{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GCNURVTWQXFXXBQQXMEVFQ7JSO","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":"1012b6572ef359fe010e51a054851fe565109b68a353e6ef6f5c2263e1743d6e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-08T11:04:34Z","title_canon_sha256":"edad475131cabb825ddf0b9ed0d176986edcd7d4ecffcbd8cc71f03aaef01402"},"schema_version":"1.0","source":{"id":"1812.03299","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.03299","created_at":"2026-07-05T00:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"1812.03299v3","created_at":"2026-07-05T00:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03299","created_at":"2026-07-05T00:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"GCNURVTWQXFX","created_at":"2026-07-05T00:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"GCNURVTWQXFXXBQQ","created_at":"2026-07-05T00:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"GCNURVTW","created_at":"2026-07-05T00:13:29Z"}],"graph_snapshots":[{"event_id":"sha256:eab65626c3a4bb5d13db28ffa66db44a11f69bae554d72fd20339ec2b59c6679","target":"graph","created_at":"2026-07-05T00:13:29Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1812.03299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding, a task to ground (i.e., localize) natural language in images, essentially requires composite visual reasoning. However, existing methods over-simplify the composite nature of language into a monolithic sentence embedding or a coarse composition of subject-predicate-object triplet. In this paper, we propose to ground natural language in an intuitive, explainable, and composite fashion as it should be. In particular, we develop a novel modular network called Neural Module Tree network (NMTree) that regularizes the visual grounding along the dependency parsing tree of the senten","authors_text":"Daqing Liu, Feng Wu, Hanwang Zhang, Zheng-Jun Zha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-08T11:04:34Z","title":"Learning to Assemble Neural Module Tree Networks for Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03299","kind":"arxiv","version":3},"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:e202be9b28c3c26879096b2844dbe7ccc04289f4ad29b1258aae5695ce1ea86c","target":"record","created_at":"2026-07-05T00:13:29Z","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":"1012b6572ef359fe010e51a054851fe565109b68a353e6ef6f5c2263e1743d6e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-08T11:04:34Z","title_canon_sha256":"edad475131cabb825ddf0b9ed0d176986edcd7d4ecffcbd8cc71f03aaef01402"},"schema_version":"1.0","source":{"id":"1812.03299","kind":"arxiv","version":3}},"canonical_sha256":"309b48d67685cb7b8610bb0952c3e9938bb0fc6876cfb983876cc2f5d6d774c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"309b48d67685cb7b8610bb0952c3e9938bb0fc6876cfb983876cc2f5d6d774c1","first_computed_at":"2026-07-05T00:13:29.053151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:13:29.053151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OrdsDMBF3J9wnWA6QGRaoLX3mZxmbwTe64aQIhmISGAhxzJP15jI+DfMSqMVTc0EeUiYSh4iHGYWLs+OJmIrDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:13:29.053582Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.03299","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e202be9b28c3c26879096b2844dbe7ccc04289f4ad29b1258aae5695ce1ea86c","sha256:eab65626c3a4bb5d13db28ffa66db44a11f69bae554d72fd20339ec2b59c6679"],"state_sha256":"53d779442018382cffe2715a6813b2e9f2e230fe774be9722b9d6ee73844e801"}