{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:J54DOTMCVRJJWAOJZWMSAHKXNM","short_pith_number":"pith:J54DOTMC","canonical_record":{"source":{"id":"2401.06071","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T17:41:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7ef3fbc0a5f1825237eb124e1c4b8a3a67a0b86a14335067f6114d3fcc44b386","abstract_canon_sha256":"e705d7558feedae7559f129d9e4716c9b8f6519f8c55fcfb13e70ecfb3972526"},"schema_version":"1.0"},"canonical_sha256":"4f78374d82ac529b01c9cd99201d576b1bc37fe0a439aaf0c9e97d1596d7916b","source":{"kind":"arxiv","id":"2401.06071","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06071","created_at":"2026-07-05T07:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06071v5","created_at":"2026-07-05T07:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06071","created_at":"2026-07-05T07:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"J54DOTMCVRJJ","created_at":"2026-07-05T07:52:15Z"},{"alias_kind":"pith_short_16","alias_value":"J54DOTMCVRJJWAOJ","created_at":"2026-07-05T07:52:15Z"},{"alias_kind":"pith_short_8","alias_value":"J54DOTMC","created_at":"2026-07-05T07:52:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:J54DOTMCVRJJWAOJZWMSAHKXNM","target":"record","payload":{"canonical_record":{"source":{"id":"2401.06071","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T17:41:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7ef3fbc0a5f1825237eb124e1c4b8a3a67a0b86a14335067f6114d3fcc44b386","abstract_canon_sha256":"e705d7558feedae7559f129d9e4716c9b8f6519f8c55fcfb13e70ecfb3972526"},"schema_version":"1.0"},"canonical_sha256":"4f78374d82ac529b01c9cd99201d576b1bc37fe0a439aaf0c9e97d1596d7916b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:15.294717Z","signature_b64":"9UwxnB/IQu7tZFhgqGmoMCKsM6Zm5jdhSMS7hI4lpjeo50nuAp2NLR7TYOqmDDOysXzi0EikoUILyKAru4kXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f78374d82ac529b01c9cd99201d576b1bc37fe0a439aaf0c9e97d1596d7916b","last_reissued_at":"2026-07-05T07:52:15.294290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:15.294290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.06071","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gh/lJg9WOO13/tD5nBDltgwdd77nHwHv6/CjGMUQUGp5QhAy3GrawPMerQuDEbprPWtYK3eQXaKZfGWoqkbfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:15:36.656464Z"},"content_sha256":"6a12214f1f0d0e465585d9a6b62911bba35eead0ecff329a2a4c8c28adc8cbc4","schema_version":"1.0","event_id":"sha256:6a12214f1f0d0e465585d9a6b62911bba35eead0ecff329a2a4c8c28adc8cbc4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:J54DOTMCVRJJWAOJZWMSAHKXNM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dong Zhang, Hang Song, Junting Pan, Qi Qi, Qi Xu, Ran Zhou, Tao Wang, Van Tu Vu, Yiqing Cai, Zefeng Li, Zhaowei Li, Zhida Huang","submitted_at":"2024-01-11T17:41:57Z","abstract_excerpt":"Multi-modal large language models have demonstrated impressive performance across various tasks in different modalities. However, existing multi-modal models primarily emphasize capturing global information within each modality while neglecting the importance of perceiving local information across modalities. Consequently, these models lack the ability to effectively understand the fine-grained details of input data, limiting their performance in tasks that require a more nuanced understanding. To address this limitation, there is a compelling need to develop models that enable fine-grained un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06071","kind":"arxiv","version":5},"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/2401.06071/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":"2026-07-05T07:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fsFZTHAKYWgFamAnWnN66rVv8fFSJnjax+5zIsM+EBmiY0YN9Z6IN3dnAHgtQl/4GbbpsdFZfoQoAA6bWOFUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:15:36.656974Z"},"content_sha256":"dc7e51613d41ae17620fd443ee12a0a85199e14d6a63911fc157afe654eba18b","schema_version":"1.0","event_id":"sha256:dc7e51613d41ae17620fd443ee12a0a85199e14d6a63911fc157afe654eba18b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J54DOTMCVRJJWAOJZWMSAHKXNM/bundle.json","state_url":"https://pith.science/pith/J54DOTMCVRJJWAOJZWMSAHKXNM