{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VJNS5STM7EF377CYYBVFEJBYKY","short_pith_number":"pith:VJNS5STM","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"},"canonical_sha256":"aa5b2eca6cf90bbffc58c06a522438562142cff8c9e100f9a66e7447be250936","source":{"kind":"arxiv","id":"1805.01047","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.01047","created_at":"2026-05-17T23:51:39Z"},{"alias_kind":"arxiv_version","alias_value":"1805.01047v2","created_at":"2026-05-17T23:51:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.01047","created_at":"2026-05-17T23:51:39Z"},{"alias_kind":"pith_short_12","alias_value":"VJNS5STM7EF3","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VJNS5STM7EF377CY","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VJNS5STM","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VJNS5STM7EF377CYYBVFEJBYKY","target":"record","payload":{"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"},"canonical_sha256":"aa5b2eca6cf90bbffc58c06a522438562142cff8c9e100f9a66e7447be250936","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"},"source_kind":"arxiv","source_id":"1805.01047","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a4WQ/iUugwBkTpV1gu4zCU0bXxGGevsbtUGIT0p3AwtLYwAUfoxgxFCteYyMAM5wWLPO4MxjlDMdlI+tmCR2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:39:17.348212Z"},"content_sha256":"773e7265c49514531e8ae5dba04c9e362c138855c4c44de03541616790af707b","schema_version":"1.0","event_id":"sha256:773e7265c49514531e8ae5dba04c9e362c138855c4c44de03541616790af707b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VJNS5STM7EF377CYYBVFEJBYKY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1oF+Fv8yLBVIio5WfRL7tomZ65O/vUf0apqfLIj4C5c37wtb7UdMZnvhBdGuEdGwvfWIy7wyUSemr+xGChOXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:39:17.348601Z"},"content_sha256":"8585f56dc80ea8e7ff47d48ed48bb17471e89f718aa4a7de199dff2398c26fec","schema_version":"1.0","event_id":"sha256:8585f56dc80ea8e7ff47d48ed48bb17471e89f718aa4a7de199dff2398c26fec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY/bundle.json","state_url":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJNS5STM7EF377CYYBVFEJBYKY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T21:39:17Z","links":{"resolver":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY","bundle":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY/bundle.json","state":"https://pith.science/pith/VJNS5STM7EF377CYYBVFEJBYKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJNS5STM7EF377CYYBVFEJBYKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VJNS5STM7EF377CYYBVFEJBYKY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7b157068b5b638924cdbc2b3fb6aaf1b36eb6ac14ccea5bd2dc81262460994d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-02T22:32:12Z","title_canon_sha256":"8d8c38de01b4acf742af501af95d6f677ddef2f13aa4f40bdc161715a5917129"},"schema_version":"1.0","source":{"id":"1805.01047","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.01047","created_at":"2026-05-17T23:51:39Z"},{"alias_kind":"arxiv_version","alias_value":"1805.01047v2","created_at":"2026-05-17T23:51:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.01047","created_at":"2026-05-17T23:51:39Z"},{"alias_kind":"pith_short_12","alias_value":"VJNS5STM7EF3","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VJNS5STM7EF377CY","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VJNS5STM","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:8585f56dc80ea8e7ff47d48ed48bb17471e89f718aa4a7de199dff2398c26fec","target":"graph","created_at":"2026-05-17T23:51:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Neil D. B. Bruce, Sen Jia","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-02T22:32:12Z","title":"EML-NET:An Expandable Multi-Layer NETwork for Saliency Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.01047","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:773e7265c49514531e8ae5dba04c9e362c138855c4c44de03541616790af707b","target":"record","created_at":"2026-05-17T23:51:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7b157068b5b638924cdbc2b3fb6aaf1b36eb6ac14ccea5bd2dc81262460994d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-02T22:32:12Z","title_canon_sha256":"8d8c38de01b4acf742af501af95d6f677ddef2f13aa4f40bdc161715a5917129"},"schema_version":"1.0","source":{"id":"1805.01047","kind":"arxiv","version":2}},"canonical_sha256":"aa5b2eca6cf90bbffc58c06a522438562142cff8c9e100f9a66e7447be250936","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa5b2eca6cf90bbffc58c06a522438562142cff8c9e100f9a66e7447be250936","first_computed_at":"2026-05-17T23:51:39.632268Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:39.632268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+U1+Z5aMXbE65oT4jqnXA3UhF642ePRdO0xyE838qrnWG5UAJFWmmZaEfzSc8Y9BoqEgHVIybR4aLoE6LYOnCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:39.632931Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.01047","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:773e7265c49514531e8ae5dba04c9e362c138855c4c44de03541616790af707b","sha256:8585f56dc80ea8e7ff47d48ed48bb17471e89f718aa4a7de199dff2398c26fec"],"state_sha256":"b61107be0b1dda02d0487a84a8fb3c604ac1955afd79183bf98be878483f531f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kAege9ChP8wwJfBcpuiEHTX8Pdlp1L+OOnAD0zYsSZjXL5L7vKewpWIsQ/cAO2PY5d0JHi9bVgOlX6Q6xBKsCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T21:39:17.351454Z","bundle_sha256":"22b8e429fc1429983c5de5053407a1d27fb0d146f88914c2eb642c9868a3b67d"}}