{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ETEZNWJISIQYIVV52EKG7QNBBQ","short_pith_number":"pith:ETEZNWJI","canonical_record":{"source":{"id":"2403.19322","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-28T11:26:30Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5ca098a95d3e006b836bb1ad061a7bb2d7c914563058fe4ebd4ba9dcdb305eec","abstract_canon_sha256":"23e815ddaba41692632bc434b790e269f9f4a5cbdfff4c6401f58cc6211815ca"},"schema_version":"1.0"},"canonical_sha256":"24c996d92892218456bdd1146fc1a10c2c1a1b18f153943491fca37d39c1ffda","source":{"kind":"arxiv","id":"2403.19322","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19322","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19322v2","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19322","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"pith_short_12","alias_value":"ETEZNWJISIQY","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"pith_short_16","alias_value":"ETEZNWJISIQYIVV5","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"pith_short_8","alias_value":"ETEZNWJI","created_at":"2026-07-05T08:33:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ETEZNWJISIQYIVV52EKG7QNBBQ","target":"record","payload":{"canonical_record":{"source":{"id":"2403.19322","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-28T11:26:30Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5ca098a95d3e006b836bb1ad061a7bb2d7c914563058fe4ebd4ba9dcdb305eec","abstract_canon_sha256":"23e815ddaba41692632bc434b790e269f9f4a5cbdfff4c6401f58cc6211815ca"},"schema_version":"1.0"},"canonical_sha256":"24c996d92892218456bdd1146fc1a10c2c1a1b18f153943491fca37d39c1ffda","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:38.241820Z","signature_b64":"3r3ZXiMaYCxnFWRjIEPmfxOpOHmh431pCWcY9O7SNZJrfwdMV23auJYsyM9d7NEW6XjoM8wrAToHmcw1ya7RAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24c996d92892218456bdd1146fc1a10c2c1a1b18f153943491fca37d39c1ffda","last_reissued_at":"2026-07-05T08:33:38.241336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:38.241336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.19322","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":"2026-07-05T08:33:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ILtMD7B1gXuVmmTi7Q8WFsUnWkQwSHsWJp17Up6aqoSF83fiGroUQK1In1tKZ88O609nbql+guW8LMqgJh4gAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:02:09.452180Z"},"content_sha256":"f9259b1a80536e59a9bdf0fef67eb31e5fae4244990e8e3629431900026f177e","schema_version":"1.0","event_id":"sha256:f9259b1a80536e59a9bdf0fef67eb31e5fae4244990e8e3629431900026f177e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ETEZNWJISIQYIVV52EKG7QNBBQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Plug-and-Play Grounding of Reasoning in Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dehu Li, Jiaxing Chen, Weimo Deng, Xiang An, Yin Xie, Yongle Zhao, Yuxuan Liu, Ziyong Feng","submitted_at":"2024-03-28T11:26:30Z","abstract_excerpt":"The rise of Multimodal Large Language Models (MLLMs), renowned for their advanced instruction-following and reasoning capabilities, has significantly propelled the field of visual reasoning. However, due to limitations in their image tokenization processes, most MLLMs struggle to capture fine details of text and objects in images, especially in high-resolution samples. To overcome this limitation, we introduce P2G, a novel framework for plug-and-play grounding in MLLMs. P2G utilizes the tool-usage potential of MLLMs to employ expert agents for on-the-fly grounding of reasoning into critical vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19322","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/2403.19322/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":"2026-07-05T08:33:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2B2CcbAZD3ObivTahLqJ4fZy6O3Iq28si3HigYk34y1C56JoCP/ucBv0oIO5S94HO0h7uJfYxxwu3EQ+PN4qDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T02:02:09.454876Z"},"content_sha256":"52fc5d134c3daca6d6bd8c12a5743c85b8541889b0a46e52df92f95523e36a67","schema_version":"1.0","event_id":"sha256:52fc5d134c3daca6d6bd8c12a5743c85b8541889b0a46e52df92f95523e36a67"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ETEZNWJISIQYIVV52EKG7QNBBQ/bundle.json","state_url":"https