{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IZFZ4VAG2MMMATKVRB6CXUUGVQ","short_pith_number":"pith:IZFZ4VAG","canonical_record":{"source":{"id":"2504.16060","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T17:37:16Z","cross_cats_sorted":[],"title_canon_sha256":"6ce6eae299b76638142480802efd25f2f1a5f0186e3444167753f86b7b9b9ee0","abstract_canon_sha256":"10857d8885838aa315788b97971aca45dec76199148e6bbde9bffc5821b20c21"},"schema_version":"1.0"},"canonical_sha256":"464b9e5406d318c04d55887c2bd286ac3fd70442d0d94ffade7f82a7c4fe9c42","source":{"kind":"arxiv","id":"2504.16060","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16060","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16060v3","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16060","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"IZFZ4VAG2MMM","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_16","alias_value":"IZFZ4VAG2MMMATKV","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_8","alias_value":"IZFZ4VAG","created_at":"2026-07-05T11:45:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IZFZ4VAG2MMMATKVRB6CXUUGVQ","target":"record","payload":{"canonical_record":{"source":{"id":"2504.16060","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T17:37:16Z","cross_cats_sorted":[],"title_canon_sha256":"6ce6eae299b76638142480802efd25f2f1a5f0186e3444167753f86b7b9b9ee0","abstract_canon_sha256":"10857d8885838aa315788b97971aca45dec76199148e6bbde9bffc5821b20c21"},"schema_version":"1.0"},"canonical_sha256":"464b9e5406d318c04d55887c2bd286ac3fd70442d0d94ffade7f82a7c4fe9c42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:57.583120Z","signature_b64":"2+cj+sUdeuqbXAHVWBKrYjftWtP9A4yI24RHAI1IQIy9Hd0GFTVzHA92kplQupyf2TBv9Kwchw3lph99/yP8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"464b9e5406d318c04d55887c2bd286ac3fd70442d0d94ffade7f82a7c4fe9c42","last_reissued_at":"2026-07-05T11:45:57.582508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:57.582508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.16060","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cCE01hLNoV5LQ0ZfpA4/Tc9HsJ5tmgi1zGPial2SkwBYQ6CsrimO1lsYVsOigsiBtZBnc/A26CIAzeWwloCtDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T14:05:19.264508Z"},"content_sha256":"2dc4a9720b25f95d7d6146016562179c006dfe3d274a7e8365ad41134038a552","schema_version":"1.0","event_id":"sha256:2dc4a9720b25f95d7d6146016562179c006dfe3d274a7e8365ad41134038a552"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IZFZ4VAG2MMMATKVRB6CXUUGVQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dezhi Luo, Jiahe Ding, Jing Ding, Joyce Chai, Run Peng, Sihan Xu, Xuejun Zhang, Yuchen Huang, Ziqiao Ma","submitted_at":"2025-04-22T17:37:16Z","abstract_excerpt":"Referring Expression Generation (REG) is a core task for evaluating the pragmatic competence of vision-language systems, requiring not only accurate semantic grounding but also adherence to principles of cooperative communication (Grice, 1975). However, current evaluations of vision-language models (VLMs) often overlook the pragmatic dimension, reducing REG to a region-based captioning task and neglecting Gricean maxims. In this work, we revisit REG from a pragmatic perspective, introducing a new dataset (RefOI) of 1.5k images annotated with both written and spoken referring expressions. Throu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16060","kind":"arxiv","version":3},"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/2504.16060/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e8k+/WhVIjak8t+Qp3vQnw/aHC//GhQL16ewzDT9O7PS1vrv2PCqiJTBPyOG4SyfxsSlBbdB6a43urIBGl/hBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T14:05:19.265045Z"},"content_sha256":"47ef9bb743b723e9322235fb66088b823acdc9cd1a3342de3bf49b4c3db8e453","schema_version":"1.0","event_id":"sha256:47ef9bb743b723e9322235fb66088b823acdc9cd1a3342de3bf49b4c3db8e453"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IZFZ4VAG2MMMATKVRB6CXUUGVQ/bundle.json","state_url":"https://pith.science/pith/IZFZ4VAG2MMMATKVRB6CXUUGVQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