{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3BJD23DKYGC5EC6FQ3W7Q2LSFG","short_pith_number":"pith:3BJD23DK","schema_version":"1.0","canonical_sha256":"d8523d6c6ac185d20bc586edf8697229b9f5d705163b8f4ffd8336c95fd8a896","source":{"kind":"arxiv","id":"2503.06380","version":1},"attestation_state":"computed","paper":{"title":"TI-JEPA: An Innovative Energy-based Joint Embedding Strategy for Text-Image Multimodal Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Duc P. T. Nguyen, Khang H. N. Vo, Thong Nguyen, Tho T. Quan","submitted_at":"2025-03-09T01:34:28Z","abstract_excerpt":"This paper focuses on multimodal alignment within the realm of Artificial Intelligence, particularly in text and image modalities. The semantic gap between the textual and visual modality poses a discrepancy problem towards the effectiveness of multi-modalities fusion. Therefore, we introduce Text-Image Joint Embedding Predictive Architecture (TI-JEPA), an innovative pre-training strategy that leverages energy-based model (EBM) framework to capture complex cross-modal relationships. TI-JEPA combines the flexibility of EBM in self-supervised learning to facilitate the compatibility between text"},"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":"2503.06380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T01:34:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a1611c68e2bfbc49384837e4dfcbeaf132e72bba0367a6edaae1781249830c57","abstract_canon_sha256":"b2e4bab5aed473156d5c00196e4ccc95852605b43825f055c5a2bb6e56d27238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:32.000848Z","signature_b64":"UCxPZHR4gYhP7v9ANrRgmEFqSno/all03YkGTeFzaYKfUrpNkrmTUu+kDmJKu6wTsqYrdFMrFF0FWlBpkOxZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8523d6c6ac185d20bc586edf8697229b9f5d705163b8f4ffd8336c95fd8a896","last_reissued_at":"2026-07-05T10:27:32.000363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:32.000363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TI-JEPA: An Innovative Energy-based Joint Embedding Strategy for Text-Image Multimodal Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Duc P. T. Nguyen, Khang H. N. Vo, Thong Nguyen, Tho T. Quan","submitted_at":"2025-03-09T01:34:28Z","abstract_excerpt":"This paper focuses on multimodal alignment within the realm of Artificial Intelligence, particularly in text and image modalities. The semantic gap between the textual and visual modality poses a discrepancy problem towards the effectiveness of multi-modalities fusion. Therefore, we introduce Text-Image Joint Embedding Predictive Architecture (TI-JEPA), an innovative pre-training strategy that leverages energy-based model (EBM) framework to capture complex cross-modal relationships. TI-JEPA combines the flexibility of EBM in self-supervised learning to facilitate the compatibility between text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06380","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/2503.06380/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":"2503.06380","created_at":"2026-07-05T10:27:32.000424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06380v1","created_at":"2026-07-05T10:27:32.000424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06380","created_at":"2026-07-05T10:27:32.000424+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BJD23DKYGC5","created_at":"2026-07-05T10:27:32.000424+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BJD23DKYGC5EC6F","created_at":"2026-07-05T10:27:32.000424+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BJD23DK","created_at":"2026-07-05T10:27:32.000424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02915","citing_title":"Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3BJD23DKYGC5EC6FQ3W7Q2LSFG","json":"https://pith.science/pith/3BJD23DKYGC5EC6FQ3W7Q2LSFG.json","graph_json":"https://pith.science/api/pith-number/3BJD23DKYGC5EC6FQ3W7Q2LSFG/graph.json","events_json":"https://pith.science/api/pith-number/3BJD23DKYGC5EC6FQ3W7Q2LSFG/events.json","paper":"https://pith.science/paper/3BJD23DK"},"agent_actions":{"view_html":"https://pith.science/pith/3BJD23DKYGC5EC6FQ3W7Q2LSFG","download_json":"https://pith.science/pith/3BJD23DKYGC5EC6FQ3W7Q2LSFG.json","view_paper":"https://pith.science/paper/3BJD23DK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06380&json=true","fetch_graph":"https://pith.science/api/pith-number/3BJD23DKYGC5EC6FQ3W7Q2LSFG/graph.json","fetch_events":"https://pith.science/api/pith-number/3BJD23DKYGC5EC6FQ3W7Q2LSFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BJD23DKYGC5EC6FQ3W7Q2LSFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BJD23DKYGC5EC6FQ3W7Q2LSFG/action/storage_attestation","attest_author":"https://pith.science/pith/3BJD23DKYGC5EC6FQ3W7Q2LSFG/action/author_attestation","sign_citation":"https://pith.science/pith/3BJD23DKYGC5EC6FQ3W7Q2LSFG/action/citation_signature","submit_replication":"https://pith.science/pith/3BJD23DKYGC5EC6FQ3W7Q2LSFG/action/replication_record"}},"created_at":"2026-07-05T10:27:32.000424+00:00","updated_at":"2026-07-05T10:27:32.000424+00:00"}