{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:QRJAJUUNWR2HZYEYLORR5OSMAQ","short_pith_number":"pith:QRJAJUUN","canonical_record":{"source":{"id":"1612.05753","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-17T13:29:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0f9e65623edc8c55de50d96ab54d6b63a712d158563ce291438ab0b85fd849fb","abstract_canon_sha256":"f6cec200d12826400c6af607d38f1133873ee9d632329b90255b39d6a6929dc5"},"schema_version":"1.0"},"canonical_sha256":"845204d28db4747ce0985ba31eba4c0425968a5f1db9a6ee9b429f98877dc38f","source":{"kind":"arxiv","id":"1612.05753","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.05753","created_at":"2026-05-18T00:50:28Z"},{"alias_kind":"arxiv_version","alias_value":"1612.05753v2","created_at":"2026-05-18T00:50:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.05753","created_at":"2026-05-18T00:50:28Z"},{"alias_kind":"pith_short_12","alias_value":"QRJAJUUNWR2H","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"QRJAJUUNWR2HZYEY","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"QRJAJUUN","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:QRJAJUUNWR2HZYEYLORR5OSMAQ","target":"record","payload":{"canonical_record":{"source":{"id":"1612.05753","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-17T13:29:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0f9e65623edc8c55de50d96ab54d6b63a712d158563ce291438ab0b85fd849fb","abstract_canon_sha256":"f6cec200d12826400c6af607d38f1133873ee9d632329b90255b39d6a6929dc5"},"schema_version":"1.0"},"canonical_sha256":"845204d28db4747ce0985ba31eba4c0425968a5f1db9a6ee9b429f98877dc38f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:28.811194Z","signature_b64":"R5oUzEWmMZJdQMN6WfsPOrwx9o81nuECMYXoCdEkx6uWWnLhWgF2ZsTYxvRoJ7qXglzjkcJmxNkinnKGto1LBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"845204d28db4747ce0985ba31eba4c0425968a5f1db9a6ee9b429f98877dc38f","last_reissued_at":"2026-05-18T00:50:28.810547Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:28.810547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.05753","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":"2026-05-18T00:50:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ysERwX1QOsk8qwb1gJ+zVwVK3X7YcnavlhvBFhuFnvJ9STys/qL19LjVCUrLM/NkhyjjpusQwHYrwLr+cRyDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:07:33.774161Z"},"content_sha256":"08a9dc410b7bd25970e398ddfa5b64954c7bfd1c0a68a7c085cf27e617c23a0f","schema_version":"1.0","event_id":"sha256:08a9dc410b7bd25970e398ddfa5b64954c7bfd1c0a68a7c085cf27e617c23a0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:QRJAJUUNWR2HZYEYLORR5OSMAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to predict where to look in interactive environments using deep recurrent q-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Borji, Enda Howley, Michael Schukat, Nasser Mozayani, Sajad Mousavi","submitted_at":"2016-12-17T13:29:59Z","abstract_excerpt":"Bottom-Up (BU) saliency models do not perform well in complex interactive environments where humans are actively engaged in tasks (e.g., sandwich making and playing the video games). In this paper, we leverage Reinforcement Learning (RL) to highlight task-relevant locations of input frames. We propose a soft attention mechanism combined with the Deep Q-Network (DQN) model to teach an RL agent how to play a game and where to look by focusing on the most pertinent parts of its visual input. Our evaluations on several Atari 2600 games show that the soft attention based model could predict fixatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.05753","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":"2026-05-18T00:50:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hrpc7RcQM9i8laMFKqH/1t2GwIgFDi1KRytk83t45L40/9WitqREQKqd8NYP4YHfJUa1Aa6PCJMcEuWXsrQ0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T03:07:33.774825Z"},"content_sha256":"1f1e53f24634928fd32bca9ae317b899332aee8d098f3fd76c2f82af4a2975e3","schema_version":"1.0","event_id":"sha256:1f1e53f24634928fd32bca9ae317b899332aee8d098f3fd76c2f82af4a2975e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QRJAJUUNWR2HZYEYLORR5OSMAQ/bundle.json","state_url":"https://pith.science/pith