{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZB3LTU4HM2UDH5QYRZPEAHFHCT","short_pith_number":"pith:ZB3LTU4H","canonical_record":{"source":{"id":"2503.12326","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T02:41:43Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"title_canon_sha256":"e8ffe4e14b666e82e0789e5222a5309ad12c9b8c4cf3e4874a38d19c59f47820","abstract_canon_sha256":"a223b6e93098a5234e5410df92435e16e3e3b4c856f710948e369f4d4bf441cb"},"schema_version":"1.0"},"canonical_sha256":"c876b9d38766a833f6188e5e401ca714c70d99c4965c9626d321f2581b62fcca","source":{"kind":"arxiv","id":"2503.12326","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12326","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12326v1","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12326","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"pith_short_12","alias_value":"ZB3LTU4HM2UD","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"pith_short_16","alias_value":"ZB3LTU4HM2UDH5QY","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"pith_short_8","alias_value":"ZB3LTU4H","created_at":"2026-07-05T10:32:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZB3LTU4HM2UDH5QYRZPEAHFHCT","target":"record","payload":{"canonical_record":{"source":{"id":"2503.12326","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T02:41:43Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"title_canon_sha256":"e8ffe4e14b666e82e0789e5222a5309ad12c9b8c4cf3e4874a38d19c59f47820","abstract_canon_sha256":"a223b6e93098a5234e5410df92435e16e3e3b4c856f710948e369f4d4bf441cb"},"schema_version":"1.0"},"canonical_sha256":"c876b9d38766a833f6188e5e401ca714c70d99c4965c9626d321f2581b62fcca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:10.376564Z","signature_b64":"vWqDfGNKe7B9iYYPEg2o7682ouDq8IjkujV6pex8yLRrdxJ9YzFVfyArlqGop5FPe67PRXmiZkVLIDFiH7STCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c876b9d38766a833f6188e5e401ca714c70d99c4965c9626d321f2581b62fcca","last_reissued_at":"2026-07-05T10:32:10.376083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:10.376083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.12326","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:32:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hpeFVztZ4D5lXvvkjFLeYik2OgrnscPU8FZ2HtdY7j+a2mrocHriOie21q5uEqkXi+FgxWKrXRSKbySNXMKEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:03:10.807709Z"},"content_sha256":"190f6c3b5a4dee385680beb4c4cf0dabe8d474eb405fb2b9486477780d3cddde","schema_version":"1.0","event_id":"sha256:190f6c3b5a4dee385680beb4c4cf0dabe8d474eb405fb2b9486477780d3cddde"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZB3LTU4HM2UDH5QYRZPEAHFHCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Vision Capabilities of Multimodal LLMs for Automated Data Extraction from Plots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.AI"],"primary_cat":"cs.CV","authors_text":"Dane Morgan, Maciej P. Polak","submitted_at":"2025-03-16T02:41:43Z","abstract_excerpt":"Automated data extraction from research texts has been steadily improving, with the emergence of large language models (LLMs) accelerating progress even further. Extracting data from plots in research papers, however, has been such a complex task that it has predominantly been confined to manual data extraction. We show that current multimodal large language models, with proper instructions and engineered workflows, are capable of accurately extracting data from plots. This capability is inherent to the pretrained models and can be achieved with a chain-of-thought sequence of zero-shot enginee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12326","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/2503.12326/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":"2026-07-05T10:32:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"klkRSiVpzKGPACVHsn4HtxibI5W67BqBxgkG7M+mcr/72njaHvfH+guSqXu1nudP/WVBvoXpB7YxKFkwUHtUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:03:10.808328Z"},"content_sha256":"fc084debe25e29c71a1a7d2ac193014774b23dd7662b8e869543179ef3fdf778","schema_version":"1.0","event_id":"sha256:fc084debe25e29c71a1a7d2ac193014774b23dd7662b8e869543179ef3fdf778"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZB3LTU4HM2UDH5QYRZPEAHFHCT/bundle.json","state_url":"https://