{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7ETOV2TXDXYZ6VPPPBAI5S34O6","short_pith_number":"pith:7ETOV2TX","canonical_record":{"source":{"id":"2502.04389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-05T23:40:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd4e894e27e88bd52a615a49d7cdd8afbd15326d574bbd102c26e15fda29e3b1","abstract_canon_sha256":"3fabad2267ad81a023f9b22c5893215fcda56cea4575246cf027a47650bc78bc"},"schema_version":"1.0"},"canonical_sha256":"f926eaea771df19f55ef78408ecb7c778f554c1de7af375324e42f5146d72d5d","source":{"kind":"arxiv","id":"2502.04389","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04389","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04389v1","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04389","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_12","alias_value":"7ETOV2TXDXYZ","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_16","alias_value":"7ETOV2TXDXYZ6VPP","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_8","alias_value":"7ETOV2TX","created_at":"2026-07-05T10:10:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7ETOV2TXDXYZ6VPPPBAI5S34O6","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-05T23:40:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd4e894e27e88bd52a615a49d7cdd8afbd15326d574bbd102c26e15fda29e3b1","abstract_canon_sha256":"3fabad2267ad81a023f9b22c5893215fcda56cea4575246cf027a47650bc78bc"},"schema_version":"1.0"},"canonical_sha256":"f926eaea771df19f55ef78408ecb7c778f554c1de7af375324e42f5146d72d5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:50.811230Z","signature_b64":"yjs7sLGC/vgudxzyRQrNDuyrENqnEcO30vYQmWbyERBtuVuAbA1fEbv5WxWVbfW5+bPXDxHUX5KabRmDC6+yBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f926eaea771df19f55ef78408ecb7c778f554c1de7af375324e42f5146d72d5d","last_reissued_at":"2026-07-05T10:10:50.810750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:50.810750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04389","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":"2026-07-05T10:10:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+VM0IjJpG0dVemcP+8qNxOcpYmQZOXzL+1it6UuJl8UXQbs15w58cCjvM56ZTbEuH/LKfdue4GRvL9KrBmgRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:27:44.432562Z"},"content_sha256":"a2447c0361c6cbee60b6f1dfb00f7676d6e8af8b81ebc7abe9ecbf0cd32bea97","schema_version":"1.0","event_id":"sha256:a2447c0361c6cbee60b6f1dfb00f7676d6e8af8b81ebc7abe9ecbf0cd32bea97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7ETOV2TXDXYZ6VPPPBAI5S34O6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Overcoming Vision Language Model Challenges in Diagram Understanding: A Proof-of-Concept with XML-Driven Large Language Models Solutions","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Hayato Motegi, Masumi Morishige, Ryo Koshihara, Shue Shiinoki","submitted_at":"2025-02-05T23:40:26Z","abstract_excerpt":"Diagrams play a crucial role in visually conveying complex relationships and processes within business documentation. Despite recent advances in Vision-Language Models (VLMs) for various image understanding tasks, accurately identifying and extracting the structures and relationships depicted in diagrams continues to pose significant challenges. This study addresses these challenges by proposing a text-driven approach that bypasses reliance on VLMs' visual recognition capabilities. Instead, it utilizes the editable source files--such as xlsx, pptx or docx--where diagram elements (e.g., shapes,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04389","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/2502.04389/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":"2026-07-05T10:10:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6FC0jQlJeKWuIcO4AKl/OkBo4SH4pEVxmQ6mM7K2SPYzbSQ7FuLxVOeIMz0NfLg7/f5UbzWh/v6+fRVUPx6MDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:27:44.433091Z"},"content_sha256":"3abf383cbee65ac7a169a2ed08f8b9764a8427fa1c5cf3232c592e6954f8558e","schema_version":"1.0","event_id":"sha256:3abf383cbee65ac7a169a2ed08f8b9764a8427fa1c5cf3232c592e6954f8558e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7ETOV2TXDXYZ6VPPPBAI5S34O6/bundle.json","state_url":"https://pith.science