{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BDBDFIX4RXBUQ57ZBTZWC7VA3D","short_pith_number":"pith:BDBDFIX4","schema_version":"1.0","canonical_sha256":"08c232a2fc8dc34877f90cf3617ea0d8f8c9d007c4932d7da90dc68f01f80c9c","source":{"kind":"arxiv","id":"1907.07804","version":2},"attestation_state":"computed","paper":{"title":"OmniNet: A unified architecture for multi-modal multi-task learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aman Hussain, Priyanka Agrawal, Subhojeet Pramanik","submitted_at":"2019-07-17T22:59:56Z","abstract_excerpt":"Transformer is a popularly used neural network architecture, especially for language understanding. We introduce an extended and unified architecture that can be used for tasks involving a variety of modalities like image, text, videos, etc. We propose a spatio-temporal cache mechanism that enables learning spatial dimension of the input in addition to the hidden states corresponding to the temporal input sequence. The proposed architecture further enables a single model to support tasks with multiple input modalities as well as asynchronous multi-task learning, thus we refer to it as OmniNet."},"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":"1907.07804","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-17T22:59:56Z","cross_cats_sorted":["cs.CL","cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"a53fa3d45763f2eb832067def50e1d60de296c0a17f67711921a63793f502a93","abstract_canon_sha256":"2ab4caf599b8b177e2f01537e5fa6485b3aa4e515457af17294001c20a358a40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:55.105388Z","signature_b64":"lZsnpznNmUlww+WW4MxWndPqm47t3Z+C7zw19XMxxvcdk7OtQB+upaHLkkWsr58kOxd/V1HBVah4T0zghIo9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08c232a2fc8dc34877f90cf3617ea0d8f8c9d007c4932d7da90dc68f01f80c9c","last_reissued_at":"2026-07-05T01:15:55.104993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:55.104993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniNet: A unified architecture for multi-modal multi-task learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aman Hussain, Priyanka Agrawal, Subhojeet Pramanik","submitted_at":"2019-07-17T22:59:56Z","abstract_excerpt":"Transformer is a popularly used neural network architecture, especially for language understanding. We introduce an extended and unified architecture that can be used for tasks involving a variety of modalities like image, text, videos, etc. We propose a spatio-temporal cache mechanism that enables learning spatial dimension of the input in addition to the hidden states corresponding to the temporal input sequence. The proposed architecture further enables a single model to support tasks with multiple input modalities as well as asynchronous multi-task learning, thus we refer to it as OmniNet."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.07804","kind":"arxiv","version":2},"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/1907.07804/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":"1907.07804","created_at":"2026-07-05T01:15:55.105058+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.07804v2","created_at":"2026-07-05T01:15:55.105058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.07804","created_at":"2026-07-05T01:15:55.105058+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDBDFIX4RXBU","created_at":"2026-07-05T01:15:55.105058+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDBDFIX4RXBUQ57Z","created_at":"2026-07-05T01:15:55.105058+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDBDFIX4","created_at":"2026-07-05T01:15:55.105058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09323","citing_title":"Dynamic Inter-Class Confusion-Aware Encoder for Audio-Visual Fusion in Human Activity Recognition","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BDBDFIX4RXBUQ57ZBTZWC7VA3D","json":"https://pith.science/pith/BDBDFIX4RXBUQ57ZBTZWC7VA3D.json","graph_json":"https://pith.science/api/pith-number/BDBDFIX4RXBUQ57ZBTZWC7VA3D/graph.json","events_json":"https://pith.science/api/pith-number/BDBDFIX4RXBUQ57ZBTZWC7VA3D/events.json","paper":"https://pith.science/paper/BDBDFIX4"},"agent_actions":{"view_html":"https://pith.science/pith/BDBDFIX4RXBUQ57ZBTZWC7VA3D","download_json":"https://pith.science/pith/BDBDFIX4RXBUQ57ZBTZWC7VA3D.json","view_paper":"https://pith.science/paper/BDBDFIX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.07804&json=true","fetch_graph":"https://pith.science/api/pith-number/BDBDFIX4RXBUQ57ZBTZWC7VA3D/graph.json","fetch_events":"https://pith.science/api/pith-number/BDBDFIX4RXBUQ57ZBTZWC7VA3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDBDFIX4RXBUQ57ZBTZWC7VA3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDBDFIX4RXBUQ57ZBTZWC7VA3D/action/storage_attestation","attest_author":"https://pith.science/pith/BDBDFIX4RXBUQ57ZBTZWC7VA3D/action/author_attestation","sign_citation":"https://pith.science/pith/BDBDFIX4RXBUQ57ZBTZWC7VA3D/action/citation_signature","submit_replication":"https://pith.science/pith/BDBDFIX4RXBUQ57ZBTZWC7VA3D/action/replication_record"}},"created_at":"2026-07-05T01:15:55.105058+00:00","updated_at":"2026-07-05T01:15:55.105058+00:00"}