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J54DOTMCVRJJWAOJZWMSAHKXNM/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":"2026-08-09T00:15:36Z","links":{"resolver":"https://pith.science/pith/J54DOTMCVRJJWAOJZWMSAHKXNM","bundle":"https://pith.science/pith/J54DOTMCVRJJWAOJZWMSAHKXNM/bundle.json","state":"https://pith.science/pith/J54DOTMCVRJJWAOJZWMSAHKXNM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J54DOTMCVRJJWAOJZWMSAHKXNM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:J54DOTMCVRJJWAOJZWMSAHKXNM","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":"e705d7558feedae7559f129d9e4716c9b8f6519f8c55fcfb13e70ecfb3972526","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T17:41:57Z","title_canon_sha256":"7ef3fbc0a5f1825237eb124e1c4b8a3a67a0b86a14335067f6114d3fcc44b386"},"schema_version":"1.0","source":{"id":"2401.06071","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06071","created_at":"2026-07-05T07:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06071v5","created_at":"2026-07-05T07:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06071","created_at":"2026-07-05T07:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"J54DOTMCVRJJ","created_at":"2026-07-05T07:52:15Z"},{"alias_kind":"pith_short_16","alias_value":"J54DOTMCVRJJWAOJ","created_at":"2026-07-05T07:52:15Z"},{"alias_kind":"pith_short_8","alias_value":"J54DOTMC","created_at":"2026-07-05T07:52:15Z"}],"graph_snapshots":[{"event_id":"sha256:dc7e51613d41ae17620fd443ee12a0a85199e14d6a63911fc157afe654eba18b","target":"graph","created_at":"2026-07-05T07:52:15Z","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/2401.06071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal large language models have demonstrated impressive performance across various tasks in different modalities. However, existing multi-modal models primarily emphasize capturing global information within each modality while neglecting the importance of perceiving local information across modalities. Consequently, these models lack the ability to effectively understand the fine-grained details of input data, limiting their performance in tasks that require a more nuanced understanding. To address this limitation, there is a compelling need to develop models that enable fine-grained un","authors_text":"Dong Zhang, Hang Song, Junting Pan, Qi Qi, Qi Xu, Ran Zhou, Tao Wang, Van Tu Vu, Yiqing Cai, Zefeng Li, Zhaowei Li, Zhida Huang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T17:41:57Z","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06071","kind":"arxiv","version":5},"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":"sha256:6a12214f1f0d0e465585d9a6b62911bba35eead0ecff329a2a4c8c28adc8cbc4","target":"record","created_at":"2026-07-05T07:52:15Z","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":"e705d7558feedae7559f129d9e4716c9b8f6519f8c55fcfb13e70ecfb3972526","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T17:41:57Z","title_canon_sha256":"7ef3fbc0a5f1825237eb124e1c4b8a3a67a0b86a14335067f6114d3fcc44b386"},"schema_version":"1.0","source":{"id":"2401.06071","kind":"arxiv","version":5}},"canonical_sha256":"4f78374d82ac529b01c9cd99201d576b1bc37fe0a439aaf0c9e97d1596d7916b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f78374d82ac529b01c9cd99201d576b1bc37fe0a439aaf0c9e97d1596d7916b","first_computed_at":"2026-07-05T07:52:15.294290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:15.294290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9UwxnB/IQu7tZFhgqGmoMCKsM6Zm5jdhSMS7hI4lpjeo50nuAp2NLR7TYOqmDDOysXzi0EikoUILyKAru4kXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:15.294717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06071","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a12214f1f0d0e465585d9a6b62911bba35eead0ecff329a2a4c8c28adc8cbc4","sha256:dc7e51613d41ae17620fd443ee12a0a85199e14d6a63911fc157afe654eba18b"],"state_sha256":"ad34ba4f705e994307b0399ca097195d43234acafe92ae6e624f7e3617034cc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KFpemhoHgskLzT44YXGUue2prVRI5LQiDGyQwdQIbc2w2oVSyphriV7Ic/tg2crxYB6Phj33poYaMnUq/W5EBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:15:36.661160Z","bundle_sha256":"0752a8abb3c30d2e1f02f68829544cd655371be989225894a7fc2f744b74b748"}}