{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YYD6WLOHI3IRCR5YQLSNG7NQ46","short_pith_number":"pith:YYD6WLOH","canonical_record":{"source":{"id":"1810.03716","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-08T21:50:27Z","cross_cats_sorted":[],"title_canon_sha256":"e21aba01337e5293fe59187279012c56cb9cea50114cc19ade989e991bd040c4","abstract_canon_sha256":"4b6131c2fb7d54b457d5155b46e301fb1fe6c33292fb85766534deaa295ee42b"},"schema_version":"1.0"},"canonical_sha256":"c607eb2dc746d11147b882e4d37db0e7ba5b3074387173329f9fceb0253bd11d","source":{"kind":"arxiv","id":"1810.03716","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03716","created_at":"2026-05-17T23:45:09Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03716v3","created_at":"2026-05-17T23:45:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03716","created_at":"2026-05-17T23:45:09Z"},{"alias_kind":"pith_short_12","alias_value":"YYD6WLOHI3IR","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YYD6WLOHI3IRCR5Y","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YYD6WLOH","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YYD6WLOHI3IRCR5YQLSNG7NQ46","target":"record","payload":{"canonical_record":{"source":{"id":"1810.03716","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-08T21:50:27Z","cross_cats_sorted":[],"title_canon_sha256":"e21aba01337e5293fe59187279012c56cb9cea50114cc19ade989e991bd040c4","abstract_canon_sha256":"4b6131c2fb7d54b457d5155b46e301fb1fe6c33292fb85766534deaa295ee42b"},"schema_version":"1.0"},"canonical_sha256":"c607eb2dc746d11147b882e4d37db0e7ba5b3074387173329f9fceb0253bd11d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:09.548206Z","signature_b64":"gKlzyFxz5dZBKHhUbfqwFJf+9my4lWGrDY5uUWs2bjnLv43L5tYJPWVROfHz2cckutY8xrJs01ZH8jB6A5BIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c607eb2dc746d11147b882e4d37db0e7ba5b3074387173329f9fceb0253bd11d","last_reissued_at":"2026-05-17T23:45:09.547375Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:09.547375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.03716","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Mm8/a/s1rKf1YEjkXBs+ruuUaQsRq7TGjsGCbJlW2vG2477TcsosX2Mh3u9v9fp1nehIKE0WyKseI7WdvegBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T14:13:46.832517Z"},"content_sha256":"8468b8a76436688b93e61ce1e74bb5fcbe36b6fb6c252697354c4a15a1c203aa","schema_version":"1.0","event_id":"sha256:8468b8a76436688b93e61ce1e74bb5fcbe36b6fb6c252697354c4a15a1c203aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YYD6WLOHI3IRCR5YQLSNG7NQ46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Saliency Prediction in the Deep Learning Era: Successes, Limitations, and Future Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Borji","submitted_at":"2018-10-08T21:50:27Z","abstract_excerpt":"Visual saliency models have enjoyed a big leap in performance in recent years, thanks to advances in deep learning and large scale annotated data. Despite enormous effort and huge breakthroughs, however, models still fall short in reaching human-level accuracy. In this work, I explore the landscape of the field emphasizing on new deep saliency models, benchmarks, and datasets. A large number of image and video saliency models are reviewed and compared over two image benchmarks and two large scale video datasets. Further, I identify factors that contribute to the gap between models and humans a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03716","kind":"arxiv","version":3},"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":"2026-05-17T23:45:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yYNc60ORz0Ae/QQpQFX0FEh88d3SGS54uCsiLZexti2P4uv+NTnskIrWoqP3risYPjPgPu3qsxwniqKtUwumCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T14:13:46.832942Z"},"content_sha256":"7862000aa651cf659cdba5a5c2b5000db9d0e3485802ad1c8244662133118d33","schema_version":"1.0","event_id":"sha256:7862000aa651cf659cdba5a5c2b5000db9d0e3485802ad1c8244662133118d33"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YYD6WLOHI3IRCR5YQLSNG7NQ46/bundle.json","state_url":"https://pith.science/pith/YYD6WLOHI3IRCR5YQLSNG7NQ46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YYD6WLOHI3IRCR5YQLSNG7NQ46/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":"2026-06-01T14:13:46Z","links":{"resolver":"https://pith.science/pith/YYD6WLOHI3IRCR5YQLSNG7NQ46","bundle":"https://pith.science/pith/YYD6WLOHI3IRCR5YQLSNG7NQ46/bundle.json","state":"https://pith.science/pith/YYD6WLOHI3IRCR5YQLSNG7NQ46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YYD6WLOHI3IRCR5YQLSNG7NQ46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YYD6WLOHI3IRCR5YQLSNG7NQ46","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":"4b6131c2fb7d54b457d5155b46e301fb1fe6c33292fb85766534deaa295ee42b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-08T21:50:27Z","title_canon_sha256":"e21aba01337e5293fe59187279012c56cb9cea50114cc19ade989e991bd040c4"},"schema_version":"1.0","source":{"id":"1810.03716","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03716","created_at":"2026-05-17T23:45:09Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03716v3","created_at":"2026-05-17T23:45:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03716","created_at":"2026-05-17T23:45:09Z"},{"alias_kind":"pith_short_12","alias_value":"YYD6WLOHI3IR","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YYD6WLOHI3IRCR5Y","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YYD6WLOH","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:7862000aa651cf659cdba5a5c2b5000db9d0e3485802ad1c8244662133118d33","target":"graph","created_at":"2026-05-17T23:45:09Z","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 models have enjoyed a big leap in performance in recent years, thanks to advances in deep learning and large scale annotated data. Despite enormous effort and huge breakthroughs, however, models still fall short in reaching human-level accuracy. In this work, I explore the landscape of the field emphasizing on new deep saliency models, benchmarks, and datasets. A large number of image and video saliency models are reviewed and compared over two image benchmarks and two large scale video datasets. Further, I identify factors that contribute to the gap between models and humans a","authors_text":"Ali Borji","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-08T21:50:27Z","title":"Saliency Prediction in the Deep Learning Era: Successes, Limitations, and Future Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03716","kind":"arxiv","version":3},"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":"sha256:8468b8a76436688b93e61ce1e74bb5fcbe36b6fb6c252697354c4a15a1c203aa","target":"record","created_at":"2026-05-17T23:45:09Z","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":"4b6131c2fb7d54b457d5155b46e301fb1fe6c33292fb85766534deaa295ee42b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-08T21:50:27Z","title_canon_sha256":"e21aba01337e5293fe59187279012c56cb9cea50114cc19ade989e991bd040c4"},"schema_version":"1.0","source":{"id":"1810.03716","kind":"arxiv","version":3}},"canonical_sha256":"c607eb2dc746d11147b882e4d37db0e7ba5b3074387173329f9fceb0253bd11d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c607eb2dc746d11147b882e4d37db0e7ba5b3074387173329f9fceb0253bd11d","first_computed_at":"2026-05-17T23:45:09.547375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:09.547375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gKlzyFxz5dZBKHhUbfqwFJf+9my4lWGrDY5uUWs2bjnLv43L5tYJPWVROfHz2cckutY8xrJs01ZH8jB6A5BIAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:09.548206Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.03716","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8468b8a76436688b93e61ce1e74bb5fcbe36b6fb6c252697354c4a15a1c203aa","sha256:7862000aa651cf659cdba5a5c2b5000db9d0e3485802ad1c8244662133118d33"],"state_sha256":"a567de136e66efbd59a8baee834698c1cf6ee4bb9eaa83d0a11f71d25e52077a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"50c9XC2f+51at/qTHvMOmPZA0Ay7NZc70qEF21xd5bti5fApNW2ZWqPNrEt0TbEKyYsYzPjmIdnpU5GsSoi4DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T14:13:46.835248Z","bundle_sha256":"8ff78357f368329156bae19b43bb93dc033ccf2aaa6196474cb2b09316925fbd"}}