{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6W4L2GBQHZFJXZ5I74DI7UMPVR","short_pith_number":"pith:6W4L2GBQ","canonical_record":{"source":{"id":"2507.23217","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T03:14:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"24a336a9c8d5c1b190a6dda0b802fce02f29867363d5b71ecc60df402eea7e50","abstract_canon_sha256":"c767a91fc0ae9eb0d0e47c8511666b38e4dc816ec658b54f2f84fa80789f3501"},"schema_version":"1.0"},"canonical_sha256":"f5b8bd18303e4a9be7a8ff068fd18fac4efb2c67cc25df0652609cc17696f215","source":{"kind":"arxiv","id":"2507.23217","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23217","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23217v1","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23217","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"6W4L2GBQHZFJ","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"pith_short_16","alias_value":"6W4L2GBQHZFJXZ5I","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"pith_short_8","alias_value":"6W4L2GBQ","created_at":"2026-07-05T11:46:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6W4L2GBQHZFJXZ5I74DI7UMPVR","target":"record","payload":{"canonical_record":{"source":{"id":"2507.23217","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T03:14:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"24a336a9c8d5c1b190a6dda0b802fce02f29867363d5b71ecc60df402eea7e50","abstract_canon_sha256":"c767a91fc0ae9eb0d0e47c8511666b38e4dc816ec658b54f2f84fa80789f3501"},"schema_version":"1.0"},"canonical_sha256":"f5b8bd18303e4a9be7a8ff068fd18fac4efb2c67cc25df0652609cc17696f215","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:07.703110Z","signature_b64":"AR1UbLwsatyn0L0+3lYFATvl+wl0NIUmmjGHVaqQOsQ5OfaOhLn82JIYoXg7p9rvcK9Vvh9tEazUBsDvP8nbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5b8bd18303e4a9be7a8ff068fd18fac4efb2c67cc25df0652609cc17696f215","last_reissued_at":"2026-07-05T11:46:07.702648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:07.702648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.23217","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":"2026-07-05T11:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XYm8DmYRuRlcFQOA4cabuAf4OTXrPOigAOWthYh9a9wrhytKVNrLo15c9HXuS/sQATmuwu3/xcE5NWMTXn2NDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:18:37.543882Z"},"content_sha256":"a4e5b8c92ef2b21e845aa6c6b139d3af17f233ef9775f1064470514d68c608ba","schema_version":"1.0","event_id":"sha256:a4e5b8c92ef2b21e845aa6c6b139d3af17f233ef9775f1064470514d68c608ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6W4L2GBQHZFJXZ5I74DI7UMPVR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-Shot Document Understanding using Pseudo Table of Contents-Guided Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Byeong Hyun Yoon, Haedong Jeong, Hyeon Seong Jeong, Sangwoo Jo, Taehoon Kim, Yoonseok Heo","submitted_at":"2025-07-31T03:14:45Z","abstract_excerpt":"Understanding complex multimodal documents remains challenging due to their structural inconsistencies and limited training data availability. We introduce \\textit{DocsRay}, a training-free document understanding system that integrates pseudo Table of Contents (TOC) generation with hierarchical Retrieval-Augmented Generation (RAG). Our approach leverages multimodal Large Language Models' (LLMs) native capabilities to seamlessly process documents containing diverse elements such as text, images, charts, and tables without requiring specialized models or additional training. DocsRay's framework "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23217","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/2507.23217/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":"2026-07-05T11:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NhrvF2TWmOAhDXp4+Iwkhwrd+SuShPN90YikeHIqsWTP7OgwlT3lzBsIIQ4HMFsXuh+U9KydSPRyPORaKmJuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:18:37.544573Z"},"content_sha256":"c4ebe34749b18f62a9b81873cdca33449e625d4221e0811c7c63b6ef92961051","schema_version":"1.0","event_id":"sha256:c4ebe34749b18f62a9b81873cdca33449e625d4221e0811c7c63b6ef92961051"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6W4L2GBQHZFJXZ5I74DI7UMPVR/bundle.json","state_url":"https://pith.science