{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JNW7M5UHRGPXZAOIB6H2P2PIUK","short_pith_number":"pith:JNW7M5UH","schema_version":"1.0","canonical_sha256":"4b6df67687899f7c81c80f8fa7e9e8a29c09eb55672a7c5ed00d5c81a87ec0e5","source":{"kind":"arxiv","id":"2303.14865","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris N. Metaxas, Ding Zhou, Hongxia Yang, Jianbo Yuan, Shijie Geng, Xinyu Li, Yu Tian, Yuxiao Chen","submitted_at":"2023-03-27T00:58:39Z","abstract_excerpt":"Contrastive learning-based vision-language pre-training approaches, such as CLIP, have demonstrated great success in many vision-language tasks. These methods achieve cross-modal alignment by encoding a matched image-text pair with similar feature embeddings, which are generated by aggregating information from visual patches and language tokens. However, direct aligning cross-modal information using such representations is challenging, as visual patches and text tokens differ in semantic levels and granularities. To alleviate this issue, we propose a Finite Discrete Tokens (FDT) based multimod"},"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":"2303.14865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-27T00:58:39Z","cross_cats_sorted":[],"title_canon_sha256":"1b0393cc74a18679ee750b486152c791fd3671b40a8150b45ad99e30b29c5573","abstract_canon_sha256":"1d886604899b1e31bd6e6eec7cdde5cd3c7949cb7f05b989174d1876821c32a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:47.104026Z","signature_b64":"N+FSnxJmvgpnM3Je+XxrVAwX1Y8tLtKmMfj2w4mKrZcANBD7e+18OGb2A/jkXWGOtUEmCZmZ1xXaMXTcaSebDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b6df67687899f7c81c80f8fa7e9e8a29c09eb55672a7c5ed00d5c81a87ec0e5","last_reissued_at":"2026-07-05T05:54:47.103535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:47.103535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris N. Metaxas, Ding Zhou, Hongxia Yang, Jianbo Yuan, Shijie Geng, Xinyu Li, Yu Tian, Yuxiao Chen","submitted_at":"2023-03-27T00:58:39Z","abstract_excerpt":"Contrastive learning-based vision-language pre-training approaches, such as CLIP, have demonstrated great success in many vision-language tasks. These methods achieve cross-modal alignment by encoding a matched image-text pair with similar feature embeddings, which are generated by aggregating information from visual patches and language tokens. However, direct aligning cross-modal information using such representations is challenging, as visual patches and text tokens differ in semantic levels and granularities. To alleviate this issue, we propose a Finite Discrete Tokens (FDT) based multimod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14865","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/2303.14865/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":"2303.14865","created_at":"2026-07-05T05:54:47.103616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14865v1","created_at":"2026-07-05T05:54:47.103616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14865","created_at":"2026-07-05T05:54:47.103616+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNW7M5UHRGPX","created_at":"2026-07-05T05:54:47.103616+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNW7M5UHRGPXZAOI","created_at":"2026-07-05T05:54:47.103616+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNW7M5UH","created_at":"2026-07-05T05:54:47.103616+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/JNW7M5UHRGPXZAOIB6H2P2PIUK","json":"https://pith.science/pith/JNW7M5UHRGPXZAOIB6H2P2PIUK.json","graph_json":"https://pith.science/api/pith-number/JNW7M5UHRGPXZAOIB6H2P2PIUK/graph.json","events_json":"https://pith.science/api/pith-number/JNW7M5UHRGPXZAOIB6H2P2PIUK/events.json","paper":"https://pith.science/paper/JNW7M5UH"},"agent_actions":{"view_html":"https://pith.science/pith/JNW7M5UHRGPXZAOIB6H2P2PIUK","download_json":"https://pith.science/pith/JNW7M5UHRGPXZAOIB6H2P2PIUK.json","view_paper":"https://pith.science/paper/JNW7M5UH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14865&json=true","fetch_graph":"https://pith.science/api/pith-number/JNW7M5UHRGPXZAOIB6H2P2PIUK/graph.json","fetch_events":"https://pith.science/api/pith-number/JNW7M5UHRGPXZAOIB6H2P2PIUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNW7M5UHRGPXZAOIB6H2P2PIUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNW7M5UHRGPXZAOIB6H2P2PIUK/action/storage_attestation","attest_author":"https://pith.science/pith/JNW7M5UHRGPXZAOIB6H2P2PIUK/action/author_attestation","sign_citation":"https://pith.science/pith/JNW7M5UHRGPXZAOIB6H2P2PIUK/action/citation_signature","submit_replication":"https://pith.science/pith/JNW7M5UHRGPXZAOIB6H2P2PIUK/action/replication_record"}},"created_at":"2026-07-05T05:54:47.103616+00:00","updated_at":"2026-07-05T05:54:47.103616+00:00"}