{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VJNS5STM7EF377CYYBVFEJBYKY","short_pith_number":"pith:VJNS5STM","schema_version":"1.0","canonical_sha256":"aa5b2eca6cf90bbffc58c06a522438562142cff8c9e100f9a66e7447be250936","source":{"kind":"arxiv","id":"1805.01047","version":2},"attestation_state":"computed","paper":{"title":"EML-NET:An Expandable Multi-Layer NETwork for Saliency Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Neil D. B. Bruce, Sen Jia","submitted_at":"2018-05-02T22:32:12Z","abstract_excerpt":"Saliency prediction can benefit from training that involves scene understanding that may be tangential to the central task; this may include understanding places, spatial layout, objects or involve different datasets and their bias. One can combine models, but to do this in a sophisticated manner can be complex, and also result in unwieldy networks or produce competing objectives that are hard to balance. In this paper, we propose a scalable system to leverage multiple powerful deep CNN models to better extract visual features for saliency prediction. Our design differs from previous studies i"},"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":"1805.01047","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-02T22:32:12Z","cross_cats_sorted":[],"title_canon_sha256":"8d8c38de01b4acf742af501af95d6f677ddef2f13aa4f40bdc161715a5917129","abstract_canon_sha256":"7b157068b5b638924cdbc2b3fb6aaf1b36eb6ac14ccea5bd2dc81262460994d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:39.632931Z","signature_b64":"+U1+Z5aMXbE65oT4jqnXA3UhF642ePRdO0xyE838qrnWG5UAJFWmmZaEfzSc8Y9BoqEgHVIybR4aLoE6LYOnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa5b2eca6cf90bbffc58c06a522438562142cff8c9e100f9a66e7447be250936","last_reissued_at":"2026-05-17T23:51:39.632268Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:39.632268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EML-NET:An Expandable Multi-Layer NETwork for Saliency Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Neil D. B. Bruce, Sen Jia","submitted_at":"2018-05-02T22:32:12Z","abstract_excerpt":"Saliency prediction can benefit from training that involves scene understanding that may be tangential to the central task; this may include understanding places, spatial layout, objects or involve different datasets and their bias. One can combine models, but to do this in a sophisticated manner can be complex, and also result in unwieldy networks or produce competing objectives that are hard to balance. In this paper, we propose a scalable system to leverage multiple powerful deep CNN models to better extract visual features for saliency prediction. Our design differs from previous studies i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.01047","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":""},"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":"1805.01047","created_at":"2026-05-17T23:51:39.632377+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.01047v2","created_at":"2026-05-17T23:51:39.632377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.01047","created_at":"2026-05-17T23:51:39.632377+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJNS5STM7EF3","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJNS5STM7EF377CY","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJNS5STM","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.02336","citing_title":"Deep Saliency Models : The Quest For The Loss Function","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY","json":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY.json","graph_json":"https://pith.science/api/pith-number/VJNS5STM7EF377CYYBVFEJBYKY/graph.json","events_json":"https://pith.science/api/pith-number/VJNS5STM7EF377CYYBVFEJBYKY/events.json","paper":"https://pith.science/paper/VJNS5STM"},"agent_actions":{"view_html":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY","download_json":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY.json","view_paper":"https://pith.science/paper/VJNS5STM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.01047&json=true","fetch_graph":"https://pith.science/api/pith-number/VJNS5STM7EF377CYYBVFEJBYKY/graph.json","fetch_events":"https://pith.science/api/pith-number/VJNS5STM7EF377CYYBVFEJBYKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY/action/storage_attestation","attest_author":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY/action/author_attestation","sign_citation":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY/action/citation_signature","submit_replication":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY/action/replication_record"}},"created_at":"2026-05-17T23:51:39.632377+00:00","updated_at":"2026-05-17T23:51:39.632377+00:00"}