{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QRAWXG2WGG5F7S3YYG54DLF3FH","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":"de3b4c57fdc1fad5140fb39619905ca72f20d8e96883e88288e26867431b39a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-18T07:03:19Z","title_canon_sha256":"a1140926b641137461a8e126523a598464a7781d8f67c04ac571e4449a869439"},"schema_version":"1.0","source":{"id":"1904.08608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.08608","created_at":"2026-05-17T23:48:13Z"},{"alias_kind":"arxiv_version","alias_value":"1904.08608v1","created_at":"2026-05-17T23:48:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08608","created_at":"2026-05-17T23:48:13Z"},{"alias_kind":"pith_short_12","alias_value":"QRAWXG2WGG5F","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QRAWXG2WGG5F7S3Y","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QRAWXG2W","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:9f5e1966a70ed120ff1cb425e49fb8b4eccb50325a7cf74c48284c1093a6c53c","target":"graph","created_at":"2026-05-17T23:48:13Z","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 do not speak word by word from scratch; our brain quickly structures a pattern like \\textsc{sth do sth at someplace} and then fill in the detailed descriptions. To render existing encoder-decoder image captioners such human-like reasoning, we propose a novel framework: learning to Collocate Neural Modules (CNM), to generate the `inner pattern' connecting visual encoder and language decoder. Unlike the widely-used neural module networks in visual Q\\&A, where the language (ie, question) is fully observable, CNM for captioning is more challenging as the language is being generated and thus is ","authors_text":"Hanwang Zhang, Jianfei Cai, Xu Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-18T07:03:19Z","title":"Learning to Collocate Neural Modules for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08608","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:dd387224f0b834a61bd902ba758e28fc16f07a02a7d35ff52b90e56f534f8619","target":"record","created_at":"2026-05-17T23:48:13Z","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":"de3b4c57fdc1fad5140fb39619905ca72f20d8e96883e88288e26867431b39a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-18T07:03:19Z","title_canon_sha256":"a1140926b641137461a8e126523a598464a7781d8f67c04ac571e4449a869439"},"schema_version":"1.0","source":{"id":"1904.08608","kind":"arxiv","version":1}},"canonical_sha256":"84416b9b5631ba5fcb78c1bbc1acbb29ea443c8fc7404331d5f3e9abe403c688","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84416b9b5631ba5fcb78c1bbc1acbb29ea443c8fc7404331d5f3e9abe403c688","first_computed_at":"2026-05-17T23:48:13.728745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:13.728745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r6JsYrrrOjUCkd3s3DangeeG+kSWTbYXOPlEaZUG8I0QCOlyL7KjZI1I4U53+l3qgHlSBab/i/tktn3Wps3vDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:13.729339Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.08608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd387224f0b834a61bd902ba758e28fc16f07a02a7d35ff52b90e56f534f8619","sha256:9f5e1966a70ed120ff1cb425e49fb8b4eccb50325a7cf74c48284c1093a6c53c"],"state_sha256":"39d6634ee3636803803a066402a535cffcb054df61aa4d3c1c4c693e927ab4de"}