{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:ZR5MG34ZGDOWUYBOUHUUYTKCEJ","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":"2849b082c2fac306d6db6bfefac2513bd54f30cdb6e0d44c598ccd6f1cd78a58","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-06T16:03:50Z","title_canon_sha256":"6d4ef779a19badef201aa9669fa0f750147007d9beaeda83f56907f29242888a"},"schema_version":"1.0","source":{"id":"1612.01887","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.01887","created_at":"2026-05-18T00:43:01Z"},{"alias_kind":"arxiv_version","alias_value":"1612.01887v2","created_at":"2026-05-18T00:43:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01887","created_at":"2026-05-18T00:43:01Z"},{"alias_kind":"pith_short_12","alias_value":"ZR5MG34ZGDOW","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZR5MG34ZGDOWUYBO","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZR5MG34Z","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:8819e5b9db9499c042cb7b6b5f5ec2a21538985a80c07d9b4d392417f83f8fce","target":"graph","created_at":"2026-05-18T00:43:01Z","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":"Attention-based neural encoder-decoder frameworks have been widely adopted for image captioning. Most methods force visual attention to be active for every generated word. However, the decoder likely requires little to no visual information from the image to predict non-visual words such as \"the\" and \"of\". Other words that may seem visual can often be predicted reliably just from the language model e.g., \"sign\" after \"behind a red stop\" or \"phone\" following \"talking on a cell\". In this paper, we propose a novel adaptive attention model with a visual sentinel. At each time step, our model decid","authors_text":"Caiming Xiong, Devi Parikh, Jiasen Lu, Richard Socher","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-06T16:03:50Z","title":"Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01887","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":"sha256:8a1c54134f7ccc61d2ff16072044fcb4def69d1eecfaa74075460adcda804e95","target":"record","created_at":"2026-05-18T00:43:01Z","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":"2849b082c2fac306d6db6bfefac2513bd54f30cdb6e0d44c598ccd6f1cd78a58","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-06T16:03:50Z","title_canon_sha256":"6d4ef779a19badef201aa9669fa0f750147007d9beaeda83f56907f29242888a"},"schema_version":"1.0","source":{"id":"1612.01887","kind":"arxiv","version":2}},"canonical_sha256":"cc7ac36f9930dd6a602ea1e94c4d42226764dc83ac51031b4ccc8d0998d21657","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc7ac36f9930dd6a602ea1e94c4d42226764dc83ac51031b4ccc8d0998d21657","first_computed_at":"2026-05-18T00:43:01.516733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:01.516733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YhJKBf7dmnhGu4WPPJEfhBDTY/xUFQ1gwywV2BHxkpJaWb6DZguLZAEauLQSlcndKCtlNhqTzf0U6KHW4m/yBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:01.517449Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.01887","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a1c54134f7ccc61d2ff16072044fcb4def69d1eecfaa74075460adcda804e95","sha256:8819e5b9db9499c042cb7b6b5f5ec2a21538985a80c07d9b4d392417f83f8fce"],"state_sha256":"b266fa3612b06c73681360133557563c177565067edc3269d09a36ea56f70914"}