/QRJAJUUNWR2HZYEYLORR5OSMAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QRJAJUUNWR2HZYEYLORR5OSMAQ/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":"2026-08-24T03:07:33Z","links":{"resolver":"https://pith.science/pith/QRJAJUUNWR2HZYEYLORR5OSMAQ","bundle":"https://pith.science/pith/QRJAJUUNWR2HZYEYLORR5OSMAQ/bundle.json","state":"https://pith.science/pith/QRJAJUUNWR2HZYEYLORR5OSMAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QRJAJUUNWR2HZYEYLORR5OSMAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:QRJAJUUNWR2HZYEYLORR5OSMAQ","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":"f6cec200d12826400c6af607d38f1133873ee9d632329b90255b39d6a6929dc5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-17T13:29:59Z","title_canon_sha256":"0f9e65623edc8c55de50d96ab54d6b63a712d158563ce291438ab0b85fd849fb"},"schema_version":"1.0","source":{"id":"1612.05753","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.05753","created_at":"2026-05-18T00:50:28Z"},{"alias_kind":"arxiv_version","alias_value":"1612.05753v2","created_at":"2026-05-18T00:50:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.05753","created_at":"2026-05-18T00:50:28Z"},{"alias_kind":"pith_short_12","alias_value":"QRJAJUUNWR2H","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"QRJAJUUNWR2HZYEY","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"QRJAJUUN","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:1f1e53f24634928fd32bca9ae317b899332aee8d098f3fd76c2f82af4a2975e3","target":"graph","created_at":"2026-05-18T00:50:28Z","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":"Bottom-Up (BU) saliency models do not perform well in complex interactive environments where humans are actively engaged in tasks (e.g., sandwich making and playing the video games). In this paper, we leverage Reinforcement Learning (RL) to highlight task-relevant locations of input frames. We propose a soft attention mechanism combined with the Deep Q-Network (DQN) model to teach an RL agent how to play a game and where to look by focusing on the most pertinent parts of its visual input. Our evaluations on several Atari 2600 games show that the soft attention based model could predict fixatio","authors_text":"Ali Borji, Enda Howley, Michael Schukat, Nasser Mozayani, Sajad Mousavi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-17T13:29:59Z","title":"Learning to predict where to look in interactive environments using deep recurrent q-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.05753","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":"sha256:08a9dc410b7bd25970e398ddfa5b64954c7bfd1c0a68a7c085cf27e617c23a0f","target":"record","created_at":"2026-05-18T00:50:28Z","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":"f6cec200d12826400c6af607d38f1133873ee9d632329b90255b39d6a6929dc5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-17T13:29:59Z","title_canon_sha256":"0f9e65623edc8c55de50d96ab54d6b63a712d158563ce291438ab0b85fd849fb"},"schema_version":"1.0","source":{"id":"1612.05753","kind":"arxiv","version":2}},"canonical_sha256":"845204d28db4747ce0985ba31eba4c0425968a5f1db9a6ee9b429f98877dc38f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"845204d28db4747ce0985ba31eba4c0425968a5f1db9a6ee9b429f98877dc38f","first_computed_at":"2026-05-18T00:50:28.810547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:28.810547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R5oUzEWmMZJdQMN6WfsPOrwx9o81nuECMYXoCdEkx6uWWnLhWgF2ZsTYxvRoJ7qXglzjkcJmxNkinnKGto1LBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:28.811194Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.05753","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08a9dc410b7bd25970e398ddfa5b64954c7bfd1c0a68a7c085cf27e617c23a0f","sha256:1f1e53f24634928fd32bca9ae317b899332aee8d098f3fd76c2f82af4a2975e3"],"state_sha256":"5b7d3bb750cab99bef8ff9cf5d3f070d9fc83d9b8e5fd4744b313c171ee96a09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+dt6I90DZE46u2htEI3S7Qc1WayIIGX74MBTw05B0S4+rvN6dezwwsFSCwgu8b9D7zBHK708M53+2XHaYo+lBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T03:07:33.780161Z","bundle_sha256":"04f06e675b708121d62217de9c77be904860f7ddfa503e5a9f8e8b81007ac17b"}}