{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XBOYIXUBP4CBNP5U4P37DO4WNN","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":"0ce31d6b3e052ea7f99aff19e8d7870ba84b4d855a040f1ec5c838bcf46459aa","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-14T18:10:05Z","title_canon_sha256":"33095ad8bbd00e2c08272bf7cfa50c41fca06216bd4fe038ec5351fe77b5a554"},"schema_version":"1.0","source":{"id":"2306.08685","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08685","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08685v2","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08685","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"pith_short_12","alias_value":"XBOYIXUBP4CB","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"pith_short_16","alias_value":"XBOYIXUBP4CBNP5U","created_at":"2026-07-05T09:54:23Z"},{"alias_kind":"pith_short_8","alias_value":"XBOYIXUB","created_at":"2026-07-05T09:54:23Z"}],"graph_snapshots":[{"event_id":"sha256:0aaa54bdfc8ac4726e112e20e30a6912d1017cc56ac9c1c06fdf03b99261a814","target":"graph","created_at":"2026-07-05T09:54:23Z","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/2306.08685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to connect language units to their referents in the physical world, referred to as grounding, is crucial to learning and understanding grounded meanings of words. While humans demonstrate fast mapping in new word learning, it remains unclear whether modern vision-language models can truly represent language with their grounded meanings and how grounding may further bootstrap new word learning. To this end, we introduce Grounded Open Vocabulary Acquisition (GOVA) to examine grounding and bootstrapping in open-world language learning. As an initial attempt, we propose object-oriented","authors_text":"Jiayi Pan, Joyce Chai, Ziqiao Ma","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-14T18:10:05Z","title":"World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08685","kind":"arxiv","version":2},"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":"sha256:0f6dd3e5cdce00a1d79890c3b421da2680bb80ca39d714bd3a93f9212d1ebdd3","target":"record","created_at":"2026-07-05T09:54:23Z","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":"0ce31d6b3e052ea7f99aff19e8d7870ba84b4d855a040f1ec5c838bcf46459aa","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-14T18:10:05Z","title_canon_sha256":"33095ad8bbd00e2c08272bf7cfa50c41fca06216bd4fe038ec5351fe77b5a554"},"schema_version":"1.0","source":{"id":"2306.08685","kind":"arxiv","version":2}},"canonical_sha256":"b85d845e817f0416bfb4e3f7f1bb966b51c8a073cdd438ab83ddd36322726821","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b85d845e817f0416bfb4e3f7f1bb966b51c8a073cdd438ab83ddd36322726821","first_computed_at":"2026-07-05T09:54:23.203646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:23.203646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U5qXaNuONUzMHJfPDmOT2Nw72ZqwS4aIuqzz2OxBj6xBqw276ZD1Ne33nLqjJF7hh9ezYnbDDY0d1Wqp9B5dAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:23.204136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08685","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f6dd3e5cdce00a1d79890c3b421da2680bb80ca39d714bd3a93f9212d1ebdd3","sha256:0aaa54bdfc8ac4726e112e20e30a6912d1017cc56ac9c1c06fdf03b99261a814"],"state_sha256":"24ca815b002a963b51a80fe7f944800fc15c8a21224bebc0d49c51512a568c94"}