{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:BSUHK4YGNQ7MCFP463GMFZWU7C","short_pith_number":"pith:BSUHK4YG","canonical_record":{"source":{"id":"1611.05594","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-17T07:39:46Z","cross_cats_sorted":[],"title_canon_sha256":"ba8606d3eb8a3bf3a1f7ea9aa141f2de1215d8d8a6b7bb56ad604c77e0c372be","abstract_canon_sha256":"e1927ce4010486f2428a31bda6de46f5acb2591d0c5e6d4962c32d3936440ed6"},"schema_version":"1.0"},"canonical_sha256":"0ca87573066c3ec115fcf6ccc2e6d4f8bc2a757d97c5d01d72f714e6b03a010c","source":{"kind":"arxiv","id":"1611.05594","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.05594","created_at":"2026-05-18T00:46:31Z"},{"alias_kind":"arxiv_version","alias_value":"1611.05594v2","created_at":"2026-05-18T00:46:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05594","created_at":"2026-05-18T00:46:31Z"},{"alias_kind":"pith_short_12","alias_value":"BSUHK4YGNQ7M","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"BSUHK4YGNQ7MCFP4","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"BSUHK4YG","created_at":"2026-05-18T12:30:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:BSUHK4YGNQ7MCFP463GMFZWU7C","target":"record","payload":{"canonical_record":{"source":{"id":"1611.05594","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-17T07:39:46Z","cross_cats_sorted":[],"title_canon_sha256":"ba8606d3eb8a3bf3a1f7ea9aa141f2de1215d8d8a6b7bb56ad604c77e0c372be","abstract_canon_sha256":"e1927ce4010486f2428a31bda6de46f5acb2591d0c5e6d4962c32d3936440ed6"},"schema_version":"1.0"},"canonical_sha256":"0ca87573066c3ec115fcf6ccc2e6d4f8bc2a757d97c5d01d72f714e6b03a010c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:31.591703Z","signature_b64":"Ojwsve2u8km2TPZfNn8hvz+X1g6NwlVWSp0q1pWH1bGfRxgSdDLvUOABPMCKuvJgjYLTt8z1M+jPGqFb/4m+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ca87573066c3ec115fcf6ccc2e6d4f8bc2a757d97c5d01d72f714e6b03a010c","last_reissued_at":"2026-05-18T00:46:31.591024Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:31.591024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.05594","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":"2026-05-18T00:46:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2mK2Zw4TAll1LaKP07izQof+toZelmGgdzQeE4bD6NvBaqZXk+Bh0TxrsgI53r5YFKmicb1rvZDnMo3caYlEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T05:54:01.793941Z"},"content_sha256":"9ab653fe7cb0ee3509640a51f5d70a55fde2fcdb168e0b36985edc26292f0324","schema_version":"1.0","event_id":"sha256:9ab653fe7cb0ee3509640a51f5d70a55fde2fcdb168e0b36985edc26292f0324"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:BSUHK4YGNQ7MCFP463GMFZWU7C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Jian Shao, Jun Xiao, Liqiang Nie, Long Chen, Tat-Seng Chua, Wei Liu","submitted_at":"2016-11-17T07:39:46Z","abstract_excerpt":"Visual attention has been successfully applied in structural prediction tasks such as visual captioning and question answering. Existing visual attention models are generally spatial, i.e., the attention is modeled as spatial probabilities that re-weight the last conv-layer feature map of a CNN encoding an input image. However, we argue that such spatial attention does not necessarily conform to the attention mechanism --- a dynamic feature extractor that combines contextual fixations over time, as CNN features are naturally spatial, channel-wise and multi-layer. In this paper, we introduce a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05594","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":"2026-05-18T00:46:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m+ZIQk69flmhbT7EnuduvFb5GTG34osGdEoaG/FzpJZ2m+M7Dmukv1Q7e//ShgikzKjcL/8vX60MV6ZH2MS5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T05:54:01.794625Z"},"content_sha256":"aa668d20755787f49ca9fb3747e4fdfe2d76a1c517817b868886f8f6e535d517","schema_version":"1.0","event_id":"sha256:aa668d20755787f49ca9fb3747e4fdfe2d76a1c517817b868886f8f6e535d517"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BSUHK4YGNQ7MCFP463GMFZWU7C/bundle.json","state_url":"https://pith.science/pith/BSUHK4YGNQ7