{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3BJD23DKYGC5EC6FQ3W7Q2LSFG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b2e4bab5aed473156d5c00196e4ccc95852605b43825f055c5a2bb6e56d27238","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T01:34:28Z","title_canon_sha256":"a1611c68e2bfbc49384837e4dfcbeaf132e72bba0367a6edaae1781249830c57"},"schema_version":"1.0","source":{"id":"2503.06380","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.06380","created_at":"2026-07-05T10:27:32Z"},{"alias_kind":"arxiv_version","alias_value":"2503.06380v1","created_at":"2026-07-05T10:27:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06380","created_at":"2026-07-05T10:27:32Z"},{"alias_kind":"pith_short_12","alias_value":"3BJD23DKYGC5","created_at":"2026-07-05T10:27:32Z"},{"alias_kind":"pith_short_16","alias_value":"3BJD23DKYGC5EC6F","created_at":"2026-07-05T10:27:32Z"},{"alias_kind":"pith_short_8","alias_value":"3BJD23DK","created_at":"2026-07-05T10:27:32Z"}],"graph_snapshots":[{"event_id":"sha256:5045ff70bc53d66c81f5febcba4ade07d9a2fd04a7cf6830ec58b251c6359ecf","target":"graph","created_at":"2026-07-05T10:27:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.06380/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Duc P. T. Nguyen, Khang H. N. Vo, Thong Nguyen, Tho T. Quan","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T01:34:28Z","title":"TI-JEPA: An Innovative Energy-based Joint Embedding Strategy for Text-Image Multimodal Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06380","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:57d89317e3fc23e05db08fc410527658900bdbb12b8e222ba3881846c1133312","target":"record","created_at":"2026-07-05T10:27:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b2e4bab5aed473156d5c00196e4ccc95852605b43825f055c5a2bb6e56d27238","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-09T01:34:28Z","title_canon_sha256":"a1611c68e2bfbc49384837e4dfcbeaf132e72bba0367a6edaae1781249830c57"},"schema_version":"1.0","source":{"id":"2503.06380","kind":"arxiv","version":1}},"canonical_sha256":"d8523d6c6ac185d20bc586edf8697229b9f5d705163b8f4ffd8336c95fd8a896","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8523d6c6ac185d20bc586edf8697229b9f5d705163b8f4ffd8336c95fd8a896","first_computed_at":"2026-07-05T10:27:32.000363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:32.000363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UCxPZHR4gYhP7v9ANrRgmEFqSno/all03YkGTeFzaYKfUrpNkrmTUu+kDmJKu6wTsqYrdFMrFF0FWlBpkOxZBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:32.000848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.06380","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57d89317e3fc23e05db08fc410527658900bdbb12b8e222ba3881846c1133312","sha256:5045ff70bc53d66c81f5febcba4ade07d9a2fd04a7cf6830ec58b251c6359ecf"],"state_sha256":"79b7a628535525589faf32d3a0c939a069525c2d701b187a4ca8fc55f8171fa2"}