{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X4M6VM74E3UKKOQGSGG7IETTAS","short_pith_number":"pith:X4M6VM74","schema_version":"1.0","canonical_sha256":"bf19eab3fc26e8a53a06918df4127304bdab273c6a9b92518c5414e468fee2c5","source":{"kind":"arxiv","id":"2606.00706","version":1},"attestation_state":"computed","paper":{"title":"CR-JEPA: Cross-Modal Joint-Embedding Predictive Learning for Remote Sensing Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayush V. Patel, Biplab Banerjee, Md Aminur Hossain, Nitant Dube","submitted_at":"2026-05-30T12:29:46Z","abstract_excerpt":"Cross-modal remote sensing image retrieval aims to retrieve semantically related scenes across heterogeneous sensing modalities. This remains challenging because paired observations may differ substantially in imaging physics, spatial resolution, spectral configuration, and visual appearance. Moreover, a single retrieval projection trained with one objective may be insufficient to jointly support cross-modal semantic alignment and same-modal neighbourhood preservation. We propose CR-JEPA, a Cross-modal Retrieval Joint-Embedding Predictive Architecture for dual-modality remote sensing retrieval"},"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":"2606.00706","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T12:29:46Z","cross_cats_sorted":[],"title_canon_sha256":"06a25d00783b78f1324359bb0c715bf32f07f29ecce912f3d172933a41143e2b","abstract_canon_sha256":"116ddac38375ffc25f56dd67917903c03aa7cc4e15268d8b747b83778be13da0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:03.326719Z","signature_b64":"nG/JsEXRxr6RI32vnFVfQ8IqPwcv3fmyU3A2c/RY27a4eeakTi+Cnni4BFkQ+z3wUDibMt5SNYlV2ZchzETHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf19eab3fc26e8a53a06918df4127304bdab273c6a9b92518c5414e468fee2c5","last_reissued_at":"2026-06-02T01:04:03.326264Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:03.326264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CR-JEPA: Cross-Modal Joint-Embedding Predictive Learning for Remote Sensing Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayush V. Patel, Biplab Banerjee, Md Aminur Hossain, Nitant Dube","submitted_at":"2026-05-30T12:29:46Z","abstract_excerpt":"Cross-modal remote sensing image retrieval aims to retrieve semantically related scenes across heterogeneous sensing modalities. This remains challenging because paired observations may differ substantially in imaging physics, spatial resolution, spectral configuration, and visual appearance. Moreover, a single retrieval projection trained with one objective may be insufficient to jointly support cross-modal semantic alignment and same-modal neighbourhood preservation. We propose CR-JEPA, a Cross-modal Retrieval Joint-Embedding Predictive Architecture for dual-modality remote sensing retrieval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00706","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/2606.00706/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":"2606.00706","created_at":"2026-06-02T01:04:03.326344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00706v1","created_at":"2026-06-02T01:04:03.326344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00706","created_at":"2026-06-02T01:04:03.326344+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4M6VM74E3UK","created_at":"2026-06-02T01:04:03.326344+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4M6VM74E3UKKOQG","created_at":"2026-06-02T01:04:03.326344+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4M6VM74","created_at":"2026-06-02T01:04:03.326344+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/X4M6VM74E3UKKOQGSGG7IETTAS","json":"https://pith.science/pith/X4M6VM74E3UKKOQGSGG7IETTAS.json","graph_json":"https://pith.science/api/pith-number/X4M6VM74E3UKKOQGSGG7IETTAS/graph.json","events_json":"https://pith.science/api/pith-number/X4M6VM74E3UKKOQGSGG7IETTAS/events.json","paper":"https://pith.science/paper/X4M6VM74"},"agent_actions":{"view_html":"https://pith.science/pith/X4M6VM74E3UKKOQGSGG7IETTAS","download_json":"https://pith.science/pith/X4M6VM74E3UKKOQGSGG7IETTAS.json","view_paper":"https://pith.science/paper/X4M6VM74","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00706&json=true","fetch_graph":"https://pith.science/api/pith-number/X4M6VM74E3UKKOQGSGG7IETTAS/graph.json","fetch_events":"https://pith.science/api/pith-number/X4M6VM74E3UKKOQGSGG7IETTAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4M6VM74E3UKKOQGSGG7IETTAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4M6VM74E3UKKOQGSGG7IETTAS/action/storage_attestation","attest_author":"https://pith.science/pith/X4M6VM74E3UKKOQGSGG7IETTAS/action/author_attestation","sign_citation":"https://pith.science/pith/X4M6VM74E3UKKOQGSGG7IETTAS/action/citation_signature","submit_replication":"https://pith.science/pith/X4M6VM74E3UKKOQGSGG7IETTAS/action/replication_record"}},"created_at":"2026-06-02T01:04:03.326344+00:00","updated_at":"2026-06-02T01:04:03.326344+00:00"}