MCFP463GMFZWU7C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BSUHK4YGNQ7MCFP463GMFZWU7C/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":"2026-06-08T05:54:01Z","links":{"resolver":"https://pith.science/pith/BSUHK4YGNQ7MCFP463GMFZWU7C","bundle":"https://pith.science/pith/BSUHK4YGNQ7MCFP463GMFZWU7C/bundle.json","state":"https://pith.science/pith/BSUHK4YGNQ7MCFP463GMFZWU7C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BSUHK4YGNQ7MCFP463GMFZWU7C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:BSUHK4YGNQ7MCFP463GMFZWU7C","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":"e1927ce4010486f2428a31bda6de46f5acb2591d0c5e6d4962c32d3936440ed6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-17T07:39:46Z","title_canon_sha256":"ba8606d3eb8a3bf3a1f7ea9aa141f2de1215d8d8a6b7bb56ad604c77e0c372be"},"schema_version":"1.0","source":{"id":"1611.05594","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.05594","created_at":"2026-05-18T00:46:31Z"},{"alias_kind":"arxiv_version","alias_value":"1611.05594v2","created_at":"2026-05-18T00:46:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05594","created_at":"2026-05-18T00:46:31Z"},{"alias_kind":"pith_short_12","alias_value":"BSUHK4YGNQ7M","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"BSUHK4YGNQ7MCFP4","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"BSUHK4YG","created_at":"2026-05-18T12:30:09Z"}],"graph_snapshots":[{"event_id":"sha256:aa668d20755787f49ca9fb3747e4fdfe2d76a1c517817b868886f8f6e535d517","target":"graph","created_at":"2026-05-18T00:46:31Z","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 attention has been successfully applied in structural prediction tasks such as visual captioning and question answering. Existing visual attention models are generally spatial, i.e., the attention is modeled as spatial probabilities that re-weight the last conv-layer feature map of a CNN encoding an input image. However, we argue that such spatial attention does not necessarily conform to the attention mechanism --- a dynamic feature extractor that combines contextual fixations over time, as CNN features are naturally spatial, channel-wise and multi-layer. In this paper, we introduce a ","authors_text":"Hanwang Zhang, Jian Shao, Jun Xiao, Liqiang Nie, Long Chen, Tat-Seng Chua, Wei Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-17T07:39:46Z","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05594","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":"sha256:9ab653fe7cb0ee3509640a51f5d70a55fde2fcdb168e0b36985edc26292f0324","target":"record","created_at":"2026-05-18T00:46:31Z","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":"e1927ce4010486f2428a31bda6de46f5acb2591d0c5e6d4962c32d3936440ed6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-17T07:39:46Z","title_canon_sha256":"ba8606d3eb8a3bf3a1f7ea9aa141f2de1215d8d8a6b7bb56ad604c77e0c372be"},"schema_version":"1.0","source":{"id":"1611.05594","kind":"arxiv","version":2}},"canonical_sha256":"0ca87573066c3ec115fcf6ccc2e6d4f8bc2a757d97c5d01d72f714e6b03a010c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ca87573066c3ec115fcf6ccc2e6d4f8bc2a757d97c5d01d72f714e6b03a010c","first_computed_at":"2026-05-18T00:46:31.591024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:31.591024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ojwsve2u8km2TPZfNn8hvz+X1g6NwlVWSp0q1pWH1bGfRxgSdDLvUOABPMCKuvJgjYLTt8z1M+jPGqFb/4m+Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:31.591703Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.05594","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ab653fe7cb0ee3509640a51f5d70a55fde2fcdb168e0b36985edc26292f0324","sha256:aa668d20755787f49ca9fb3747e4fdfe2d76a1c517817b868886f8f6e535d517"],"state_sha256":"827f79c92fb4182c47eb3cffda8155b84915a5907aa10e8d7c64dcb1c3ddb030"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cWwEQ3s1GiRb36OXU/ca4B76C4RR5AHKTLa5PiPGXH1VHbESem7VARvCHlZEuk0WzcAeqiNZKlBn5Mtpt8KJCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T05:54:01.798154Z","bundle_sha256":"c0e8a2f2811957ca757383decc86a754c96ba8953ebebe737c80bb97797404d3"}}