{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EPJQOI2H2KZW2FVGQINFJUHX35","short_pith_number":"pith:EPJQOI2H","schema_version":"1.0","canonical_sha256":"23d3072347d2b36d16a6821a54d0f7df730544d137b62619586d1394bd030fe2","source":{"kind":"arxiv","id":"2509.03805","version":1},"attestation_state":"computed","paper":{"title":"Measuring How (Not Just Whether) VLMs Build Common Ground","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anthony Sicilia, Malihe Alikhani, Mert \\.Inan, Saki Imai","submitted_at":"2025-09-04T01:43:49Z","abstract_excerpt":"Large vision language models (VLMs) increasingly claim reasoning skills, yet current benchmarks evaluate them in single-turn or question answering settings. However, grounding is an interactive process in which people gradually develop shared understanding through ongoing communication. We introduce a four-metric suite (grounding efficiency, content alignment, lexical adaptation, and human-likeness) to systematically evaluate VLM performance in interactive grounding contexts. We deploy the suite on 150 self-play sessions of interactive referential games between three proprietary VLMs and compa"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.03805","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-04T01:43:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cab05a47c1fc4e4656d6695a3a234b476ee184d82c10263300e2a2c961f74bd1","abstract_canon_sha256":"e35404ddb07e7c56ccd6b90b4cd3a5ab14516a171ee3bebdca9f1c3d8340fdd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:46.760499Z","signature_b64":"yJzp19AtL866CBOFVQ0S6hOz6pzJoCTP3kc87TvgvjvZMkBW5J1MqVnFwgcNzZsP8A6AKv8YtyYMx/HHvEM6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23d3072347d2b36d16a6821a54d0f7df730544d137b62619586d1394bd030fe2","last_reissued_at":"2026-07-05T12:04:46.759994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:46.759994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring How (Not Just Whether) VLMs Build Common Ground","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anthony Sicilia, Malihe Alikhani, Mert \\.Inan, Saki Imai","submitted_at":"2025-09-04T01:43:49Z","abstract_excerpt":"Large vision language models (VLMs) increasingly claim reasoning skills, yet current benchmarks evaluate them in single-turn or question answering settings. However, grounding is an interactive process in which people gradually develop shared understanding through ongoing communication. We introduce a four-metric suite (grounding efficiency, content alignment, lexical adaptation, and human-likeness) to systematically evaluate VLM performance in interactive grounding contexts. We deploy the suite on 150 self-play sessions of interactive referential games between three proprietary VLMs and compa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03805","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.03805/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.03805","created_at":"2026-07-05T12:04:46.760053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03805v1","created_at":"2026-07-05T12:04:46.760053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03805","created_at":"2026-07-05T12:04:46.760053+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPJQOI2H2KZW","created_at":"2026-07-05T12:04:46.760053+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPJQOI2H2KZW2FVG","created_at":"2026-07-05T12:04:46.760053+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPJQOI2H","created_at":"2026-07-05T12:04:46.760053+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EPJQOI2H2KZW2FVGQINFJUHX35","json":"https://pith.science/pith/EPJQOI2H2KZW2FVGQINFJUHX35.json","graph_json":"https://pith.science/api/pith-number/EPJQOI2H2KZW2FVGQINFJUHX35/graph.json","events_json":"https://pith.science/api/pith-number/EPJQOI2H2KZW2FVGQINFJUHX35/events.json","paper":"https://pith.science/paper/EPJQOI2H"},"agent_actions":{"view_html":"https://pith.science/pith/EPJQOI2H2KZW2FVGQINFJUHX35","download_json":"https://pith.science/pith/EPJQOI2H2KZW2FVGQINFJUHX35.json","view_paper":"https://pith.science/paper/EPJQOI2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03805&json=true","fetch_graph":"https://pith.science/api/pith-number/EPJQOI2H2KZW2FVGQINFJUHX35/graph.json","fetch_events":"https://pith.science/api/pith-number/EPJQOI2H2KZW2FVGQINFJUHX35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPJQOI2H2KZW2FVGQINFJUHX35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPJQOI2H2KZW2FVGQINFJUHX35/action/storage_attestation","attest_author":"https://pith.science/pith/EPJQOI2H2KZW2FVGQINFJUHX35/action/author_attestation","sign_citation":"https://pith.science/pith/EPJQOI2H2KZW2FVGQINFJUHX35/action/citation_signature","submit_replication":"https://pith.science/pith/EPJQOI2H2KZW2FVGQINFJUHX35/action/replication_record"}},"created_at":"2026-07-05T12:04:46.760053+00:00","updated_at":"2026-07-05T12:04:46.760053+00:00"}