IZFZ4VAG2MMMATKVRB6CXUUGVQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T14:05:19Z","links":{"resolver":"https://pith.science/pith/IZFZ4VAG2MMMATKVRB6CXUUGVQ","bundle":"https://pith.science/pith/IZFZ4VAG2MMMATKVRB6CXUUGVQ/bundle.json","state":"https://pith.science/pith/IZFZ4VAG2MMMATKVRB6CXUUGVQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IZFZ4VAG2MMMATKVRB6CXUUGVQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IZFZ4VAG2MMMATKVRB6CXUUGVQ","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":"10857d8885838aa315788b97971aca45dec76199148e6bbde9bffc5821b20c21","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T17:37:16Z","title_canon_sha256":"6ce6eae299b76638142480802efd25f2f1a5f0186e3444167753f86b7b9b9ee0"},"schema_version":"1.0","source":{"id":"2504.16060","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16060","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16060v3","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16060","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"IZFZ4VAG2MMM","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_16","alias_value":"IZFZ4VAG2MMMATKV","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_8","alias_value":"IZFZ4VAG","created_at":"2026-07-05T11:45:57Z"}],"graph_snapshots":[{"event_id":"sha256:47ef9bb743b723e9322235fb66088b823acdc9cd1a3342de3bf49b4c3db8e453","target":"graph","created_at":"2026-07-05T11:45:57Z","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/2504.16060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring Expression Generation (REG) is a core task for evaluating the pragmatic competence of vision-language systems, requiring not only accurate semantic grounding but also adherence to principles of cooperative communication (Grice, 1975). However, current evaluations of vision-language models (VLMs) often overlook the pragmatic dimension, reducing REG to a region-based captioning task and neglecting Gricean maxims. In this work, we revisit REG from a pragmatic perspective, introducing a new dataset (RefOI) of 1.5k images annotated with both written and spoken referring expressions. Throu","authors_text":"Dezhi Luo, Jiahe Ding, Jing Ding, Joyce Chai, Run Peng, Sihan Xu, Xuejun Zhang, Yuchen Huang, Ziqiao Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T17:37:16Z","title":"Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16060","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":"sha256:2dc4a9720b25f95d7d6146016562179c006dfe3d274a7e8365ad41134038a552","target":"record","created_at":"2026-07-05T11:45:57Z","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":"10857d8885838aa315788b97971aca45dec76199148e6bbde9bffc5821b20c21","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T17:37:16Z","title_canon_sha256":"6ce6eae299b76638142480802efd25f2f1a5f0186e3444167753f86b7b9b9ee0"},"schema_version":"1.0","source":{"id":"2504.16060","kind":"arxiv","version":3}},"canonical_sha256":"464b9e5406d318c04d55887c2bd286ac3fd70442d0d94ffade7f82a7c4fe9c42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"464b9e5406d318c04d55887c2bd286ac3fd70442d0d94ffade7f82a7c4fe9c42","first_computed_at":"2026-07-05T11:45:57.582508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:57.582508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2+cj+sUdeuqbXAHVWBKrYjftWtP9A4yI24RHAI1IQIy9Hd0GFTVzHA92kplQupyf2TBv9Kwchw3lph99/yP8Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:57.583120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16060","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dc4a9720b25f95d7d6146016562179c006dfe3d274a7e8365ad41134038a552","sha256:47ef9bb743b723e9322235fb66088b823acdc9cd1a3342de3bf49b4c3db8e453"],"state_sha256":"aa936826d84f64b1f627f8beeba626defe4136ddf8b62f01fcef2aa312b95ba3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lmn0tgVibLgRJL5tyXdrpAIY65BcO5TgR+03Ul+njfJcnOAjkWjCOI4UHrBn7fdpAr5Kx6YFYk+Zem2RVTljBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T14:05:19.274334Z","bundle_sha256":"c288aa22f497821bc25a20bdeaaac287fc8167c4a726e9d3cbf2114c142b3837"}}