b80990dde1670c24e47","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T12:23:08Z","title_canon_sha256":"eab52b543285e60b73b84ea112e622def953f60250f21cf6459414abe192140d"},"schema_version":"1.0","source":{"id":"2405.17104","kind":"arxiv","version":2}},"canonical_sha256":"15c22b6e16e4a1eb19d1d88e724c33175a6de1c987abe20c8c411d6dc1037f4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15c22b6e16e4a1eb19d1d88e724c33175a6de1c987abe20c8c411d6dc1037f4d","first_computed_at":"2026-07-05T08:24:07.371866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:07.371866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B1bJ4GMbp3KMbwIN7WcDIi8Bc8yzYzlhAb4VTswLje8g1kD4swm7ih3d9j0QztomE6/+UrAdk8ge0TjmGAK0Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:07.372412Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17104","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5085e1f45b2195b7e45e5393ecf5d1529f11b024fb834ea44b1073c2aecd84e","sha256:3df71f1d4d4b09c2d5f68005d25fe9b5fc1baa727c088b0e8b7e420e1d5230e6"],"state_sha256":"2ffdfc26445bbd813e79183433e59189a82a83125d63418abe9a2e74048cc1c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tJPMp8sh/pdn4vU3a+Zl/V76HL4iT/rXjiuHXm3EnRgj7Es7J6OuQ/2JgwYBraG3qdYChx/smFSlXR21mFwfDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T06:46:19.052428Z","bundle_sha256":"0583ea5d29af34cab1c1a1ea577b6f83324de0974bcfeb970e43d8e5456ed887"}}