/pith/7ETOV2TXDXYZ6VPPPBAI5S34O6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7ETOV2TXDXYZ6VPPPBAI5S34O6/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":"2026-08-09T19:27:44Z","links":{"resolver":"https://pith.science/pith/7ETOV2TXDXYZ6VPPPBAI5S34O6","bundle":"https://pith.science/pith/7ETOV2TXDXYZ6VPPPBAI5S34O6/bundle.json","state":"https://pith.science/pith/7ETOV2TXDXYZ6VPPPBAI5S34O6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7ETOV2TXDXYZ6VPPPBAI5S34O6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7ETOV2TXDXYZ6VPPPBAI5S34O6","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":"3fabad2267ad81a023f9b22c5893215fcda56cea4575246cf027a47650bc78bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-05T23:40:26Z","title_canon_sha256":"fd4e894e27e88bd52a615a49d7cdd8afbd15326d574bbd102c26e15fda29e3b1"},"schema_version":"1.0","source":{"id":"2502.04389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04389","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04389v1","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04389","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_12","alias_value":"7ETOV2TXDXYZ","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_16","alias_value":"7ETOV2TXDXYZ6VPP","created_at":"2026-07-05T10:10:50Z"},{"alias_kind":"pith_short_8","alias_value":"7ETOV2TX","created_at":"2026-07-05T10:10:50Z"}],"graph_snapshots":[{"event_id":"sha256:3abf383cbee65ac7a169a2ed08f8b9764a8427fa1c5cf3232c592e6954f8558e","target":"graph","created_at":"2026-07-05T10:10:50Z","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/2502.04389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diagrams play a crucial role in visually conveying complex relationships and processes within business documentation. Despite recent advances in Vision-Language Models (VLMs) for various image understanding tasks, accurately identifying and extracting the structures and relationships depicted in diagrams continues to pose significant challenges. This study addresses these challenges by proposing a text-driven approach that bypasses reliance on VLMs' visual recognition capabilities. Instead, it utilizes the editable source files--such as xlsx, pptx or docx--where diagram elements (e.g., shapes,","authors_text":"Hayato Motegi, Masumi Morishige, Ryo Koshihara, Shue Shiinoki","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-05T23:40:26Z","title":"Overcoming Vision Language Model Challenges in Diagram Understanding: A Proof-of-Concept with XML-Driven Large Language Models Solutions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04389","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:a2447c0361c6cbee60b6f1dfb00f7676d6e8af8b81ebc7abe9ecbf0cd32bea97","target":"record","created_at":"2026-07-05T10:10:50Z","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":"3fabad2267ad81a023f9b22c5893215fcda56cea4575246cf027a47650bc78bc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-05T23:40:26Z","title_canon_sha256":"fd4e894e27e88bd52a615a49d7cdd8afbd15326d574bbd102c26e15fda29e3b1"},"schema_version":"1.0","source":{"id":"2502.04389","kind":"arxiv","version":1}},"canonical_sha256":"f926eaea771df19f55ef78408ecb7c778f554c1de7af375324e42f5146d72d5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f926eaea771df19f55ef78408ecb7c778f554c1de7af375324e42f5146d72d5d","first_computed_at":"2026-07-05T10:10:50.810750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:50.810750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yjs7sLGC/vgudxzyRQrNDuyrENqnEcO30vYQmWbyERBtuVuAbA1fEbv5WxWVbfW5+bPXDxHUX5KabRmDC6+yBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:50.811230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2447c0361c6cbee60b6f1dfb00f7676d6e8af8b81ebc7abe9ecbf0cd32bea97","sha256:3abf383cbee65ac7a169a2ed08f8b9764a8427fa1c5cf3232c592e6954f8558e"],"state_sha256":"e5fecf737f1deda76adfc782afa22312d87ce59bac69604965638e73356224d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zgHNIPE7RwspulfKRmo5iY+QCFlAckemZEaCuWO729Ssrh0EOkW++dWlaC32w4726w2l5urNP9/zoUTM3psEBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:27:44.436516Z","bundle_sha256":"52c39262bea3f97007d1bb311ee320bd5c96797ef65c9348d3402d2cbcf9d743"}}