{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X7IS4N2BIUY2WUFCTYLO3KEPJL","short_pith_number":"pith:X7IS4N2B","schema_version":"1.0","canonical_sha256":"bfd12e37414531ab50a29e16eda88f4aefe1efdea45157c0fc0a6ccee550698a","source":{"kind":"arxiv","id":"2605.07415","version":2},"attestation_state":"computed","paper":{"title":"ChartREG++: Towards Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A new benchmark and code-driven synthesis pipeline improve referring expression grounding on charts with multiple targets and diverse clues.","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Qingfu Zhu, Tianhao Niu, Wanxiang Che, Xuan Dong, Ziyu Han","submitted_at":"2026-05-08T08:07:11Z","abstract_excerpt":"Referring expression grounding is a core problem in visual grounding and is widely used as a diagnostic of spatial grounding and reasoning in vision and language models, yet most prior work focuses on natural images. In contrast, existing chart referring expression grounding-related benchmarks remain limited: (1) they largely adopt bounding boxes, constraining localization precision for fine chart elements (2) they mostly assume a single and two referred target instances, failing to handle multi-instance target references; (3) the language expressions over-rely on textual cues or data-rank clu"},"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":"2605.07415","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-08T08:07:11Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e4123e93fe4522b2a1fbc4a03bdbb45570cd91f48708a16c29ac2b653eb583c5","abstract_canon_sha256":"65c60e257d7ad46333a07d328d6afaf4374524cfc96f6176377e5988ff8ff638"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:03.089508Z","signature_b64":"4x8abZzDUDpC4xaz2KS4ebdieWe57n05Tv5sJVQz+aKphI6T0DN8OpJ5l7Zsoxcq9v3/L0giYHwVIDZppUrXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfd12e37414531ab50a29e16eda88f4aefe1efdea45157c0fc0a6ccee550698a","last_reissued_at":"2026-06-10T01:10:03.088707Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:03.088707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChartREG++: Towards Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A new benchmark and code-driven synthesis pipeline improve referring expression grounding on charts with multiple targets and diverse clues.","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Qingfu Zhu, Tianhao Niu, Wanxiang Che, Xuan Dong, Ziyu Han","submitted_at":"2026-05-08T08:07:11Z","abstract_excerpt":"Referring expression grounding is a core problem in visual grounding and is widely used as a diagnostic of spatial grounding and reasoning in vision and language models, yet most prior work focuses on natural images. In contrast, existing chart referring expression grounding-related benchmarks remain limited: (1) they largely adopt bounding boxes, constraining localization precision for fine chart elements (2) they mostly assume a single and two referred target instances, failing to handle multi-instance target references; (3) the language expressions over-rely on textual cues or data-rank clu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The resulting system consistently outperforms baselines on our benchmark and generalizes well to a ChartQA-derived real-chart grounding benchmark.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the code-driven synthesis pipeline produces masks that faithfully match real rendered charts and that the benchmark's distribution of clues and chart types reflects practical use cases.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ChartREG++ creates a new multi-target chart grounding benchmark with diverse cues and a code-driven synthesis pipeline for accurate masks, yielding a model that outperforms baselines and generalizes to real ChartQA charts.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A new benchmark and code-driven synthesis pipeline improve referring expression grounding on charts with multiple targets and diverse clues.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"abd04d178281dfc7f799b83010ee9732cb601b4d786311a8a4cca5cdc3355285"},"source":{"id":"2605.07415","kind":"arxiv","version":2},"verdict":{"id":"2a89a22e-1bbc-4c78-aac3-7179b9504c8d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T01:44:53.476341Z","strongest_claim":"The resulting system consistently outperforms baselines on our benchmark and generalizes well to a ChartQA-derived real-chart grounding benchmark.","one_line_summary":"ChartREG++ creates a new multi-target chart grounding benchmark with diverse cues and a code-driven synthesis pipeline for accurate masks, yielding a model that outperforms baselines and generalizes to real ChartQA charts.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the code-driven synthesis pipeline produces masks that faithfully match real rendered charts and that the benchmark's distribution of clues and chart types reflects practical use cases.","pith_extraction_headline":"A new benchmark and code-driven synthesis pipeline improve referring expression grounding on charts with multiple targets and diverse clues."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07415/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T11:02:03.197994Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T05:44:38.532890Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:19.182812Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:51:25.686300Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"54672c9fff77e40e49ab305bb6fe980f3cabb231b0da042afb17350c45e3f948"},"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":"2605.07415","created_at":"2026-06-10T01:10:03.088830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.07415v2","created_at":"2026-06-10T01:10:03.088830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07415","created_at":"2026-06-10T01:10:03.088830+00:00"},{"alias_kind":"pith_short_12","alias_value":"X7IS4N2BIUY2","created_at":"2026-06-10T01:10:03.088830+00:00"},{"alias_kind":"pith_short_16","alias_value":"X7IS4N2BIUY2WUFC","created_at":"2026-06-10T01:10:03.088830+00:00"},{"alias_kind":"pith_short_8","alias_value":"X7IS4N2B","created_at":"2026-06-10T01:10:03.088830+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/X7IS4N2BIUY2WUFCTYLO3KEPJL","json":"https://pith.science/pith/X7IS4N2BIUY2WUFCTYLO3KEPJL.json","graph_json":"https://pith.science/api/pith-number/X7IS4N2BIUY2WUFCTYLO3KEPJL/graph.json","events_json":"https://pith.science/api/pith-number/X7IS4N2BIUY2WUFCTYLO3KEPJL/events.json","paper":"https://pith.science/paper/X7IS4N2B"},"agent_actions":{"view_html":"https://pith.science/pith/X7IS4N2BIUY2WUFCTYLO3KEPJL","download_json":"https://pith.science/pith/X7IS4N2BIUY2WUFCTYLO3KEPJL.json","view_paper":"https://pith.science/paper/X7IS4N2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.07415&json=true","fetch_graph":"https://pith.science/api/pith-number/X7IS4N2BIUY2WUFCTYLO3KEPJL/graph.json","fetch_events":"https://pith.science/api/pith-number/X7IS4N2BIUY2WUFCTYLO3KEPJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X7IS4N2BIUY2WUFCTYLO3KEPJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X7IS4N2BIUY2WUFCTYLO3KEPJL/action/storage_attestation","attest_author":"https://pith.science/pith/X7IS4N2BIUY2WUFCTYLO3KEPJL/action/author_attestation","sign_citation":"https://pith.science/pith/X7IS4N2BIUY2WUFCTYLO3KEPJL/action/citation_signature","submit_replication":"https://pith.science/pith/X7IS4N2BIUY2WUFCTYLO3KEPJL/action/replication_record"}},"created_at":"2026-06-10T01:10:03.088830+00:00","updated_at":"2026-06-10T01:10:03.088830+00:00"}