pith.science/pith/ZB3LTU4HM2UDH5QYRZPEAHFHCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZB3LTU4HM2UDH5QYRZPEAHFHCT/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":"2026-08-05T17:03:10Z","links":{"resolver":"https://pith.science/pith/ZB3LTU4HM2UDH5QYRZPEAHFHCT","bundle":"https://pith.science/pith/ZB3LTU4HM2UDH5QYRZPEAHFHCT/bundle.json","state":"https://pith.science/pith/ZB3LTU4HM2UDH5QYRZPEAHFHCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZB3LTU4HM2UDH5QYRZPEAHFHCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZB3LTU4HM2UDH5QYRZPEAHFHCT","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":"a223b6e93098a5234e5410df92435e16e3e3b4c856f710948e369f4d4bf441cb","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T02:41:43Z","title_canon_sha256":"e8ffe4e14b666e82e0789e5222a5309ad12c9b8c4cf3e4874a38d19c59f47820"},"schema_version":"1.0","source":{"id":"2503.12326","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12326","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12326v1","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12326","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"pith_short_12","alias_value":"ZB3LTU4HM2UD","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"pith_short_16","alias_value":"ZB3LTU4HM2UDH5QY","created_at":"2026-07-05T10:32:10Z"},{"alias_kind":"pith_short_8","alias_value":"ZB3LTU4H","created_at":"2026-07-05T10:32:10Z"}],"graph_snapshots":[{"event_id":"sha256:fc084debe25e29c71a1a7d2ac193014774b23dd7662b8e869543179ef3fdf778","target":"graph","created_at":"2026-07-05T10:32:10Z","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/2503.12326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated data extraction from research texts has been steadily improving, with the emergence of large language models (LLMs) accelerating progress even further. Extracting data from plots in research papers, however, has been such a complex task that it has predominantly been confined to manual data extraction. We show that current multimodal large language models, with proper instructions and engineered workflows, are capable of accurately extracting data from plots. This capability is inherent to the pretrained models and can be achieved with a chain-of-thought sequence of zero-shot enginee","authors_text":"Dane Morgan, Maciej P. Polak","cross_cats":["cond-mat.mtrl-sci","cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T02:41:43Z","title":"Leveraging Vision Capabilities of Multimodal LLMs for Automated Data Extraction from Plots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12326","kind":"arxiv","version":1},"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":"sha256:190f6c3b5a4dee385680beb4c4cf0dabe8d474eb405fb2b9486477780d3cddde","target":"record","created_at":"2026-07-05T10:32:10Z","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":"a223b6e93098a5234e5410df92435e16e3e3b4c856f710948e369f4d4bf441cb","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T02:41:43Z","title_canon_sha256":"e8ffe4e14b666e82e0789e5222a5309ad12c9b8c4cf3e4874a38d19c59f47820"},"schema_version":"1.0","source":{"id":"2503.12326","kind":"arxiv","version":1}},"canonical_sha256":"c876b9d38766a833f6188e5e401ca714c70d99c4965c9626d321f2581b62fcca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c876b9d38766a833f6188e5e401ca714c70d99c4965c9626d321f2581b62fcca","first_computed_at":"2026-07-05T10:32:10.376083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:10.376083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vWqDfGNKe7B9iYYPEg2o7682ouDq8IjkujV6pex8yLRrdxJ9YzFVfyArlqGop5FPe67PRXmiZkVLIDFiH7STCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:10.376564Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12326","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:190f6c3b5a4dee385680beb4c4cf0dabe8d474eb405fb2b9486477780d3cddde","sha256:fc084debe25e29c71a1a7d2ac193014774b23dd7662b8e869543179ef3fdf778"],"state_sha256":"bd690ac38b7a91601a17dffa281cfd134e5aa740c44c547a5b60ae420a48429e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fmb90tORrgoWfOo5TLG6KkMVNJqb5BTwvBMXtKutUXeeYfcx1vlqxN0jMyMvQF6SMjkBx/z3oKs8mk9wSykjBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:03:10.812080Z","bundle_sha256":"404646e72bc7a9f1297f022f914ba6aa2e562e2e885f838dbf159f6a0502224c"}}