{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6PO4E3XZFTSPANATEQP2RXPJPZ","short_pith_number":"pith:6PO4E3XZ","schema_version":"1.0","canonical_sha256":"f3ddc26ef92ce4f03413241fa8dde97e5ed1282fc2928663b1dfd6b95ce11837","source":{"kind":"arxiv","id":"2606.10504","version":1},"attestation_state":"computed","paper":{"title":"Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anh Duc Chu, Phi Le Nguyen, Quang Hung Pham, Trong Khiem Tran, Trong Nghia Hoang","submitted_at":"2026-06-09T07:29:12Z","abstract_excerpt":"Cross-modal knowledge distillation (CMKD) studies how a (large) teacher model trained on one type of data (e.g., images) can guide a (smaller) student model building on another type of data (e.g., text/audio). Existing CMKD methods often require paired multi-modal data with aligned semantics, but obtaining such paired data are often costly and impractical. To mitigate this limitation, we develop a new CMKD framework for the more challenging setting where paired data are unavailable. In particular, we establish a cross-modal distributional relationship between teacher and student models, which "},"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":"2606.10504","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T07:29:12Z","cross_cats_sorted":[],"title_canon_sha256":"23e582519a48d654ab5cc0b19edef91f01b24ecf6b5bd77f469b93b83bbfe294","abstract_canon_sha256":"9661c99bea8c2c8741c33841f29a03e406960078a6f901a7138bab8c40699cb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:22.864913Z","signature_b64":"DxgwYcs9iXiS9YFqlZxZbeQ5QBLSalXLBfnR0Ek0gXtxhR/saE/r8qx3h1iGEwBj8plVZtRY3sonfj6uBXGkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3ddc26ef92ce4f03413241fa8dde97e5ed1282fc2928663b1dfd6b95ce11837","last_reissued_at":"2026-06-10T01:10:22.864461Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:22.864461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anh Duc Chu, Phi Le Nguyen, Quang Hung Pham, Trong Khiem Tran, Trong Nghia Hoang","submitted_at":"2026-06-09T07:29:12Z","abstract_excerpt":"Cross-modal knowledge distillation (CMKD) studies how a (large) teacher model trained on one type of data (e.g., images) can guide a (smaller) student model building on another type of data (e.g., text/audio). Existing CMKD methods often require paired multi-modal data with aligned semantics, but obtaining such paired data are often costly and impractical. To mitigate this limitation, we develop a new CMKD framework for the more challenging setting where paired data are unavailable. In particular, we establish a cross-modal distributional relationship between teacher and student models, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10504","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/2606.10504/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":"2606.10504","created_at":"2026-06-10T01:10:22.864528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10504v1","created_at":"2026-06-10T01:10:22.864528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10504","created_at":"2026-06-10T01:10:22.864528+00:00"},{"alias_kind":"pith_short_12","alias_value":"6PO4E3XZFTSP","created_at":"2026-06-10T01:10:22.864528+00:00"},{"alias_kind":"pith_short_16","alias_value":"6PO4E3XZFTSPANAT","created_at":"2026-06-10T01:10:22.864528+00:00"},{"alias_kind":"pith_short_8","alias_value":"6PO4E3XZ","created_at":"2026-06-10T01:10:22.864528+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/6PO4E3XZFTSPANATEQP2RXPJPZ","json":"https://pith.science/pith/6PO4E3XZFTSPANATEQP2RXPJPZ.json","graph_json":"https://pith.science/api/pith-number/6PO4E3XZFTSPANATEQP2RXPJPZ/graph.json","events_json":"https://pith.science/api/pith-number/6PO4E3XZFTSPANATEQP2RXPJPZ/events.json","paper":"https://pith.science/paper/6PO4E3XZ"},"agent_actions":{"view_html":"https://pith.science/pith/6PO4E3XZFTSPANATEQP2RXPJPZ","download_json":"https://pith.science/pith/6PO4E3XZFTSPANATEQP2RXPJPZ.json","view_paper":"https://pith.science/paper/6PO4E3XZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10504&json=true","fetch_graph":"https://pith.science/api/pith-number/6PO4E3XZFTSPANATEQP2RXPJPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/6PO4E3XZFTSPANATEQP2RXPJPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6PO4E3XZFTSPANATEQP2RXPJPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6PO4E3XZFTSPANATEQP2RXPJPZ/action/storage_attestation","attest_author":"https://pith.science/pith/6PO4E3XZFTSPANATEQP2RXPJPZ/action/author_attestation","sign_citation":"https://pith.science/pith/6PO4E3XZFTSPANATEQP2RXPJPZ/action/citation_signature","submit_replication":"https://pith.science/pith/6PO4E3XZFTSPANATEQP2RXPJPZ/action/replication_record"}},"created_at":"2026-06-10T01:10:22.864528+00:00","updated_at":"2026-06-10T01:10:22.864528+00:00"}