{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CBYDTD4HWW46ICCBPBKSY2RJRS","short_pith_number":"pith:CBYDTD4H","schema_version":"1.0","canonical_sha256":"1070398f87b5b9e4084178552c6a298c87a25db4439b99163e4437db544ac2b6","source":{"kind":"arxiv","id":"2407.12315","version":2},"attestation_state":"computed","paper":{"title":"ModalChorus: Visual Probing and Alignment of Multi-modal Embeddings via Modal Fusion Map","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.IR"],"primary_cat":"cs.CV","authors_text":"Shishi Xiao, Wei Zeng, Xingchen Zeng, Yilin Ye","submitted_at":"2024-07-17T04:49:56Z","abstract_excerpt":"Multi-modal embeddings form the foundation for vision-language models, such as CLIP embeddings, the most widely used text-image embeddings. However, these embeddings are vulnerable to subtle misalignment of cross-modal features, resulting in decreased model performance and diminished generalization. To address this problem, we design ModalChorus, an interactive system for visual probing and alignment of multi-modal embeddings. ModalChorus primarily offers a two-stage process: 1) embedding probing with Modal Fusion Map (MFM), a novel parametric dimensionality reduction method that integrates bo"},"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":"2407.12315","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T04:49:56Z","cross_cats_sorted":["cs.AI","cs.HC","cs.IR"],"title_canon_sha256":"cd1c822621a6115f6fb6919cbd08a103fbf4cf70b20943a8778e03696e4a3cc0","abstract_canon_sha256":"20d9b30233b9d15f9ac48aa7e47cc4fed41a49a79ab8df9a3edc9f70b91d75bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:29.128480Z","signature_b64":"PLWBy/feVPq248aSxJ6mg6mSEGX7nAFXI7HxqzjPQHr6X6b+cMZnfljZGns+0g809bVYqMggHRCCMzCBnmMuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1070398f87b5b9e4084178552c6a298c87a25db4439b99163e4437db544ac2b6","last_reissued_at":"2026-07-05T09:26:29.127991Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:29.127991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ModalChorus: Visual Probing and Alignment of Multi-modal Embeddings via Modal Fusion Map","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.IR"],"primary_cat":"cs.CV","authors_text":"Shishi Xiao, Wei Zeng, Xingchen Zeng, Yilin Ye","submitted_at":"2024-07-17T04:49:56Z","abstract_excerpt":"Multi-modal embeddings form the foundation for vision-language models, such as CLIP embeddings, the most widely used text-image embeddings. However, these embeddings are vulnerable to subtle misalignment of cross-modal features, resulting in decreased model performance and diminished generalization. To address this problem, we design ModalChorus, an interactive system for visual probing and alignment of multi-modal embeddings. ModalChorus primarily offers a two-stage process: 1) embedding probing with Modal Fusion Map (MFM), a novel parametric dimensionality reduction method that integrates bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12315","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/2407.12315/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":"2407.12315","created_at":"2026-07-05T09:26:29.128047+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12315v2","created_at":"2026-07-05T09:26:29.128047+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12315","created_at":"2026-07-05T09:26:29.128047+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBYDTD4HWW46","created_at":"2026-07-05T09:26:29.128047+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBYDTD4HWW46ICCB","created_at":"2026-07-05T09:26:29.128047+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBYDTD4H","created_at":"2026-07-05T09:26:29.128047+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16839","citing_title":"Human-Guided Image Generation for Expanding Small-Scale Training Image Datasets","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBYDTD4HWW46ICCBPBKSY2RJRS","json":"https://pith.science/pith/CBYDTD4HWW46ICCBPBKSY2RJRS.json","graph_json":"https://pith.science/api/pith-number/CBYDTD4HWW46ICCBPBKSY2RJRS/graph.json","events_json":"https://pith.science/api/pith-number/CBYDTD4HWW46ICCBPBKSY2RJRS/events.json","paper":"https://pith.science/paper/CBYDTD4H"},"agent_actions":{"view_html":"https://pith.science/pith/CBYDTD4HWW46ICCBPBKSY2RJRS","download_json":"https://pith.science/pith/CBYDTD4HWW46ICCBPBKSY2RJRS.json","view_paper":"https://pith.science/paper/CBYDTD4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12315&json=true","fetch_graph":"https://pith.science/api/pith-number/CBYDTD4HWW46ICCBPBKSY2RJRS/graph.json","fetch_events":"https://pith.science/api/pith-number/CBYDTD4HWW46ICCBPBKSY2RJRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBYDTD4HWW46ICCBPBKSY2RJRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBYDTD4HWW46ICCBPBKSY2RJRS/action/storage_attestation","attest_author":"https://pith.science/pith/CBYDTD4HWW46ICCBPBKSY2RJRS/action/author_attestation","sign_citation":"https://pith.science/pith/CBYDTD4HWW46ICCBPBKSY2RJRS/action/citation_signature","submit_replication":"https://pith.science/pith/CBYDTD4HWW46ICCBPBKSY2RJRS/action/replication_record"}},"created_at":"2026-07-05T09:26:29.128047+00:00","updated_at":"2026-07-05T09:26:29.128047+00:00"}