{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2QEY2XHYY2XENSBC3NUWHG5WAD","short_pith_number":"pith:2QEY2XHY","schema_version":"1.0","canonical_sha256":"d4098d5cf8c6ae46c822db69639bb600e7382f904ebcd301b8e63d1951937c9c","source":{"kind":"arxiv","id":"2608.12724","version":1},"attestation_state":"computed","paper":{"title":"MAG: MAnifold Guided Semi-Supervised Multi-modal In-Context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bharadwaj Veeravalli, Bowen Zheng, Fady Rezk, Kangkang Lu, Nancy F. Chen, Shijie Li, Tiankai Chen, Xiaodong Shi, Xun Xu, Zirui Cheng","submitted_at":"2026-08-13T02:10:52Z","abstract_excerpt":"Few-shot in-context learning (ICL) with multi-modal large language models (MLLMs) enables task adaptation without parameter updates, but its performance is highly sensitive to the quality and coverage of the selected demonstrations. While unlabeled multi-modal data is abundant, it remains elusive how to exploit them for ICL. We propose MAG (MAnifold-Guided semi-supervised in-context demonstra- tion selection), an efficient framework that leverages unlabeled data to improve multi-modal ICL. MAG formulates demonstration selection as a semi-supervised propagation problem on a multi-modal graph an"},"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":"2608.12724","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T02:10:52Z","cross_cats_sorted":[],"title_canon_sha256":"b0b1d003003b3a93c53ab388f581996994911bbcd94456e1aab7d665a9ad6807","abstract_canon_sha256":"741208dbb32c850ef9aedbb798c63fae451ae0d992bd3d469608f0d0c115d85a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:47:10.935609Z","signature_b64":"VWxGjoeDq8fmQ88vWNW1IiZsFXfasbkbAZuGSBaUJJAoUJbG8ureWJ1aM7cZgdm7m6ChsOOp6S7z0uZDMaaoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4098d5cf8c6ae46c822db69639bb600e7382f904ebcd301b8e63d1951937c9c","last_reissued_at":"2026-08-14T00:47:10.933313Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:47:10.933313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAG: MAnifold Guided Semi-Supervised Multi-modal In-Context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bharadwaj Veeravalli, Bowen Zheng, Fady Rezk, Kangkang Lu, Nancy F. Chen, Shijie Li, Tiankai Chen, Xiaodong Shi, Xun Xu, Zirui Cheng","submitted_at":"2026-08-13T02:10:52Z","abstract_excerpt":"Few-shot in-context learning (ICL) with multi-modal large language models (MLLMs) enables task adaptation without parameter updates, but its performance is highly sensitive to the quality and coverage of the selected demonstrations. While unlabeled multi-modal data is abundant, it remains elusive how to exploit them for ICL. We propose MAG (MAnifold-Guided semi-supervised in-context demonstra- tion selection), an efficient framework that leverages unlabeled data to improve multi-modal ICL. MAG formulates demonstration selection as a semi-supervised propagation problem on a multi-modal graph an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12724","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/2608.12724/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":"2608.12724","created_at":"2026-08-14T00:47:10.934393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12724v1","created_at":"2026-08-14T00:47:10.934393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12724","created_at":"2026-08-14T00:47:10.934393+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QEY2XHYY2XE","created_at":"2026-08-14T00:47:10.934393+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QEY2XHYY2XENSBC","created_at":"2026-08-14T00:47:10.934393+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QEY2XHY","created_at":"2026-08-14T00:47:10.934393+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/2QEY2XHYY2XENSBC3NUWHG5WAD","json":"https://pith.science/pith/2QEY2XHYY2XENSBC3NUWHG5WAD.json","graph_json":"https://pith.science/api/pith-number/2QEY2XHYY2XENSBC3NUWHG5WAD/graph.json","events_json":"https://pith.science/api/pith-number/2QEY2XHYY2XENSBC3NUWHG5WAD/events.json","paper":"https://pith.science/paper/2QEY2XHY"},"agent_actions":{"view_html":"https://pith.science/pith/2QEY2XHYY2XENSBC3NUWHG5WAD","download_json":"https://pith.science/pith/2QEY2XHYY2XENSBC3NUWHG5WAD.json","view_paper":"https://pith.science/paper/2QEY2XHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12724&json=true","fetch_graph":"https://pith.science/api/pith-number/2QEY2XHYY2XENSBC3NUWHG5WAD/graph.json","fetch_events":"https://pith.science/api/pith-number/2QEY2XHYY2XENSBC3NUWHG5WAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QEY2XHYY2XENSBC3NUWHG5WAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QEY2XHYY2XENSBC3NUWHG5WAD/action/storage_attestation","attest_author":"https://pith.science/pith/2QEY2XHYY2XENSBC3NUWHG5WAD/action/author_attestation","sign_citation":"https://pith.science/pith/2QEY2XHYY2XENSBC3NUWHG5WAD/action/citation_signature","submit_replication":"https://pith.science/pith/2QEY2XHYY2XENSBC3NUWHG5WAD/action/replication_record"}},"created_at":"2026-08-14T00:47:10.934393+00:00","updated_at":"2026-08-14T00:47:10.934393+00:00"}