{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:KXOMQHFRFCNVB5MFNH5JRQQOPC","short_pith_number":"pith:KXOMQHFR","canonical_record":{"source":{"id":"1612.07360","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-21T22:02:34Z","cross_cats_sorted":[],"title_canon_sha256":"60de6ab1beb463202ac40a375d20f6314c2815d6c8ce38743288bf11ef4b226b","abstract_canon_sha256":"b2e378d40f7d66649e715619e6ac070329bdbd3d5077782c72d5175918a5a081"},"schema_version":"1.0"},"canonical_sha256":"55dcc81cb1289b50f58569fa98c20e788f65bd2053e3e787a3836a4596ffc8ce","source":{"kind":"arxiv","id":"1612.07360","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.07360","created_at":"2026-05-18T00:35:43Z"},{"alias_kind":"arxiv_version","alias_value":"1612.07360v2","created_at":"2026-05-18T00:35:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.07360","created_at":"2026-05-18T00:35:43Z"},{"alias_kind":"pith_short_12","alias_value":"KXOMQHFRFCNV","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"KXOMQHFRFCNVB5MF","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"KXOMQHFR","created_at":"2026-05-18T12:30:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:KXOMQHFRFCNVB5MFNH5JRQQOPC","target":"record","payload":{"canonical_record":{"source":{"id":"1612.07360","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-21T22:02:34Z","cross_cats_sorted":[],"title_canon_sha256":"60de6ab1beb463202ac40a375d20f6314c2815d6c8ce38743288bf11ef4b226b","abstract_canon_sha256":"b2e378d40f7d66649e715619e6ac070329bdbd3d5077782c72d5175918a5a081"},"schema_version":"1.0"},"canonical_sha256":"55dcc81cb1289b50f58569fa98c20e788f65bd2053e3e787a3836a4596ffc8ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:43.785625Z","signature_b64":"zdzdUkEckogzv1jgfji4dKfuCLvwvBMGPY4+Phpds69oV5W4RRgSciOVsGnA+yi2Cx6jlNiolpFDtR2iLwitBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55dcc81cb1289b50f58569fa98c20e788f65bd2053e3e787a3836a4596ffc8ce","last_reissued_at":"2026-05-18T00:35:43.785055Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:43.785055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.07360","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":"2026-05-18T00:35:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R9oAnKRwgil6DzdGwZUGYnfhiVL10+hSeDxXRErJvJ8W/9a1v0bHU+Ot7kysZ0cE1QAjf2zPc4+Ers8M0f2qAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:49:28.926573Z"},"content_sha256":"4f44bd027bd9c49503c5b34de02cd797cadb7d94d956be59da1b853493e8cacf","schema_version":"1.0","event_id":"sha256:4f44bd027bd9c49503c5b34de02cd797cadb7d94d956be59da1b853493e8cacf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:KXOMQHFRFCNVB5MFNH5JRQQOPC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Top-down Visual Saliency Guided by Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abir Das, Jianming Zhang, Kate Saenko, Vasili Ramanishka","submitted_at":"2016-12-21T22:02:34Z","abstract_excerpt":"Neural image/video captioning models can generate accurate descriptions, but their internal process of mapping regions to words is a black box and therefore difficult to explain. Top-down neural saliency methods can find important regions given a high-level semantic task such as object classification, but cannot use a natural language sentence as the top-down input for the task. In this paper, we propose Caption-Guided Visual Saliency to expose the region-to-word mapping in modern encoder-decoder networks and demonstrate that it is learned implicitly from caption training data, without any pix"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.07360","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":"2026-05-18T00:35:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8xF6iJwjd3lWyspTRImfwBlvXws+YBkO+NUU2VyIcN8YNSg/ssqnepk9dSm4bXtvob8CYOzljAd3fGzNvUOJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:49:28.927007Z"},"content_sha256":"cb93bd91ea6fa035d86f7e52c4201ca5ff9e3201d5286fefebecdd13406262f7","schema_version":"1.0","event_id":"sha256:cb93bd91ea6fa035d86f7e52c4201ca5ff9e3201d5286fefebecdd13406262f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KXOMQHFRFCNVB5MFNH5JRQQOPC/bundle.json","state_url":"https://pith.science/