{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:5DJ3O42CGAKLLIKR73UDP3VNTQ","short_pith_number":"pith:5DJ3O42C","canonical_record":{"source":{"id":"1609.02077","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-07T17:13:16Z","cross_cats_sorted":[],"title_canon_sha256":"4c2f7a6cf45950090665d5c9a7f17ff6014f47c8fbc2c4d09532882a46652982","abstract_canon_sha256":"14de981193f4555c5bd9c863285a703e32b1c03e20a8bd43a37bce1a75d663bd"},"schema_version":"1.0"},"canonical_sha256":"e8d3b773423014b5a151fee837eead9c265c9fa1db09aee3469a6b914764de72","source":{"kind":"arxiv","id":"1609.02077","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.02077","created_at":"2026-05-18T01:00:25Z"},{"alias_kind":"arxiv_version","alias_value":"1609.02077v1","created_at":"2026-05-18T01:00:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.02077","created_at":"2026-05-18T01:00:25Z"},{"alias_kind":"pith_short_12","alias_value":"5DJ3O42CGAKL","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5DJ3O42CGAKLLIKR","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5DJ3O42C","created_at":"2026-05-18T12:30:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:5DJ3O42CGAKLLIKR73UDP3VNTQ","target":"record","payload":{"canonical_record":{"source":{"id":"1609.02077","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-07T17:13:16Z","cross_cats_sorted":[],"title_canon_sha256":"4c2f7a6cf45950090665d5c9a7f17ff6014f47c8fbc2c4d09532882a46652982","abstract_canon_sha256":"14de981193f4555c5bd9c863285a703e32b1c03e20a8bd43a37bce1a75d663bd"},"schema_version":"1.0"},"canonical_sha256":"e8d3b773423014b5a151fee837eead9c265c9fa1db09aee3469a6b914764de72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:25.200629Z","signature_b64":"c8GqrRud01ZG5/hgr1R6ypE+00+Ubh26xx/T5WKW/K1rd4wlS+FDOoICKaTYq+Yycaf+la/e9NAziTDmm2cJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8d3b773423014b5a151fee837eead9c265c9fa1db09aee3469a6b914764de72","last_reissued_at":"2026-05-18T01:00:25.200112Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:25.200112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.02077","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:00:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BhGXh5Gfs00B097r7ftRGshzyGI3C6sl369JjXrIoPPJD3e8O1JLbAMxqjsqsWjtgs0eoZdYRAGAy1qCLQD8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T03:46:48.854549Z"},"content_sha256":"06628a46c97268e5eb06c4f0dfb734370068318501020b9710d35e20550da8e0","schema_version":"1.0","event_id":"sha256:06628a46c97268e5eb06c4f0dfb734370068318501020b9710d35e20550da8e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:5DJ3O42CGAKLLIKR73UDP3VNTQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Saliency Detection Based on Multiscale Deep CNN Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanbin Li, Yizhou Yu","submitted_at":"2016-09-07T17:13:16Z","abstract_excerpt":"Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks (CNNs), which have had many successes in visual recognition tasks. For learning such saliency models, we introduce a neural network architecture, which has fully connected layers on top of CNNs responsible for feature extraction at three different scales. The penultimate layer of our neural network has been confirmed to be a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.02077","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:00:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/TPvzI0AtTapX8ct80tU3AY17wRN2pnOpbRN8ixm5EKOf2HZX4vMr6aSVSM0WownG4Sf2BcB/zt5UsM1MMR0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T03:46:48.855239Z"},"content_sha256":"91db11dd5e3be4ef522aba4cf067cba78ce0b5ea35bb0cb8c01996fc09ee08ed","schema_version":"1.0","event_id":"sha256:91db11dd5e3be4ef522aba4cf067cba78ce0b5ea35bb0cb8c01996fc09ee08ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5DJ3O42CGAKLLIKR73UDP3VNTQ/bundle.json","state_url":"https://pith.science/pith/5DJ3O42CGAKLLIKR73UDP3VNTQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5DJ3O42CGAKLLIKR73UDP3VNTQ/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":"2026-06-09T03:46:48Z","links":{"resolver":"https://pith.science/pith/5DJ3O42CGAKLLIKR73UDP3VNTQ","bundle":"https://pith.science/pith/5DJ3O42CGAKLLIKR73UDP3VNTQ/bundle.json","state":"https://pith.science/pith/5DJ3O42CGAKLLIKR73UDP3VNTQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5DJ3O42CGAKLLIKR73UDP3VNTQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:5DJ3O42CGAKLLIKR73UDP3VNTQ","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":"14de981193f4555c5bd9c863285a703e32b1c03e20a8bd43a37bce1a75d663bd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-07T17:13:16Z","title_canon_sha256":"4c2f7a6cf45950090665d5c9a7f17ff6014f47c8fbc2c4d09532882a46652982"},"schema_version":"1.0","source":{"id":"1609.02077","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.02077","created_at":"2026-05-18T01:00:25Z"},{"alias_kind":"arxiv_version","alias_value":"1609.02077v1","created_at":"2026-05-18T01:00:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.02077","created_at":"2026-05-18T01:00:25Z"},{"alias_kind":"pith_short_12","alias_value":"5DJ3O42CGAKL","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5DJ3O42CGAKLLIKR","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5DJ3O42C","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:91db11dd5e3be4ef522aba4cf067cba78ce0b5ea35bb0cb8c01996fc09ee08ed","target":"graph","created_at":"2026-05-18T01:00:25Z","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":"Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks (CNNs), which have had many successes in visual recognition tasks. For learning such saliency models, we introduce a neural network architecture, which has fully connected layers on top of CNNs responsible for feature extraction at three different scales. The penultimate layer of our neural network has been confirmed to be a","authors_text":"Guanbin Li, Yizhou Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-07T17:13:16Z","title":"Visual Saliency Detection Based on Multiscale Deep CNN Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.02077","kind":"arxiv","version":1},"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":"sha256:06628a46c97268e5eb06c4f0dfb734370068318501020b9710d35e20550da8e0","target":"record","created_at":"2026-05-18T01:00:25Z","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":"14de981193f4555c5bd9c863285a703e32b1c03e20a8bd43a37bce1a75d663bd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-07T17:13:16Z","title_canon_sha256":"4c2f7a6cf45950090665d5c9a7f17ff6014f47c8fbc2c4d09532882a46652982"},"schema_version":"1.0","source":{"id":"1609.02077","kind":"arxiv","version":1}},"canonical_sha256":"e8d3b773423014b5a151fee837eead9c265c9fa1db09aee3469a6b914764de72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8d3b773423014b5a151fee837eead9c265c9fa1db09aee3469a6b914764de72","first_computed_at":"2026-05-18T01:00:25.200112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:00:25.200112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c8GqrRud01ZG5/hgr1R6ypE+00+Ubh26xx/T5WKW/K1rd4wlS+FDOoICKaTYq+Yycaf+la/e9NAziTDmm2cJDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:00:25.200629Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.02077","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06628a46c97268e5eb06c4f0dfb734370068318501020b9710d35e20550da8e0","sha256:91db11dd5e3be4ef522aba4cf067cba78ce0b5ea35bb0cb8c01996fc09ee08ed"],"state_sha256":"ec9765a923e322c7f8767722476a15095b807c679234cda0662256f31729c01d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QtTJydhiZOqCVO2ALquIG75PFIw64wb1otXs5zDB+5yIi17z+CxLKka7RStBPuzitdtSFrRMChrwoXSkKaz1CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T03:46:48.859062Z","bundle_sha256":"d925ee2374571cb9b0ac980fed749e77b50183cb0e5f7e3fcedfd61843d0e679"}}