{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7QHB5P6MO2GSBE52MOZ7WJFFCZ","short_pith_number":"pith:7QHB5P6M","schema_version":"1.0","canonical_sha256":"fc0e1ebfcc768d2093ba63b3fb24a51658a37da88e35e6aca22a37591b4dbb87","source":{"kind":"arxiv","id":"2606.00065","version":1},"attestation_state":"computed","paper":{"title":"Beyond Text and Tables: Vision-Language Model Integration in ComProScanner for Extracting Materials Data from Scientific Figures with High Accuracy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Aritra Roy, Chiara Gattinoni, Enrico Grisan, John Buckeridge","submitted_at":"2026-05-19T23:55:19Z","abstract_excerpt":"Automated extraction of materials composition-property data from scientific literature has advanced considerably with the development of large language model-based pipelines; however, existing frameworks remain limited to textual and tabular content, overlooking the substantial proportion of quantitative property data reported exclusively in scientific figures. Here, we extend ComProScanner, a fully end-to-end multi-agent framework for automated composition-property database construction, with a native vision-language model (VLM) based figure extraction capability. The extension introduces a F"},"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":"2606.00065","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-19T23:55:19Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI","cs.CL"],"title_canon_sha256":"2d0280c05f95590ea44ab8f0c5520716e822e98b5bc47514e4e8c90a534d3a3c","abstract_canon_sha256":"a6e369a91a1b121bed74058d9a518fa0a44d210558310919ce639945005bab93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T00:03:13.892768Z","signature_b64":"Ys2RLN3thpDhaTzwnnlQBQdPq316vOdY20RZXkVCO8RB7ZzsCiIqBH/nats2fi3Le/W9vi0MI/Q/XhyUEI91Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc0e1ebfcc768d2093ba63b3fb24a51658a37da88e35e6aca22a37591b4dbb87","last_reissued_at":"2026-06-02T00:03:13.892304Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T00:03:13.892304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Text and Tables: Vision-Language Model Integration in ComProScanner for Extracting Materials Data from Scientific Figures with High Accuracy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Aritra Roy, Chiara Gattinoni, Enrico Grisan, John Buckeridge","submitted_at":"2026-05-19T23:55:19Z","abstract_excerpt":"Automated extraction of materials composition-property data from scientific literature has advanced considerably with the development of large language model-based pipelines; however, existing frameworks remain limited to textual and tabular content, overlooking the substantial proportion of quantitative property data reported exclusively in scientific figures. Here, we extend ComProScanner, a fully end-to-end multi-agent framework for automated composition-property database construction, with a native vision-language model (VLM) based figure extraction capability. The extension introduces a F"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00065","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/2606.00065/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":"2606.00065","created_at":"2026-06-02T00:03:13.892382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00065v1","created_at":"2026-06-02T00:03:13.892382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00065","created_at":"2026-06-02T00:03:13.892382+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QHB5P6MO2GS","created_at":"2026-06-02T00:03:13.892382+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QHB5P6MO2GSBE52","created_at":"2026-06-02T00:03:13.892382+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QHB5P6M","created_at":"2026-06-02T00:03:13.892382+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/7QHB5P6MO2GSBE52MOZ7WJFFCZ","json":"https://pith.science/pith/7QHB5P6MO2GSBE52MOZ7WJFFCZ.json","graph_json":"https://pith.science/api/pith-number/7QHB5P6MO2GSBE52MOZ7WJFFCZ/graph.json","events_json":"https://pith.science/api/pith-number/7QHB5P6MO2GSBE52MOZ7WJFFCZ/events.json","paper":"https://pith.science/paper/7QHB5P6M"},"agent_actions":{"view_html":"https://pith.science/pith/7QHB5P6MO2GSBE52MOZ7WJFFCZ","download_json":"https://pith.science/pith/7QHB5P6MO2GSBE52MOZ7WJFFCZ.json","view_paper":"https://pith.science/paper/7QHB5P6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00065&json=true","fetch_graph":"https://pith.science/api/pith-number/7QHB5P6MO2GSBE52MOZ7WJFFCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7QHB5P6MO2GSBE52MOZ7WJFFCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QHB5P6MO2GSBE52MOZ7WJFFCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QHB5P6MO2GSBE52MOZ7WJFFCZ/action/storage_attestation","attest_author":"https://pith.science/pith/7QHB5P6MO2GSBE52MOZ7WJFFCZ/action/author_attestation","sign_citation":"https://pith.science/pith/7QHB5P6MO2GSBE52MOZ7WJFFCZ/action/citation_signature","submit_replication":"https://pith.science/pith/7QHB5P6MO2GSBE52MOZ7WJFFCZ/action/replication_record"}},"created_at":"2026-06-02T00:03:13.892382+00:00","updated_at":"2026-06-02T00:03:13.892382+00:00"}