{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FLJIL72IZHQEJ5V264U4CMN2ZC","short_pith_number":"pith:FLJIL72I","schema_version":"1.0","canonical_sha256":"2ad285ff48c9e044f6baf729c131bac8a7deb55e5cf0f16a2db8ab21f2991b74","source":{"kind":"arxiv","id":"1811.09796","version":6},"attestation_state":"computed","paper":{"title":"A Novel Technique for Evidence based Conditional Inference in Deep Neural Networks via Latent Feature Perturbation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chetan Arora, Dinesh Khandelwal, Parag Singla, Suyash Agrawal","submitted_at":"2018-11-24T09:17:57Z","abstract_excerpt":"Auxiliary information can be exploited in machine learning models using the paradigm of evidence based conditional inference. Multi-modal techniques in Deep Neural Networks (DNNs) can be seen as perturbing the latent feature representation for incorporating evidence from the auxiliary modality. However, they require training a specialized network which can map sparse evidence to a high dimensional latent space vector. Designing such a network, as well as collecting jointly labeled data for training is a non-trivial task. In this paper, we present a novel multi-task learning (MTL) based framewo"},"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":"1811.09796","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-24T09:17:57Z","cross_cats_sorted":[],"title_canon_sha256":"9ca54f894eafe3cfe62cbb46626e9b8f9c64f26b79a6d4b46d494896335cc7ce","abstract_canon_sha256":"fced577ec0219c3cb425c58ad3089db9d985eb403021eff7ce582312d4b37934"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:25.412819Z","signature_b64":"/k15UZQH9UswWeYN49fzyQSJb6l0n1NfMK6dTdsNzPRR+Ax63Tg+hSXmgjMkvjvIT4hameGHQlI7i8H3yLo8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ad285ff48c9e044f6baf729c131bac8a7deb55e5cf0f16a2db8ab21f2991b74","last_reissued_at":"2026-07-05T00:24:25.412369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:25.412369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Novel Technique for Evidence based Conditional Inference in Deep Neural Networks via Latent Feature Perturbation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chetan Arora, Dinesh Khandelwal, Parag Singla, Suyash Agrawal","submitted_at":"2018-11-24T09:17:57Z","abstract_excerpt":"Auxiliary information can be exploited in machine learning models using the paradigm of evidence based conditional inference. Multi-modal techniques in Deep Neural Networks (DNNs) can be seen as perturbing the latent feature representation for incorporating evidence from the auxiliary modality. However, they require training a specialized network which can map sparse evidence to a high dimensional latent space vector. Designing such a network, as well as collecting jointly labeled data for training is a non-trivial task. In this paper, we present a novel multi-task learning (MTL) based framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09796","kind":"arxiv","version":6},"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/1811.09796/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":"1811.09796","created_at":"2026-07-05T00:24:25.412427+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.09796v6","created_at":"2026-07-05T00:24:25.412427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09796","created_at":"2026-07-05T00:24:25.412427+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLJIL72IZHQE","created_at":"2026-07-05T00:24:25.412427+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLJIL72IZHQEJ5V2","created_at":"2026-07-05T00:24:25.412427+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLJIL72I","created_at":"2026-07-05T00:24:25.412427+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/FLJIL72IZHQEJ5V264U4CMN2ZC","json":"https://pith.science/pith/FLJIL72IZHQEJ5V264U4CMN2ZC.json","graph_json":"https://pith.science/api/pith-number/FLJIL72IZHQEJ5V264U4CMN2ZC/graph.json","events_json":"https://pith.science/api/pith-number/FLJIL72IZHQEJ5V264U4CMN2ZC/events.json","paper":"https://pith.science/paper/FLJIL72I"},"agent_actions":{"view_html":"https://pith.science/pith/FLJIL72IZHQEJ5V264U4CMN2ZC","download_json":"https://pith.science/pith/FLJIL72IZHQEJ5V264U4CMN2ZC.json","view_paper":"https://pith.science/paper/FLJIL72I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.09796&json=true","fetch_graph":"https://pith.science/api/pith-number/FLJIL72IZHQEJ5V264U4CMN2ZC/graph.json","fetch_events":"https://pith.science/api/pith-number/FLJIL72IZHQEJ5V264U4CMN2ZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLJIL72IZHQEJ5V264U4CMN2ZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLJIL72IZHQEJ5V264U4CMN2ZC/action/storage_attestation","attest_author":"https://pith.science/pith/FLJIL72IZHQEJ5V264U4CMN2ZC/action/author_attestation","sign_citation":"https://pith.science/pith/FLJIL72IZHQEJ5V264U4CMN2ZC/action/citation_signature","submit_replication":"https://pith.science/pith/FLJIL72IZHQEJ5V264U4CMN2ZC/action/replication_record"}},"created_at":"2026-07-05T00:24:25.412427+00:00","updated_at":"2026-07-05T00:24:25.412427+00:00"}