{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AYRC5V6MXUCUHOPGPQBKZT2FKG","short_pith_number":"pith:AYRC5V6M","schema_version":"1.0","canonical_sha256":"06222ed7ccbd0543b9e67c02accf45518b8f63e7fa772c8742cbb61f0e06fc04","source":{"kind":"arxiv","id":"2311.05709","version":1},"attestation_state":"computed","paper":{"title":"OmniVec: Learning robust representations with cross modal sharing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gaurav Sharma, Siddharth Srivastava","submitted_at":"2023-11-07T14:00:09Z","abstract_excerpt":"Majority of research in learning based methods has been towards designing and training networks for specific tasks. However, many of the learning based tasks, across modalities, share commonalities and could be potentially tackled in a joint framework. We present an approach in such direction, to learn multiple tasks, in multiple modalities, with a unified architecture. The proposed network is composed of task specific encoders, a common trunk in the middle, followed by task specific prediction heads. We first pre-train it by self-supervised masked training, followed by sequential training for"},"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":"2311.05709","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T14:00:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f37ff2e3aab2f7b05ce226fd016519fcb5b5e62a05c818f3c4ae04642c33a0c2","abstract_canon_sha256":"39b7865aece0c33286f7c402cd0df01c5b7c0af923e610f7989392bcf57551c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:21.609797Z","signature_b64":"RAehp9dXKah4VmbDXUK0rEWPdKP3VUWBWs+GZwiENXcaMaFX1fBIsPsExB33HqZeo3ayJw8tJrvMU+QPwRxgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06222ed7ccbd0543b9e67c02accf45518b8f63e7fa772c8742cbb61f0e06fc04","last_reissued_at":"2026-07-05T07:11:21.609250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:21.609250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniVec: Learning robust representations with cross modal sharing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gaurav Sharma, Siddharth Srivastava","submitted_at":"2023-11-07T14:00:09Z","abstract_excerpt":"Majority of research in learning based methods has been towards designing and training networks for specific tasks. However, many of the learning based tasks, across modalities, share commonalities and could be potentially tackled in a joint framework. We present an approach in such direction, to learn multiple tasks, in multiple modalities, with a unified architecture. The proposed network is composed of task specific encoders, a common trunk in the middle, followed by task specific prediction heads. We first pre-train it by self-supervised masked training, followed by sequential training for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05709","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/2311.05709/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":"2311.05709","created_at":"2026-07-05T07:11:21.609322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.05709v1","created_at":"2026-07-05T07:11:21.609322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05709","created_at":"2026-07-05T07:11:21.609322+00:00"},{"alias_kind":"pith_short_12","alias_value":"AYRC5V6MXUCU","created_at":"2026-07-05T07:11:21.609322+00:00"},{"alias_kind":"pith_short_16","alias_value":"AYRC5V6MXUCUHOPG","created_at":"2026-07-05T07:11:21.609322+00:00"},{"alias_kind":"pith_short_8","alias_value":"AYRC5V6M","created_at":"2026-07-05T07:11:21.609322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.17323","citing_title":"XAMI -- A Benchmark Dataset for Artefact Detection in XMM-Newton Optical Images","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AYRC5V6MXUCUHOPGPQBKZT2FKG","json":"https://pith.science/pith/AYRC5V6MXUCUHOPGPQBKZT2FKG.json","graph_json":"https://pith.science/api/pith-number/AYRC5V6MXUCUHOPGPQBKZT2FKG/graph.json","events_json":"https://pith.science/api/pith-number/AYRC5V6MXUCUHOPGPQBKZT2FKG/events.json","paper":"https://pith.science/paper/AYRC5V6M"},"agent_actions":{"view_html":"https://pith.science/pith/AYRC5V6MXUCUHOPGPQBKZT2FKG","download_json":"https://pith.science/pith/AYRC5V6MXUCUHOPGPQBKZT2FKG.json","view_paper":"https://pith.science/paper/AYRC5V6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.05709&json=true","fetch_graph":"https://pith.science/api/pith-number/AYRC5V6MXUCUHOPGPQBKZT2FKG/graph.json","fetch_events":"https://pith.science/api/pith-number/AYRC5V6MXUCUHOPGPQBKZT2FKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AYRC5V6MXUCUHOPGPQBKZT2FKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AYRC5V6MXUCUHOPGPQBKZT2FKG/action/storage_attestation","attest_author":"https://pith.science/pith/AYRC5V6MXUCUHOPGPQBKZT2FKG/action/author_attestation","sign_citation":"https://pith.science/pith/AYRC5V6MXUCUHOPGPQBKZT2FKG/action/citation_signature","submit_replication":"https://pith.science/pith/AYRC5V6MXUCUHOPGPQBKZT2FKG/action/replication_record"}},"created_at":"2026-07-05T07:11:21.609322+00:00","updated_at":"2026-07-05T07:11:21.609322+00:00"}