pith/KXOMQHFRFCNVB5MFNH5JRQQOPC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KXOMQHFRFCNVB5MFNH5JRQQOPC/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":"2026-05-25T15:49:28Z","links":{"resolver":"https://pith.science/pith/KXOMQHFRFCNVB5MFNH5JRQQOPC","bundle":"https://pith.science/pith/KXOMQHFRFCNVB5MFNH5JRQQOPC/bundle.json","state":"https://pith.science/pith/KXOMQHFRFCNVB5MFNH5JRQQOPC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KXOMQHFRFCNVB5MFNH5JRQQOPC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:KXOMQHFRFCNVB5MFNH5JRQQOPC","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":"b2e378d40f7d66649e715619e6ac070329bdbd3d5077782c72d5175918a5a081","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-21T22:02:34Z","title_canon_sha256":"60de6ab1beb463202ac40a375d20f6314c2815d6c8ce38743288bf11ef4b226b"},"schema_version":"1.0","source":{"id":"1612.07360","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.07360","created_at":"2026-05-18T00:35:43Z"},{"alias_kind":"arxiv_version","alias_value":"1612.07360v2","created_at":"2026-05-18T00:35:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.07360","created_at":"2026-05-18T00:35:43Z"},{"alias_kind":"pith_short_12","alias_value":"KXOMQHFRFCNV","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"KXOMQHFRFCNVB5MF","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"KXOMQHFR","created_at":"2026-05-18T12:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:cb93bd91ea6fa035d86f7e52c4201ca5ff9e3201d5286fefebecdd13406262f7","target":"graph","created_at":"2026-05-18T00:35:43Z","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":"Neural image/video captioning models can generate accurate descriptions, but their internal process of mapping regions to words is a black box and therefore difficult to explain. Top-down neural saliency methods can find important regions given a high-level semantic task such as object classification, but cannot use a natural language sentence as the top-down input for the task. In this paper, we propose Caption-Guided Visual Saliency to expose the region-to-word mapping in modern encoder-decoder networks and demonstrate that it is learned implicitly from caption training data, without any pix","authors_text":"Abir Das, Jianming Zhang, Kate Saenko, Vasili Ramanishka","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-21T22:02:34Z","title":"Top-down Visual Saliency Guided by Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.07360","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":"sha256:4f44bd027bd9c49503c5b34de02cd797cadb7d94d956be59da1b853493e8cacf","target":"record","created_at":"2026-05-18T00:35:43Z","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":"b2e378d40f7d66649e715619e6ac070329bdbd3d5077782c72d5175918a5a081","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-21T22:02:34Z","title_canon_sha256":"60de6ab1beb463202ac40a375d20f6314c2815d6c8ce38743288bf11ef4b226b"},"schema_version":"1.0","source":{"id":"1612.07360","kind":"arxiv","version":2}},"canonical_sha256":"55dcc81cb1289b50f58569fa98c20e788f65bd2053e3e787a3836a4596ffc8ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55dcc81cb1289b50f58569fa98c20e788f65bd2053e3e787a3836a4596ffc8ce","first_computed_at":"2026-05-18T00:35:43.785055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:43.785055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zdzdUkEckogzv1jgfji4dKfuCLvwvBMGPY4+Phpds69oV5W4RRgSciOVsGnA+yi2Cx6jlNiolpFDtR2iLwitBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:43.785625Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.07360","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f44bd027bd9c49503c5b34de02cd797cadb7d94d956be59da1b853493e8cacf","sha256:cb93bd91ea6fa035d86f7e52c4201ca5ff9e3201d5286fefebecdd13406262f7"],"state_sha256":"c0fa8e7f76f81526ac8d8fc0159c2d134255c77cc74fb8516e01082db6d65666"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0dRjvm2wtqz+ckIJeUKqt+/pI42ZwmTCBuGSexlEnWbQ695W+rpkkTl5J+Dfj7wvF+IxrasLzGrH3DIl0Ki0Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:49:28.930656Z","bundle_sha256":"3fb038a662a76cfe1e29051d1ff32b4cf20d847360baa07d0a5c0b5698c0f78a"}}