/pith/6W4L2GBQHZFJXZ5I74DI7UMPVR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6W4L2GBQHZFJXZ5I74DI7UMPVR/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":"2026-08-23T18:18:37Z","links":{"resolver":"https://pith.science/pith/6W4L2GBQHZFJXZ5I74DI7UMPVR","bundle":"https://pith.science/pith/6W4L2GBQHZFJXZ5I74DI7UMPVR/bundle.json","state":"https://pith.science/pith/6W4L2GBQHZFJXZ5I74DI7UMPVR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6W4L2GBQHZFJXZ5I74DI7UMPVR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6W4L2GBQHZFJXZ5I74DI7UMPVR","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":"c767a91fc0ae9eb0d0e47c8511666b38e4dc816ec658b54f2f84fa80789f3501","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T03:14:45Z","title_canon_sha256":"24a336a9c8d5c1b190a6dda0b802fce02f29867363d5b71ecc60df402eea7e50"},"schema_version":"1.0","source":{"id":"2507.23217","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23217","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23217v1","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23217","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"6W4L2GBQHZFJ","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"pith_short_16","alias_value":"6W4L2GBQHZFJXZ5I","created_at":"2026-07-05T11:46:07Z"},{"alias_kind":"pith_short_8","alias_value":"6W4L2GBQ","created_at":"2026-07-05T11:46:07Z"}],"graph_snapshots":[{"event_id":"sha256:c4ebe34749b18f62a9b81873cdca33449e625d4221e0811c7c63b6ef92961051","target":"graph","created_at":"2026-07-05T11:46:07Z","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/2507.23217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding complex multimodal documents remains challenging due to their structural inconsistencies and limited training data availability. We introduce \\textit{DocsRay}, a training-free document understanding system that integrates pseudo Table of Contents (TOC) generation with hierarchical Retrieval-Augmented Generation (RAG). Our approach leverages multimodal Large Language Models' (LLMs) native capabilities to seamlessly process documents containing diverse elements such as text, images, charts, and tables without requiring specialized models or additional training. DocsRay's framework ","authors_text":"Byeong Hyun Yoon, Haedong Jeong, Hyeon Seong Jeong, Sangwoo Jo, Taehoon Kim, Yoonseok Heo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T03:14:45Z","title":"Zero-Shot Document Understanding using Pseudo Table of Contents-Guided Retrieval-Augmented Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23217","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:a4e5b8c92ef2b21e845aa6c6b139d3af17f233ef9775f1064470514d68c608ba","target":"record","created_at":"2026-07-05T11:46:07Z","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":"c767a91fc0ae9eb0d0e47c8511666b38e4dc816ec658b54f2f84fa80789f3501","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T03:14:45Z","title_canon_sha256":"24a336a9c8d5c1b190a6dda0b802fce02f29867363d5b71ecc60df402eea7e50"},"schema_version":"1.0","source":{"id":"2507.23217","kind":"arxiv","version":1}},"canonical_sha256":"f5b8bd18303e4a9be7a8ff068fd18fac4efb2c67cc25df0652609cc17696f215","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5b8bd18303e4a9be7a8ff068fd18fac4efb2c67cc25df0652609cc17696f215","first_computed_at":"2026-07-05T11:46:07.702648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:07.702648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AR1UbLwsatyn0L0+3lYFATvl+wl0NIUmmjGHVaqQOsQ5OfaOhLn82JIYoXg7p9rvcK9Vvh9tEazUBsDvP8nbAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:07.703110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.23217","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4e5b8c92ef2b21e845aa6c6b139d3af17f233ef9775f1064470514d68c608ba","sha256:c4ebe34749b18f62a9b81873cdca33449e625d4221e0811c7c63b6ef92961051"],"state_sha256":"046da1ba9849f09a2d965db713f6437a38394858418c615a056c352be1f08c97"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5x+uD9NXWgmJX+pkJIke7+ZWA+Oz5SJwCtXG2FxqkJc//m1dtW9n2i6wigtBJtKV60gQUD2mHaTWmTWbwY64Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T18:18:37.549623Z","bundle_sha256":"acbeacac92e4b4dd8127b12f2375c603b366e2dca6f95cdc841ce7cbcf3ef39b"}}