{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LWBNC7G22X4GLRK5NX6IXEPW42","short_pith_number":"pith:LWBNC7G2","canonical_record":{"source":{"id":"1803.05753","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-15T14:00:28Z","cross_cats_sorted":[],"title_canon_sha256":"dd5394e6f1267ba273b4904bf31f58477c10444bc7ae0d55aa8d32dd9e860edf","abstract_canon_sha256":"a3a13a0348e8960e7a5959e3dd37645b587875f6f0e71bdd8b4cd5474aab8155"},"schema_version":"1.0"},"canonical_sha256":"5d82d17cdad5f865c55d6dfc8b91f6e6baa6af9f99e56fa7ceac344afa4a0424","source":{"kind":"arxiv","id":"1803.05753","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.05753","created_at":"2026-05-18T00:20:23Z"},{"alias_kind":"arxiv_version","alias_value":"1803.05753v3","created_at":"2026-05-18T00:20:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.05753","created_at":"2026-05-18T00:20:23Z"},{"alias_kind":"pith_short_12","alias_value":"LWBNC7G22X4G","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LWBNC7G22X4GLRK5","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LWBNC7G2","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LWBNC7G22X4GLRK5NX6IXEPW42","target":"record","payload":{"canonical_record":{"source":{"id":"1803.05753","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-15T14:00:28Z","cross_cats_sorted":[],"title_canon_sha256":"dd5394e6f1267ba273b4904bf31f58477c10444bc7ae0d55aa8d32dd9e860edf","abstract_canon_sha256":"a3a13a0348e8960e7a5959e3dd37645b587875f6f0e71bdd8b4cd5474aab8155"},"schema_version":"1.0"},"canonical_sha256":"5d82d17cdad5f865c55d6dfc8b91f6e6baa6af9f99e56fa7ceac344afa4a0424","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:23.770136Z","signature_b64":"5nIx+fafd7tIXnPv78abpQIh5bFWUZR1yJjJsd8u7mGsSebWQZ/1OYjw8RAFlLi6XkfBK7QcA10Lw5w7TPy+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d82d17cdad5f865c55d6dfc8b91f6e6baa6af9f99e56fa7ceac344afa4a0424","last_reissued_at":"2026-05-18T00:20:23.769694Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:23.769694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.05753","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":"2026-05-18T00:20:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qU4Tqf8JLQRJm7h/RF/am6fQ79yD3PsjRxqyKCKXNDqAUtSs0Nph48IaWNJaaIBppeIrVENByFIgbB1Iy7z0CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T18:06:03.662047Z"},"content_sha256":"a31ce4b748ec16f80b334f1c7ec02cd96c98e904a949455d228ba7cabc628363","schema_version":"1.0","event_id":"sha256:a31ce4b748ec16f80b334f1c7ec02cd96c98e904a949455d228ba7cabc628363"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LWBNC7G22X4GLRK5NX6IXEPW42","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Catches the Eye? Visualizing and Understanding Deep Saliency Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Borji, Nicolas Pugeault, Sen He, Yang Mi","submitted_at":"2018-03-15T14:00:28Z","abstract_excerpt":"Deep convolutional neural networks have demonstrated high performances for fixation prediction in recent years. How they achieve this, however, is less explored and they remain to be black box models. Here, we attempt to shed light on the internal structure of deep saliency models and study what features they extract for fixation prediction. Specifically, we use a simple yet powerful architecture, consisting of only one CNN and a single resolution input, combined with a new loss function for pixel-wise fixation prediction during free viewing of natural scenes. We show that our simple method is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.05753","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":"2026-05-18T00:20:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L1N7V8UB8m0lRJrSEvWwKsPVDhMYEXhed6zCfVZSOyXcBubbrSR00li6oNVf9JEcFBpsOGJEgIVOULBk3EFwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T18:06:03.662745Z"},"content_sha256":"1d0557a85919a5ee2b2ce7b14f406d8c3ac6e591dda9233e8ef12028ea58352b","schema_version":"1.0","event_id":"sha256:1d0557a85919a5ee2b2ce7b14f406d8c3ac6e591dda9233e8ef12028ea58352b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LWBNC7G22X4GLRK5NX6IXEPW42/bundle.json","state_url":"https://pith.science/pith