{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5X4SCC2VFEAK3N37JA6DDNICFI","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":"4bc3f6272c9b5c3ddc00153a181e457023482dc65c912cbc19a34eaba5b05e97","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2018-09-06T12:26:24Z","title_canon_sha256":"5a39d64b6df8955d45d82b4363d5fc83cbcabfbee2aa5cfc9c43cd6f7189419b"},"schema_version":"1.0","source":{"id":"1809.01943","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.01943","created_at":"2026-05-18T00:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"1809.01943v1","created_at":"2026-05-18T00:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01943","created_at":"2026-05-18T00:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"5X4SCC2VFEAK","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5X4SCC2VFEAK3N37","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5X4SCC2V","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:097176a90a7077a1dab9429b0ce1a368ab25c101642ec7c2766927faae342019","target":"graph","created_at":"2026-05-18T00:06:21Z","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 reasoning is a special visual question answering problem that is multi-step and compositional by nature, and also requires intensive text-vision interactions. We propose CMM: Cascaded Mutual Modulation as a novel end-to-end visual reasoning model. CMM includes a multi-step comprehension process for both question and image. In each step, we use a Feature-wise Linear Modulation (FiLM) technique to enable textual/visual pipeline to mutually control each other. Experiments show that CMM significantly outperforms most related models, and reach state-of-the-arts on two visual reasoning benchm","authors_text":"Bo Xu, Feng Wang, Jiaming Xu, Yiqun Yao","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2018-09-06T12:26:24Z","title":"Cascaded Mutual Modulation for Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01943","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:b70ce1362a07c5e564af577be1c91500220959a4bfc0733716f57fe60978360d","target":"record","created_at":"2026-05-18T00:06:21Z","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":"4bc3f6272c9b5c3ddc00153a181e457023482dc65c912cbc19a34eaba5b05e97","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2018-09-06T12:26:24Z","title_canon_sha256":"5a39d64b6df8955d45d82b4363d5fc83cbcabfbee2aa5cfc9c43cd6f7189419b"},"schema_version":"1.0","source":{"id":"1809.01943","kind":"arxiv","version":1}},"canonical_sha256":"edf9210b552900adb77f483c31b5022a26f0b7a69e0aa67f17933e5fbcea255f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edf9210b552900adb77f483c31b5022a26f0b7a69e0aa67f17933e5fbcea255f","first_computed_at":"2026-05-18T00:06:21.632006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:21.632006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q+wuK+Ju37Q3+NVj384hxjQkR34KrKu4DyAu4XzAMcbtDpk2QV3iPoReJ1w7quBRyadjYHIIk4VHvCbipj1RBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:21.632376Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.01943","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b70ce1362a07c5e564af577be1c91500220959a4bfc0733716f57fe60978360d","sha256:097176a90a7077a1dab9429b0ce1a368ab25c101642ec7c2766927faae342019"],"state_sha256":"1a8abdd76cc0ce3d38c8ccefbe79c23a92b00f507f248a062acfffeedd531a95"}