{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5BSEDU3S3GPRRZR5R5AXNIKK77","short_pith_number":"pith:5BSEDU3S","schema_version":"1.0","canonical_sha256":"e86441d372d99f18e63d8f4176a14affc7936b6fcafb83e6454090c195501734","source":{"kind":"arxiv","id":"2507.13364","version":1},"attestation_state":"computed","paper":{"title":"OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gaurav Sharma, Siddharth Srivastava","submitted_at":"2025-07-06T18:51:22Z","abstract_excerpt":"We present a novel multimodal multitask network and associated training algorithm. The method is capable of ingesting data from approximately 12 different modalities namely image, video, audio, text, depth, point cloud, time series, tabular, graph, X-ray, infrared, IMU, and hyperspectral. The proposed approach utilizes modality specialized tokenizers, a shared transformer architecture, and cross-attention mechanisms to project the data from different modalities into a unified embedding space. It addresses multimodal and multitask scenarios by incorporating modality-specific task heads for diff"},"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":"2507.13364","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-06T18:51:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"753399631a82e2991d1d570654e7adf06dc9a3ec08a0fb98a3da714b3c107cc4","abstract_canon_sha256":"9bb3aaff315463d528025813ef761179fc845ed0ecd427f220b154e9eeeba34f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:15.986458Z","signature_b64":"PX7XfoY3SaaXH7PWrfFew9g42zaYvT0TNhf8XIMXhGI8YfqHtFnNHzHT8QOQNNm/Sn01NBnTINqCfjkWAFxlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e86441d372d99f18e63d8f4176a14affc7936b6fcafb83e6454090c195501734","last_reissued_at":"2026-07-05T11:39:15.985977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:15.985977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gaurav Sharma, Siddharth Srivastava","submitted_at":"2025-07-06T18:51:22Z","abstract_excerpt":"We present a novel multimodal multitask network and associated training algorithm. The method is capable of ingesting data from approximately 12 different modalities namely image, video, audio, text, depth, point cloud, time series, tabular, graph, X-ray, infrared, IMU, and hyperspectral. The proposed approach utilizes modality specialized tokenizers, a shared transformer architecture, and cross-attention mechanisms to project the data from different modalities into a unified embedding space. It addresses multimodal and multitask scenarios by incorporating modality-specific task heads for diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13364","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/2507.13364/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":"2507.13364","created_at":"2026-07-05T11:39:15.986051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13364v1","created_at":"2026-07-05T11:39:15.986051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13364","created_at":"2026-07-05T11:39:15.986051+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BSEDU3S3GPR","created_at":"2026-07-05T11:39:15.986051+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BSEDU3S3GPRRZR5","created_at":"2026-07-05T11:39:15.986051+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BSEDU3S","created_at":"2026-07-05T11:39:15.986051+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/5BSEDU3S3GPRRZR5R5AXNIKK77","json":"https://pith.science/pith/5BSEDU3S3GPRRZR5R5AXNIKK77.json","graph_json":"https://pith.science/api/pith-number/5BSEDU3S3GPRRZR5R5AXNIKK77/graph.json","events_json":"https://pith.science/api/pith-number/5BSEDU3S3GPRRZR5R5AXNIKK77/events.json","paper":"https://pith.science/paper/5BSEDU3S"},"agent_actions":{"view_html":"https://pith.science/pith/5BSEDU3S3GPRRZR5R5AXNIKK77","download_json":"https://pith.science/pith/5BSEDU3S3GPRRZR5R5AXNIKK77.json","view_paper":"https://pith.science/paper/5BSEDU3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13364&json=true","fetch_graph":"https://pith.science/api/pith-number/5BSEDU3S3GPRRZR5R5AXNIKK77/graph.json","fetch_events":"https://pith.science/api/pith-number/5BSEDU3S3GPRRZR5R5AXNIKK77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BSEDU3S3GPRRZR5R5AXNIKK77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BSEDU3S3GPRRZR5R5AXNIKK77/action/storage_attestation","attest_author":"https://pith.science/pith/5BSEDU3S3GPRRZR5R5AXNIKK77/action/author_attestation","sign_citation":"https://pith.science/pith/5BSEDU3S3GPRRZR5R5AXNIKK77/action/citation_signature","submit_replication":"https://pith.science/pith/5BSEDU3S3GPRRZR5R5AXNIKK77/action/replication_record"}},"created_at":"2026-07-05T11:39:15.986051+00:00","updated_at":"2026-07-05T11:39:15.986051+00:00"}