{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OTD6S6E5FPWBHKAGKSXKXERISR","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":"4d57ac0f4ede39eff63da1733998be86247203646fe5a41f7607665dd6a34859","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-04-17T05:33:45Z","title_canon_sha256":"930a0cd9213527181650736615c5634e5d104502c7899decfabc5bd7c31b657c"},"schema_version":"1.0","source":{"id":"2605.18774","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18774","created_at":"2026-05-20T00:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18774v1","created_at":"2026-05-20T00:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18774","created_at":"2026-05-20T00:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"OTD6S6E5FPWB","created_at":"2026-05-20T00:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"OTD6S6E5FPWBHKAG","created_at":"2026-05-20T00:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"OTD6S6E5","created_at":"2026-05-20T00:06:21Z"}],"graph_snapshots":[{"event_id":"sha256:a8a16019dcb75c7da04579be06f795496f0df96b1ad537caf8f33843270401ab","target":"graph","created_at":"2026-05-20T00:06:21Z","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/2605.18774/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In long, multi-page industrial documents, retrieval-augmented generation (RAG) depends heavily on whether chunk boundaries follow the document's true structure. Existing text-centric chunkers and generative hierarchy parsers often miss cross-page parent-child relations, figure/table-caption bindings, and boundary cues, which leads to fragmented or redundant chunks and degrades both retrieval and answer quality. We propose M3DocDep, an LVLM-based pipeline that first recovers block-level dependencies and then constructs chunks along the recovered document tree. The pipeline uses SharedDet as a c","authors_text":"Heuiseok Lim, Jaehyung Seo, Jeongbae Park, Joongmin Shin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-04-17T05:33:45Z","title":"M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18774","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":"sha256:719266d69e70fa78dfe3829af8a313f25d3caad9560acfcf869fda136d0d55d4","target":"record","created_at":"2026-05-20T00:06:21Z","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":"4d57ac0f4ede39eff63da1733998be86247203646fe5a41f7607665dd6a34859","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-04-17T05:33:45Z","title_canon_sha256":"930a0cd9213527181650736615c5634e5d104502c7899decfabc5bd7c31b657c"},"schema_version":"1.0","source":{"id":"2605.18774","kind":"arxiv","version":1}},"canonical_sha256":"74c7e9789d2bec13a80654aeab9228946e25be292b6eba41eff380e98d6e3fdc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74c7e9789d2bec13a80654aeab9228946e25be292b6eba41eff380e98d6e3fdc","first_computed_at":"2026-05-20T00:06:21.385074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:21.385074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Na645/JCQz14ZTW1C3J9pc4iRURTPtv1PzE3NFgZeoyhvLDI5aJM2eyaBwyXQrSy8S/niq9gg1qwflrYUHNCDA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:21.385957Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18774","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:719266d69e70fa78dfe3829af8a313f25d3caad9560acfcf869fda136d0d55d4","sha256:a8a16019dcb75c7da04579be06f795496f0df96b1ad537caf8f33843270401ab"],"state_sha256":"999038ccaa2a76af671f986086b13c6d8506f63c9a75752141e53e036ca3c483"}