{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2O5MQMYHNPFBYZ26BHRBEBSGRF","short_pith_number":"pith:2O5MQMYH","schema_version":"1.0","canonical_sha256":"d3bac833076bca1c675e09e2120646896ef5ea6fc2b80c2b5a88ca5c4fa480bf","source":{"kind":"arxiv","id":"2605.18257","version":1},"attestation_state":"computed","paper":{"title":"CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jie Li, Kai Han, Zeyu Chen","submitted_at":"2026-05-18T11:56:19Z","abstract_excerpt":"Multimodal representation alignment is pivotal for large language models and robotics. Traditional methods are often hindered by cross-modal information discrepancies and data scarcity, leading to suboptimal alignment spaces that overlook modality-unique features. We propose CodeBind, a framework that optimizes multimodal representation spaces through a modality-shared-specific codebook design. By incrementally aligning target and bridging modalities, CodeBind bypasses the need for fully paired data. Unlike traditional hard alignment, CodeBind decomposes features into shared components for sem"},"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":"2605.18257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T11:56:19Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4e7bf3ed239fcf28781e6a2aa34177dbd75fb80987f22280e616cceb42a7b998","abstract_canon_sha256":"db45c236cd311ab6a275f160738daf58a2cbc1f460744a8b31a15407c67d91a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:52.418325Z","signature_b64":"tYigRDBIyt7aduDdaxWQtp/k84Fn/OPqbVtAlZ89sIhp12n+BcN13CQs0s6eMihtJa7dAYjTjCLzlyTD+cQwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3bac833076bca1c675e09e2120646896ef5ea6fc2b80c2b5a88ca5c4fa480bf","last_reissued_at":"2026-05-20T00:05:52.417726Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:52.417726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jie Li, Kai Han, Zeyu Chen","submitted_at":"2026-05-18T11:56:19Z","abstract_excerpt":"Multimodal representation alignment is pivotal for large language models and robotics. Traditional methods are often hindered by cross-modal information discrepancies and data scarcity, leading to suboptimal alignment spaces that overlook modality-unique features. We propose CodeBind, a framework that optimizes multimodal representation spaces through a modality-shared-specific codebook design. By incrementally aligning target and bridging modalities, CodeBind bypasses the need for fully paired data. Unlike traditional hard alignment, CodeBind decomposes features into shared components for sem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18257","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/2605.18257/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.262300Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.981539Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"31658d0f415e2bbc40c27c575f6d623cd0cee6910c3ee2f224e1bc0813f83d58"},"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":"2605.18257","created_at":"2026-05-20T00:05:52.417843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18257v1","created_at":"2026-05-20T00:05:52.417843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18257","created_at":"2026-05-20T00:05:52.417843+00:00"},{"alias_kind":"pith_short_12","alias_value":"2O5MQMYHNPFB","created_at":"2026-05-20T00:05:52.417843+00:00"},{"alias_kind":"pith_short_16","alias_value":"2O5MQMYHNPFBYZ26","created_at":"2026-05-20T00:05:52.417843+00:00"},{"alias_kind":"pith_short_8","alias_value":"2O5MQMYH","created_at":"2026-05-20T00:05:52.417843+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/2O5MQMYHNPFBYZ26BHRBEBSGRF","json":"https://pith.science/pith/2O5MQMYHNPFBYZ26BHRBEBSGRF.json","graph_json":"https://pith.science/api/pith-number/2O5MQMYHNPFBYZ26BHRBEBSGRF/graph.json","events_json":"https://pith.science/api/pith-number/2O5MQMYHNPFBYZ26BHRBEBSGRF/events.json","paper":"https://pith.science/paper/2O5MQMYH"},"agent_actions":{"view_html":"https://pith.science/pith/2O5MQMYHNPFBYZ26BHRBEBSGRF","download_json":"https://pith.science/pith/2O5MQMYHNPFBYZ26BHRBEBSGRF.json","view_paper":"https://pith.science/paper/2O5MQMYH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18257&json=true","fetch_graph":"https://pith.science/api/pith-number/2O5MQMYHNPFBYZ26BHRBEBSGRF/graph.json","fetch_events":"https://pith.science/api/pith-number/2O5MQMYHNPFBYZ26BHRBEBSGRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2O5MQMYHNPFBYZ26BHRBEBSGRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2O5MQMYHNPFBYZ26BHRBEBSGRF/action/storage_attestation","attest_author":"https://pith.science/pith/2O5MQMYHNPFBYZ26BHRBEBSGRF/action/author_attestation","sign_citation":"https://pith.science/pith/2O5MQMYHNPFBYZ26BHRBEBSGRF/action/citation_signature","submit_replication":"https://pith.science/pith/2O5MQMYHNPFBYZ26BHRBEBSGRF/action/replication_record"}},"created_at":"2026-05-20T00:05:52.417843+00:00","updated_at":"2026-05-20T00:05:52.417843+00:00"}