{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FR5YQYBLN6S4IO2PP6KY4BK3DU","short_pith_number":"pith:FR5YQYBL","schema_version":"1.0","canonical_sha256":"2c7b88602b6fa5c43b4f7f958e055b1d36166ee2866f4daeb4a6bb424e5ddc9c","source":{"kind":"arxiv","id":"1807.09534","version":1},"attestation_state":"computed","paper":{"title":"Conditional Information Gain Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cem Keskin, Lale Akarun, Ufuk Can Bi\\c{c}ici","submitted_at":"2018-07-25T11:26:46Z","abstract_excerpt":"Deep neural network models owe their representational power to the high number of learnable parameters. It is often infeasible to run these largely parametrized deep models in limited resource environments, like mobile phones. Network models employing conditional computing are able to reduce computational requirements while achieving high representational power, with their ability to model hierarchies. We propose Conditional Information Gain Networks, which allow the feed forward deep neural networks to execute conditionally, skipping parts of the model based on the sample and the decision mec"},"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":"1807.09534","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-25T11:26:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a177ab760b27f15a721c294430bfb4e6a53e974d3e0170ef43bf4fb57ec59298","abstract_canon_sha256":"423def8901e37271681a398be70fb5b9d51cec2d1b298840f10406082b3f9bf9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:46.632725Z","signature_b64":"5Qk11tykNRXautzDXAUEPkRntUWaWWff+0DVm9iG2tEQT3oQ71j4OYQfPy++lxRm/W3C+N+wAtppiMK+LeNxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c7b88602b6fa5c43b4f7f958e055b1d36166ee2866f4daeb4a6bb424e5ddc9c","last_reissued_at":"2026-05-18T00:09:46.632116Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:46.632116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional Information Gain Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cem Keskin, Lale Akarun, Ufuk Can Bi\\c{c}ici","submitted_at":"2018-07-25T11:26:46Z","abstract_excerpt":"Deep neural network models owe their representational power to the high number of learnable parameters. It is often infeasible to run these largely parametrized deep models in limited resource environments, like mobile phones. Network models employing conditional computing are able to reduce computational requirements while achieving high representational power, with their ability to model hierarchies. We propose Conditional Information Gain Networks, which allow the feed forward deep neural networks to execute conditionally, skipping parts of the model based on the sample and the decision mec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09534","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":""},"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":"1807.09534","created_at":"2026-05-18T00:09:46.632193+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.09534v1","created_at":"2026-05-18T00:09:46.632193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09534","created_at":"2026-05-18T00:09:46.632193+00:00"},{"alias_kind":"pith_short_12","alias_value":"FR5YQYBLN6S4","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FR5YQYBLN6S4IO2P","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FR5YQYBL","created_at":"2026-05-18T12:32:25.280505+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/FR5YQYBLN6S4IO2PP6KY4BK3DU","json":"https://pith.science/pith/FR5YQYBLN6S4IO2PP6KY4BK3DU.json","graph_json":"https://pith.science/api/pith-number/FR5YQYBLN6S4IO2PP6KY4BK3DU/graph.json","events_json":"https://pith.science/api/pith-number/FR5YQYBLN6S4IO2PP6KY4BK3DU/events.json","paper":"https://pith.science/paper/FR5YQYBL"},"agent_actions":{"view_html":"https://pith.science/pith/FR5YQYBLN6S4IO2PP6KY4BK3DU","download_json":"https://pith.science/pith/FR5YQYBLN6S4IO2PP6KY4BK3DU.json","view_paper":"https://pith.science/paper/FR5YQYBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.09534&json=true","fetch_graph":"https://pith.science/api/pith-number/FR5YQYBLN6S4IO2PP6KY4BK3DU/graph.json","fetch_events":"https://pith.science/api/pith-number/FR5YQYBLN6S4IO2PP6KY4BK3DU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FR5YQYBLN6S4IO2PP6KY4BK3DU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FR5YQYBLN6S4IO2PP6KY4BK3DU/action/storage_attestation","attest_author":"https://pith.science/pith/FR5YQYBLN6S4IO2PP6KY4BK3DU/action/author_attestation","sign_citation":"https://pith.science/pith/FR5YQYBLN6S4IO2PP6KY4BK3DU/action/citation_signature","submit_replication":"https://pith.science/pith/FR5YQYBLN6S4IO2PP6KY4BK3DU/action/replication_record"}},"created_at":"2026-05-18T00:09:46.632193+00:00","updated_at":"2026-05-18T00:09:46.632193+00:00"}