{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:OJKIETQMUN4W3VTSVSFPFJQ4HM","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":"597fe70620ed743eb3b1d530452cd25a73583d13801eaec48c8353b931a238ba","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-09T08:24:02Z","title_canon_sha256":"5eb20243223bc31a78ea6c4481fc8e97db074110cd040f17f27cc33c24c4a052"},"schema_version":"1.0","source":{"id":"1608.02717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.02717","created_at":"2026-05-18T01:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"1608.02717v1","created_at":"2026-05-18T01:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.02717","created_at":"2026-05-18T01:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"OJKIETQMUN4W","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OJKIETQMUN4W3VTS","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OJKIETQM","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:81099edf92e8d8e9762261ae41baae6c8b3044a58a0aa1b3200a32aca780351d","target":"graph","created_at":"2026-05-18T01:09:33Z","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":"We present Mean Box Pooling, a novel visual representation that pools over CNN representations of a large number, highly overlapping object proposals. We show that such representation together with nCCA, a successful multimodal embedding technique, achieves state-of-the-art performance on the Visual Madlibs task. Moreover, inspired by the nCCA's objective function, we extend classical CNN+LSTM approach to train the network by directly maximizing the similarity between the internal representation of the deep learning architecture and candidate answers. Again, such approach achieves a significan","authors_text":"Ashkan Mokarian, Mario Fritz, Mateusz Malinowski","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-09T08:24:02Z","title":"Mean Box Pooling: A Rich Image Representation and Output Embedding for the Visual Madlibs Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.02717","kind":"arxiv","version":1},"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":"sha256:902c19131a592cda7fb0b1a1887cd8c5cfb7f29e0c4e5ed397091a325638b1ca","target":"record","created_at":"2026-05-18T01:09:33Z","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":"597fe70620ed743eb3b1d530452cd25a73583d13801eaec48c8353b931a238ba","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-09T08:24:02Z","title_canon_sha256":"5eb20243223bc31a78ea6c4481fc8e97db074110cd040f17f27cc33c24c4a052"},"schema_version":"1.0","source":{"id":"1608.02717","kind":"arxiv","version":1}},"canonical_sha256":"7254824e0ca3796dd672ac8af2a61c3b2bfc52231e7044070b579a38543a7d4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7254824e0ca3796dd672ac8af2a61c3b2bfc52231e7044070b579a38543a7d4c","first_computed_at":"2026-05-18T01:09:33.856561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:09:33.856561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VWoLCakKzjp9RhAmWHoF1ereakb0tS911S5MAJUAawvgfcQ8vferyE2EySa0CwS4Q0Q+QZUZE++6MEkq4oPcAg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:09:33.857048Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.02717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:902c19131a592cda7fb0b1a1887cd8c5cfb7f29e0c4e5ed397091a325638b1ca","sha256:81099edf92e8d8e9762261ae41baae6c8b3044a58a0aa1b3200a32aca780351d"],"state_sha256":"d49a561c8813b71cf5668e0e21d4a5030fa3ecd2b402fe32d18115d1026aff2d"}