{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FXK25YQ6TLIGDXADS5V54NDIR2","short_pith_number":"pith:FXK25YQ6","canonical_record":{"source":{"id":"2412.16420","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T00:52:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"82f11361f8fa2ac85f3824ca9659de72b712eb71f1737927afa4e920ab7a6218","abstract_canon_sha256":"2959d45feee8dbe6f42692808d5581a1e3419336457a81c561ad53c523555a07"},"schema_version":"1.0"},"canonical_sha256":"2dd5aee21e9ad061dc03976bde34688e82524056a8e185d776ef433da69a1d17","source":{"kind":"arxiv","id":"2412.16420","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16420","created_at":"2026-07-05T09:52:45Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16420v1","created_at":"2026-07-05T09:52:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16420","created_at":"2026-07-05T09:52:45Z"},{"alias_kind":"pith_short_12","alias_value":"FXK25YQ6TLIG","created_at":"2026-07-05T09:52:45Z"},{"alias_kind":"pith_short_16","alias_value":"FXK25YQ6TLIGDXAD","created_at":"2026-07-05T09:52:45Z"},{"alias_kind":"pith_short_8","alias_value":"FXK25YQ6","created_at":"2026-07-05T09:52:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FXK25YQ6TLIGDXADS5V54NDIR2","target":"record","payload":{"canonical_record":{"source":{"id":"2412.16420","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T00:52:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"82f11361f8fa2ac85f3824ca9659de72b712eb71f1737927afa4e920ab7a6218","abstract_canon_sha256":"2959d45feee8dbe6f42692808d5581a1e3419336457a81c561ad53c523555a07"},"schema_version":"1.0"},"canonical_sha256":"2dd5aee21e9ad061dc03976bde34688e82524056a8e185d776ef433da69a1d17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:45.760016Z","signature_b64":"Im4ezPjQRz1CTUP229v7U0BQPilUktGqocxoycfjFaim6KnOV1cXCmm9c1TG8DNHiNaUXM9dxHGmZB0xU84ZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dd5aee21e9ad061dc03976bde34688e82524056a8e185d776ef433da69a1d17","last_reissued_at":"2026-07-05T09:52:45.759581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:45.759581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.16420","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":"2026-07-05T09:52:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"86NuCS/YRd9Wb/YdEHgOJDpxBnb6+YGSV+XXxCFGk5ahGy9rBINrcCBnRv9BbMGiyVpGhveTYJ7YhOA1ISrBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:58:59.217819Z"},"content_sha256":"5c2f939fe146b569108081a69340e16b2be24e1a46ae442500aef8cee1beaf3c","schema_version":"1.0","event_id":"sha256:5c2f939fe146b569108081a69340e16b2be24e1a46ae442500aef8cee1beaf3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FXK25YQ6TLIGDXADS5V54NDIR2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ankan Dash, Guiling Wang, Junyi Ye, Wenpeng Yin","submitted_at":"2024-12-21T00:52:41Z","abstract_excerpt":"Flowcharts are typically presented as images, driving the trend of using vision-language models (VLMs) for end-to-end flowchart understanding. However, two key challenges arise: (i) Limited controllability--users have minimal influence over the downstream task, as they can only modify input images, while the training of VLMs is often out of reach for most researchers. (ii) Lack of explainability--it is difficult to trace VLM errors to specific causes, such as failures in visual encoding or reasoning. We propose TextFlow, addressing aforementioned issues with two stages: (i) Vision Textualizer-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16420","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/2412.16420/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":"2026-07-05T09:52:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lISzk3OmgpARhke0L1yBBNoVbRKAn4q0QWNVF7IapB5jcm2BHt+yA3KqVB8uOJGenLSXU+wm/bROFnynaYwKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:58:59.218342Z"},"content_sha256":"3a27aaaab65c05d79569cface3678259245535a2cafb4c373c61f309aaf84083","schema_version":"1.0","event_id":"sha256:3a27aaaab65c05d79569cface3678259245535a2cafb4c373c61f309aaf84083"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FXK25YQ6TLIGDXADS5V54NDIR2/bundle.json","state_url":"https://pith.science/pith/FXK25YQ6TLIGDXADS5V54NDIR2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FXK25YQ6TLIGDXADS5V54NDIR2/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":"2026-08-08T21:58:59Z","links":{"resolver":"https://pith.science/pith/FXK25YQ6TLIGDXADS5V54NDIR2","bundle":"https://pith.science/pith/FXK25YQ6TLIGDXADS5V54NDIR2/bundle.json","state":"https://pith.science/pith/FXK25YQ6TLIGDXADS5V54NDIR2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FXK25YQ6TLIGDXADS5V54NDIR2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FXK25YQ6TLIGDXADS5V54NDIR2","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":"2959d45feee8dbe6f42692808d5581a1e3419336457a81c561ad53c523555a07","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T00:52:41Z","title_canon_sha256":"82f11361f8fa2ac85f3824ca9659de72b712eb71f1737927afa4e920ab7a6218"},"schema_version":"1.0","source":{"id":"2412.16420","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16420","created_at":"2026-07-05T09:52:45Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16420v1","created_at":"2026-07-05T09:52:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16420","created_at":"2026-07-05T09:52:45Z"},{"alias_kind":"pith_short_12","alias_value":"FXK25YQ6TLIG","created_at":"2026-07-05T09:52:45Z"},{"alias_kind":"pith_short_16","alias_value":"FXK25YQ6TLIGDXAD","created_at":"2026-07-05T09:52:45Z"},{"alias_kind":"pith_short_8","alias_value":"FXK25YQ6","created_at":"2026-07-05T09:52:45Z"}],"graph_snapshots":[{"event_id":"sha256:3a27aaaab65c05d79569cface3678259245535a2cafb4c373c61f309aaf84083","target":"graph","created_at":"2026-07-05T09:52:45Z","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/2412.16420/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Flowcharts are typically presented as images, driving the trend of using vision-language models (VLMs) for end-to-end flowchart understanding. However, two key challenges arise: (i) Limited controllability--users have minimal influence over the downstream task, as they can only modify input images, while the training of VLMs is often out of reach for most researchers. (ii) Lack of explainability--it is difficult to trace VLM errors to specific causes, such as failures in visual encoding or reasoning. We propose TextFlow, addressing aforementioned issues with two stages: (i) Vision Textualizer-","authors_text":"Ankan Dash, Guiling Wang, Junyi Ye, Wenpeng Yin","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T00:52:41Z","title":"Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16420","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":"sha256:5c2f939fe146b569108081a69340e16b2be24e1a46ae442500aef8cee1beaf3c","target":"record","created_at":"2026-07-05T09:52:45Z","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":"2959d45feee8dbe6f42692808d5581a1e3419336457a81c561ad53c523555a07","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T00:52:41Z","title_canon_sha256":"82f11361f8fa2ac85f3824ca9659de72b712eb71f1737927afa4e920ab7a6218"},"schema_version":"1.0","source":{"id":"2412.16420","kind":"arxiv","version":1}},"canonical_sha256":"2dd5aee21e9ad061dc03976bde34688e82524056a8e185d776ef433da69a1d17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2dd5aee21e9ad061dc03976bde34688e82524056a8e185d776ef433da69a1d17","first_computed_at":"2026-07-05T09:52:45.759581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:45.759581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Im4ezPjQRz1CTUP229v7U0BQPilUktGqocxoycfjFaim6KnOV1cXCmm9c1TG8DNHiNaUXM9dxHGmZB0xU84ZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:45.760016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16420","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c2f939fe146b569108081a69340e16b2be24e1a46ae442500aef8cee1beaf3c","sha256:3a27aaaab65c05d79569cface3678259245535a2cafb4c373c61f309aaf84083"],"state_sha256":"c143003b90013b6e0030d7a9289cd2f8a4a22625fb49a57f12ef02c12632a2ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8hAx0TeXKA0JeYCG5dzjjr10Yy8qspO9BW19jddTGSXklndbjHNone2H4s0TkYCfK8derX+F7p6hN63O33lEAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:58:59.222048Z","bundle_sha256":"3ec1e4379b3ac72536ed7c96cc93275ae77c6fb45f13b1b85f42c77d3d835a4e"}}