{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FW2ZW6H3OS7DTNMMNRDNPYTKSF","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":"ed4c1b2d0b70d0c57dcb1db7bc66e6d8b8b2ef3b717102bfa3673326efd9ab03","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-26T05:26:15Z","title_canon_sha256":"b3536793340bcb704f7125e9a5be2ddda8be1774e0a6b5f14cbc95f89231deff"},"schema_version":"1.0","source":{"id":"1807.09958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.09958","created_at":"2026-05-18T00:08:14Z"},{"alias_kind":"arxiv_version","alias_value":"1807.09958v1","created_at":"2026-05-18T00:08:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09958","created_at":"2026-05-18T00:08:14Z"},{"alias_kind":"pith_short_12","alias_value":"FW2ZW6H3OS7D","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FW2ZW6H3OS7DTNMM","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FW2ZW6H3","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:66ba829d17adfd2d82f73a396cccc07b28dc60067f388000a8a1f1ef941235e7","target":"graph","created_at":"2026-05-18T00:08:14Z","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":"RNNs and their variants have been widely adopted for image captioning. In RNNs, the production of a caption is driven by a sequence of latent states. Existing captioning models usually represent latent states as vectors, taking this practice for granted. We rethink this choice and study an alternative formulation, namely using two-dimensional maps to encode latent states. This is motivated by the curiosity about a question: how the spatial structures in the latent states affect the resultant captions? Our study on MSCOCO and Flickr30k leads to two significant observations. First, the formulati","authors_text":"Bo Dai, Dahua Lin, Deming Ye","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-26T05:26:15Z","title":"Rethinking the Form of Latent States in Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09958","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:e992d490383c7979d35bcc95f5343160fbf67ce45f7c9b2acea5f68da3929709","target":"record","created_at":"2026-05-18T00:08:14Z","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":"ed4c1b2d0b70d0c57dcb1db7bc66e6d8b8b2ef3b717102bfa3673326efd9ab03","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-26T05:26:15Z","title_canon_sha256":"b3536793340bcb704f7125e9a5be2ddda8be1774e0a6b5f14cbc95f89231deff"},"schema_version":"1.0","source":{"id":"1807.09958","kind":"arxiv","version":1}},"canonical_sha256":"2db59b78fb74be39b58c6c46d7e26a916d2b6ac0d2935e3b343ef6762b54d4e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2db59b78fb74be39b58c6c46d7e26a916d2b6ac0d2935e3b343ef6762b54d4e5","first_computed_at":"2026-05-18T00:08:14.360285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:14.360285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MOSJ07NC429GBOWIg2+bx/1//CVMNd96vsM+zvv/2n8FQDuRXkqrnV2DYhooCI/lYM4kT4h9+FbH86EYSIXMAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:14.360648Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.09958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e992d490383c7979d35bcc95f5343160fbf67ce45f7c9b2acea5f68da3929709","sha256:66ba829d17adfd2d82f73a396cccc07b28dc60067f388000a8a1f1ef941235e7"],"state_sha256":"8dd97c76835ffeafde11811df006f79329279731138d80b7be48348a554624d1"}