{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:B2P5SWELOEXCJVQ7NLI6FADHKP","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":"824233ffd404b8721ac2a7120958d55e025286ea592e56ca546bfbe95c45ab3f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-24T04:05:08Z","title_canon_sha256":"fdab7f21beb0728ceb0f94d739a3788cd3cf24c7fe5f8bb753a1d79e1eb27942"},"schema_version":"1.0","source":{"id":"2103.12975","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12975","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12975v1","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12975","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"B2P5SWELOEXC","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"pith_short_16","alias_value":"B2P5SWELOEXCJVQ7","created_at":"2026-07-05T02:26:04Z"},{"alias_kind":"pith_short_8","alias_value":"B2P5SWEL","created_at":"2026-07-05T02:26:04Z"}],"graph_snapshots":[{"event_id":"sha256:c7c256cf6930b52b94cebf31c691c9e002d9594b46421b7d0accb08f724ffaa6","target":"graph","created_at":"2026-07-05T02:26:04Z","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/2103.12975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cognitive grammar suggests that the acquisition of language grammar is grounded within visual structures. While grammar is an essential representation of natural language, it also exists ubiquitously in vision to represent the hierarchical part-whole structure. In this work, we study grounded grammar induction of vision and language in a joint learning framework. Specifically, we present VLGrammar, a method that uses compound probabilistic context-free grammars (compound PCFGs) to induce the language grammar and the image grammar simultaneously. We propose a novel contrastive learning framewor","authors_text":"Qing Li, Siyuan Huang, Song-Chun Zhu, Yining Hong","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-24T04:05:08Z","title":"VLGrammar: Grounded Grammar Induction of Vision and Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12975","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":"sha256:19b4916f47e4af903b4129848037251c08e4a86e1e2cea071da98e4457baa8c7","target":"record","created_at":"2026-07-05T02:26:04Z","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":"824233ffd404b8721ac2a7120958d55e025286ea592e56ca546bfbe95c45ab3f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-24T04:05:08Z","title_canon_sha256":"fdab7f21beb0728ceb0f94d739a3788cd3cf24c7fe5f8bb753a1d79e1eb27942"},"schema_version":"1.0","source":{"id":"2103.12975","kind":"arxiv","version":1}},"canonical_sha256":"0e9fd9588b712e24d61f6ad1e2806753d292ff3cdfdcc58d66d5f9e8a5570c67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e9fd9588b712e24d61f6ad1e2806753d292ff3cdfdcc58d66d5f9e8a5570c67","first_computed_at":"2026-07-05T02:26:04.296501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:04.296501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jQIyWO4I9sJwaSArMISKnTuqWkY2RjWRgItXiFh4ZD5wgk4mhekMh7CgVXap1+Zds1sOXv3OVAAtLg9Iy89yBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:04.296944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.12975","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19b4916f47e4af903b4129848037251c08e4a86e1e2cea071da98e4457baa8c7","sha256:c7c256cf6930b52b94cebf31c691c9e002d9594b46421b7d0accb08f724ffaa6"],"state_sha256":"77a88332b5bfa75fe22b990320ade5723f6ab7d10377381e3c5a12a90ffcc5a5"}