{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GW7UCTK5IPUYH52LEM6XJARVUT","short_pith_number":"pith:GW7UCTK5","schema_version":"1.0","canonical_sha256":"35bf414d5d43e983f74b233d748235a4db4f440fcec4d3029ae790ba7b260901","source":{"kind":"arxiv","id":"2605.19523","version":1},"attestation_state":"computed","paper":{"title":"Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Hao Zhou, Jie Zhou, Lean Wang, Lei Li, Xu Sun, Yuanxin Liu, Zhiyu Xu","submitted_at":"2026-05-19T08:24:19Z","abstract_excerpt":"Vision-Language Models (VLMs) have demonstrated remarkable proficiency in general multi-modal understanding; yet they struggle to efficiently acquire continually evolving domain-specific skills. Conventional approaches to enhancing VLM capabilities, such as Supervised Fine-Tuning (SFT), require extensive dataset curation and substantial computational resources. Model merging has emerged as an efficient alternative that enables the transfer of domain-specific expertise from Large Language Models (LLMs) to VLMs without incurring additional training data requirements or significant computational "},"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":"2605.19523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T08:24:19Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"c49eb9831a301288d36ebdf6a7349318c32747ba66b73ddcb476915acc646327","abstract_canon_sha256":"bf33169c662121ac08fc2921b20707fa83e6ae0daa762fa49d9cc9e5a7b646ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:49.993485Z","signature_b64":"fCt9YHMO/79PpfzXJAGsEfv5GwFHwXVOvLLuA+fs9RJsb/OOzjqUeNOsPjRo9wa18bHNuXGDCKVmY2MuS8rmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35bf414d5d43e983f74b233d748235a4db4f440fcec4d3029ae790ba7b260901","last_reissued_at":"2026-05-20T01:05:49.992714Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:49.992714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Hao Zhou, Jie Zhou, Lean Wang, Lei Li, Xu Sun, Yuanxin Liu, Zhiyu Xu","submitted_at":"2026-05-19T08:24:19Z","abstract_excerpt":"Vision-Language Models (VLMs) have demonstrated remarkable proficiency in general multi-modal understanding; yet they struggle to efficiently acquire continually evolving domain-specific skills. Conventional approaches to enhancing VLM capabilities, such as Supervised Fine-Tuning (SFT), require extensive dataset curation and substantial computational resources. Model merging has emerged as an efficient alternative that enables the transfer of domain-specific expertise from Large Language Models (LLMs) to VLMs without incurring additional training data requirements or significant computational "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19523","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/2605.19523/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":"2605.19523","created_at":"2026-05-20T01:05:49.992837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19523v1","created_at":"2026-05-20T01:05:49.992837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19523","created_at":"2026-05-20T01:05:49.992837+00:00"},{"alias_kind":"pith_short_12","alias_value":"GW7UCTK5IPUY","created_at":"2026-05-20T01:05:49.992837+00:00"},{"alias_kind":"pith_short_16","alias_value":"GW7UCTK5IPUYH52L","created_at":"2026-05-20T01:05:49.992837+00:00"},{"alias_kind":"pith_short_8","alias_value":"GW7UCTK5","created_at":"2026-05-20T01:05:49.992837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GW7UCTK5IPUYH52LEM6XJARVUT","json":"https://pith.science/pith/GW7UCTK5IPUYH52LEM6XJARVUT.json","graph_json":"https://pith.science/api/pith-number/GW7UCTK5IPUYH52LEM6XJARVUT/graph.json","events_json":"https://pith.science/api/pith-number/GW7UCTK5IPUYH52LEM6XJARVUT/events.json","paper":"https://pith.science/paper/GW7UCTK5"},"agent_actions":{"view_html":"https://pith.science/pith/GW7UCTK5IPUYH52LEM6XJARVUT","download_json":"https://pith.science/pith/GW7UCTK5IPUYH52LEM6XJARVUT.json","view_paper":"https://pith.science/paper/GW7UCTK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19523&json=true","fetch_graph":"https://pith.science/api/pith-number/GW7UCTK5IPUYH52LEM6XJARVUT/graph.json","fetch_events":"https://pith.science/api/pith-number/GW7UCTK5IPUYH52LEM6XJARVUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GW7UCTK5IPUYH52LEM6XJARVUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GW7UCTK5IPUYH52LEM6XJARVUT/action/storage_attestation","attest_author":"https://pith.science/pith/GW7UCTK5IPUYH52LEM6XJARVUT/action/author_attestation","sign_citation":"https://pith.science/pith/GW7UCTK5IPUYH52LEM6XJARVUT/action/citation_signature","submit_replication":"https://pith.science/pith/GW7UCTK5IPUYH52LEM6XJARVUT/action/replication_record"}},"created_at":"2026-05-20T01:05:49.992837+00:00","updated_at":"2026-05-20T01:05:49.992837+00:00"}