{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LUHQPM55BO4Q4DVQOAFHLXVDUT","short_pith_number":"pith:LUHQPM55","schema_version":"1.0","canonical_sha256":"5d0f07b3bd0bb90e0eb0700a75dea3a4ca975a7fcebc8fad6d28420232bc0259","source":{"kind":"arxiv","id":"2501.08597","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Knowledge Integration for Enhanced Vision-Language Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Julian Perry, Surasakdi Siripong, Thanakorn Phonchai","submitted_at":"2025-01-15T05:45:04Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in multimodal tasks, but their performance is often constrained by the lack of external knowledge integration, limiting their ability to handle knowledge-intensive tasks such as visual question answering and reasoning. To address this challenge, we propose a novel method, Adaptive Knowledge-Guided Pretraining for Large Vision-Language Models (AKGP-LVLM), which dynamically incorporates structured and unstructured knowledge into LVLMs during pretraining and fine-tuning. Our approach employs a knowledge encoder to repr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.08597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-15T05:45:04Z","cross_cats_sorted":[],"title_canon_sha256":"21dc543bbc9f95122a3c0e0106454981d1e56d29fb97ac152dc8c83c50b0f15b","abstract_canon_sha256":"4c94b89f2f4851b635c2128c84275196dd70269f0850a991bfc0b25861cb2cd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:21.821725Z","signature_b64":"ORdf0GKicFwyDmGqJOth+XMwOPn9LDAqB6+DEgtKDLqeLUro9zb2ldlWb+lmkmqJVFkF10/+uY84ccK/SgIpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d0f07b3bd0bb90e0eb0700a75dea3a4ca975a7fcebc8fad6d28420232bc0259","last_reissued_at":"2026-07-05T10:01:21.821268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:21.821268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Knowledge Integration for Enhanced Vision-Language Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Julian Perry, Surasakdi Siripong, Thanakorn Phonchai","submitted_at":"2025-01-15T05:45:04Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in multimodal tasks, but their performance is often constrained by the lack of external knowledge integration, limiting their ability to handle knowledge-intensive tasks such as visual question answering and reasoning. To address this challenge, we propose a novel method, Adaptive Knowledge-Guided Pretraining for Large Vision-Language Models (AKGP-LVLM), which dynamically incorporates structured and unstructured knowledge into LVLMs during pretraining and fine-tuning. Our approach employs a knowledge encoder to repr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08597","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/2501.08597/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.08597","created_at":"2026-07-05T10:01:21.821323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08597v1","created_at":"2026-07-05T10:01:21.821323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08597","created_at":"2026-07-05T10:01:21.821323+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUHQPM55BO4Q","created_at":"2026-07-05T10:01:21.821323+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUHQPM55BO4Q4DVQ","created_at":"2026-07-05T10:01:21.821323+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUHQPM55","created_at":"2026-07-05T10:01:21.821323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.12343","citing_title":"Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUHQPM55BO4Q4DVQOAFHLXVDUT","json":"https://pith.science/pith/LUHQPM55BO4Q4DVQOAFHLXVDUT.json","graph_json":"https://pith.science/api/pith-number/LUHQPM55BO4Q4DVQOAFHLXVDUT/graph.json","events_json":"https://pith.science/api/pith-number/LUHQPM55BO4Q4DVQOAFHLXVDUT/events.json","paper":"https://pith.science/paper/LUHQPM55"},"agent_actions":{"view_html":"https://pith.science/pith/LUHQPM55BO4Q4DVQOAFHLXVDUT","download_json":"https://pith.science/pith/LUHQPM55BO4Q4DVQOAFHLXVDUT.json","view_paper":"https://pith.science/paper/LUHQPM55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08597&json=true","fetch_graph":"https://pith.science/api/pith-number/LUHQPM55BO4Q4DVQOAFHLXVDUT/graph.json","fetch_events":"https://pith.science/api/pith-number/LUHQPM55BO4Q4DVQOAFHLXVDUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUHQPM55BO4Q4DVQOAFHLXVDUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUHQPM55BO4Q4DVQOAFHLXVDUT/action/storage_attestation","attest_author":"https://pith.science/pith/LUHQPM55BO4Q4DVQOAFHLXVDUT/action/author_attestation","sign_citation":"https://pith.science/pith/LUHQPM55BO4Q4DVQOAFHLXVDUT/action/citation_signature","submit_replication":"https://pith.science/pith/LUHQPM55BO4Q4DVQOAFHLXVDUT/action/replication_record"}},"created_at":"2026-07-05T10:01:21.821323+00:00","updated_at":"2026-07-05T10:01:21.821323+00:00"}