/LWBNC7G22X4GLRK5NX6IXEPW42/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LWBNC7G22X4GLRK5NX6IXEPW42/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":"2026-05-26T18:06:03Z","links":{"resolver":"https://pith.science/pith/LWBNC7G22X4GLRK5NX6IXEPW42","bundle":"https://pith.science/pith/LWBNC7G22X4GLRK5NX6IXEPW42/bundle.json","state":"https://pith.science/pith/LWBNC7G22X4GLRK5NX6IXEPW42/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LWBNC7G22X4GLRK5NX6IXEPW42/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LWBNC7G22X4GLRK5NX6IXEPW42","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":"a3a13a0348e8960e7a5959e3dd37645b587875f6f0e71bdd8b4cd5474aab8155","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-15T14:00:28Z","title_canon_sha256":"dd5394e6f1267ba273b4904bf31f58477c10444bc7ae0d55aa8d32dd9e860edf"},"schema_version":"1.0","source":{"id":"1803.05753","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.05753","created_at":"2026-05-18T00:20:23Z"},{"alias_kind":"arxiv_version","alias_value":"1803.05753v3","created_at":"2026-05-18T00:20:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.05753","created_at":"2026-05-18T00:20:23Z"},{"alias_kind":"pith_short_12","alias_value":"LWBNC7G22X4G","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LWBNC7G22X4GLRK5","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LWBNC7G2","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:1d0557a85919a5ee2b2ce7b14f406d8c3ac6e591dda9233e8ef12028ea58352b","target":"graph","created_at":"2026-05-18T00:20:23Z","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":"Deep convolutional neural networks have demonstrated high performances for fixation prediction in recent years. How they achieve this, however, is less explored and they remain to be black box models. Here, we attempt to shed light on the internal structure of deep saliency models and study what features they extract for fixation prediction. Specifically, we use a simple yet powerful architecture, consisting of only one CNN and a single resolution input, combined with a new loss function for pixel-wise fixation prediction during free viewing of natural scenes. We show that our simple method is","authors_text":"Ali Borji, Nicolas Pugeault, Sen He, Yang Mi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-15T14:00:28Z","title":"What Catches the Eye? Visualizing and Understanding Deep Saliency Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.05753","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:a31ce4b748ec16f80b334f1c7ec02cd96c98e904a949455d228ba7cabc628363","target":"record","created_at":"2026-05-18T00:20:23Z","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":"a3a13a0348e8960e7a5959e3dd37645b587875f6f0e71bdd8b4cd5474aab8155","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2018-03-15T14:00:28Z","title_canon_sha256":"dd5394e6f1267ba273b4904bf31f58477c10444bc7ae0d55aa8d32dd9e860edf"},"schema_version":"1.0","source":{"id":"1803.05753","kind":"arxiv","version":3}},"canonical_sha256":"5d82d17cdad5f865c55d6dfc8b91f6e6baa6af9f99e56fa7ceac344afa4a0424","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d82d17cdad5f865c55d6dfc8b91f6e6baa6af9f99e56fa7ceac344afa4a0424","first_computed_at":"2026-05-18T00:20:23.769694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:23.769694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5nIx+fafd7tIXnPv78abpQIh5bFWUZR1yJjJsd8u7mGsSebWQZ/1OYjw8RAFlLi6XkfBK7QcA10Lw5w7TPy+AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:23.770136Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.05753","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a31ce4b748ec16f80b334f1c7ec02cd96c98e904a949455d228ba7cabc628363","sha256:1d0557a85919a5ee2b2ce7b14f406d8c3ac6e591dda9233e8ef12028ea58352b"],"state_sha256":"82842fa12e594ff13db88fa480d579a3ac40dcaaaa04abcb1c0d71171a8be54b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cAoG3/55rZQWncMDZI90RV0ZJWlD9oO/5arK8DgU5tPlelcz+TPqvqBsCEY2LpLpP3JFWwGOUW3d8kw4wbDsCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T18:06:03.666239Z","bundle_sha256":"7057aadb91824eb5d6972f09824721992648c3912f39545e4ee3464fee3bae0a"}}