{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RBLXUOBZM4GCTISQG5PI4QVDSR","short_pith_number":"pith:RBLXUOBZ","schema_version":"1.0","canonical_sha256":"88577a3839670c29a250375e8e42a3944d6ef45c0fe354a7cf0a26fc4be7f82d","source":{"kind":"arxiv","id":"2407.15731","version":2},"attestation_state":"computed","paper":{"title":"The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Vogt-Lowell, Laura Niss, Theodoros Tsiligkaridis","submitted_at":"2024-07-22T15:35:09Z","abstract_excerpt":"The fine-tuning of large vision-language foundation models remains an underexplored area, particularly regarding its impact on learning gains and catastrophic forgetting. Inspired by the significance of modality gaps in contrastive dual-encoders, we introduce the Inter-Intra Modal Measure (IIMM) - a predictive metric that quantifies the relationship between intra-modal image embedding similarity and inter-modal misalignment. Through extensive empirical analysis across four state-of-the-art vision-language models and five fine-tuning techniques, we establish a strong linear relationship: tasks "},"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":"2407.15731","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T15:35:09Z","cross_cats_sorted":[],"title_canon_sha256":"39f4c00b9561dc4502aca13bbb1dc511e1385f51148e7214d9fc28483abf37a1","abstract_canon_sha256":"edacc44bd0ab3635d4f5afa56f5d1bff39741f130018f77803fa11ebbc16bfc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:12.826670Z","signature_b64":"YfOIiKEoyxtxpOX8CfRFcb7gVhcx2nG9ZhlcpIcf8NR1DwoWPAEpqYOij7kEUaIeWJymTFR9LEFGKve3NXZ6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88577a3839670c29a250375e8e42a3944d6ef45c0fe354a7cf0a26fc4be7f82d","last_reissued_at":"2026-07-05T11:47:12.826150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:12.826150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kevin Vogt-Lowell, Laura Niss, Theodoros Tsiligkaridis","submitted_at":"2024-07-22T15:35:09Z","abstract_excerpt":"The fine-tuning of large vision-language foundation models remains an underexplored area, particularly regarding its impact on learning gains and catastrophic forgetting. Inspired by the significance of modality gaps in contrastive dual-encoders, we introduce the Inter-Intra Modal Measure (IIMM) - a predictive metric that quantifies the relationship between intra-modal image embedding similarity and inter-modal misalignment. Through extensive empirical analysis across four state-of-the-art vision-language models and five fine-tuning techniques, we establish a strong linear relationship: tasks "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15731","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/2407.15731/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":"2407.15731","created_at":"2026-07-05T11:47:12.826209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15731v2","created_at":"2026-07-05T11:47:12.826209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15731","created_at":"2026-07-05T11:47:12.826209+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBLXUOBZM4GC","created_at":"2026-07-05T11:47:12.826209+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBLXUOBZM4GCTISQ","created_at":"2026-07-05T11:47:12.826209+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBLXUOBZ","created_at":"2026-07-05T11:47:12.826209+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17235","citing_title":"CHAOS: Chart Analysis with Outlier Samples","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RBLXUOBZM4GCTISQG5PI4QVDSR","json":"https://pith.science/pith/RBLXUOBZM4GCTISQG5PI4QVDSR.json","graph_json":"https://pith.science/api/pith-number/RBLXUOBZM4GCTISQG5PI4QVDSR/graph.json","events_json":"https://pith.science/api/pith-number/RBLXUOBZM4GCTISQG5PI4QVDSR/events.json","paper":"https://pith.science/paper/RBLXUOBZ"},"agent_actions":{"view_html":"https://pith.science/pith/RBLXUOBZM4GCTISQG5PI4QVDSR","download_json":"https://pith.science/pith/RBLXUOBZM4GCTISQG5PI4QVDSR.json","view_paper":"https://pith.science/paper/RBLXUOBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15731&json=true","fetch_graph":"https://pith.science/api/pith-number/RBLXUOBZM4GCTISQG5PI4QVDSR/graph.json","fetch_events":"https://pith.science/api/pith-number/RBLXUOBZM4GCTISQG5PI4QVDSR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBLXUOBZM4GCTISQG5PI4QVDSR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBLXUOBZM4GCTISQG5PI4QVDSR/action/storage_attestation","attest_author":"https://pith.science/pith/RBLXUOBZM4GCTISQG5PI4QVDSR/action/author_attestation","sign_citation":"https://pith.science/pith/RBLXUOBZM4GCTISQG5PI4QVDSR/action/citation_signature","submit_replication":"https://pith.science/pith/RBLXUOBZM4GCTISQG5PI4QVDSR/action/replication_record"}},"created_at":"2026-07-05T11:47:12.826209+00:00","updated_at":"2026-07-05T11:47:12.826209+00:00"}