://pith.science/pith/ETEZNWJISIQYIVV52EKG7QNBBQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ETEZNWJISIQYIVV52EKG7QNBBQ/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":"2026-08-17T02:02:09Z","links":{"resolver":"https://pith.science/pith/ETEZNWJISIQYIVV52EKG7QNBBQ","bundle":"https://pith.science/pith/ETEZNWJISIQYIVV52EKG7QNBBQ/bundle.json","state":"https://pith.science/pith/ETEZNWJISIQYIVV52EKG7QNBBQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ETEZNWJISIQYIVV52EKG7QNBBQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ETEZNWJISIQYIVV52EKG7QNBBQ","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":"23e815ddaba41692632bc434b790e269f9f4a5cbdfff4c6401f58cc6211815ca","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-28T11:26:30Z","title_canon_sha256":"5ca098a95d3e006b836bb1ad061a7bb2d7c914563058fe4ebd4ba9dcdb305eec"},"schema_version":"1.0","source":{"id":"2403.19322","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19322","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19322v2","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19322","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"pith_short_12","alias_value":"ETEZNWJISIQY","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"pith_short_16","alias_value":"ETEZNWJISIQYIVV5","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"pith_short_8","alias_value":"ETEZNWJI","created_at":"2026-07-05T08:33:38Z"}],"graph_snapshots":[{"event_id":"sha256:52fc5d134c3daca6d6bd8c12a5743c85b8541889b0a46e52df92f95523e36a67","target":"graph","created_at":"2026-07-05T08:33:38Z","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/2403.19322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rise of Multimodal Large Language Models (MLLMs), renowned for their advanced instruction-following and reasoning capabilities, has significantly propelled the field of visual reasoning. However, due to limitations in their image tokenization processes, most MLLMs struggle to capture fine details of text and objects in images, especially in high-resolution samples. To overcome this limitation, we introduce P2G, a novel framework for plug-and-play grounding in MLLMs. P2G utilizes the tool-usage potential of MLLMs to employ expert agents for on-the-fly grounding of reasoning into critical vi","authors_text":"Dehu Li, Jiaxing Chen, Weimo Deng, Xiang An, Yin Xie, Yongle Zhao, Yuxuan Liu, Ziyong Feng","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-28T11:26:30Z","title":"Plug-and-Play Grounding of Reasoning in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19322","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:f9259b1a80536e59a9bdf0fef67eb31e5fae4244990e8e3629431900026f177e","target":"record","created_at":"2026-07-05T08:33:38Z","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":"23e815ddaba41692632bc434b790e269f9f4a5cbdfff4c6401f58cc6211815ca","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-28T11:26:30Z","title_canon_sha256":"5ca098a95d3e006b836bb1ad061a7bb2d7c914563058fe4ebd4ba9dcdb305eec"},"schema_version":"1.0","source":{"id":"2403.19322","kind":"arxiv","version":2}},"canonical_sha256":"24c996d92892218456bdd1146fc1a10c2c1a1b18f153943491fca37d39c1ffda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24c996d92892218456bdd1146fc1a10c2c1a1b18f153943491fca37d39c1ffda","first_computed_at":"2026-07-05T08:33:38.241336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:38.241336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3r3ZXiMaYCxnFWRjIEPmfxOpOHmh431pCWcY9O7SNZJrfwdMV23auJYsyM9d7NEW6XjoM8wrAToHmcw1ya7RAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:38.241820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19322","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9259b1a80536e59a9bdf0fef67eb31e5fae4244990e8e3629431900026f177e","sha256:52fc5d134c3daca6d6bd8c12a5743c85b8541889b0a46e52df92f95523e36a67"],"state_sha256":"f55222f53d77cb8749d4ee3296d7ea0f273fd014b83cf91108ba50061781988f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AzxmaSEcTWSD6MdcUTKK0tXLJ+LtWL9Sqc63Mr//3TfJ6bPkFwsEJ6U3GbghtZtAUFsOIMkh3+IT1X/cm3NhCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T02:02:09.464349Z","bundle_sha256":"6e2ddc0bc2bdedb493e297e0dc4dbceab063b1b1e6ef8f5c860b922ce1f56b5e"}}