{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QRFQEFAVMI7EWY7OJYSED5ARKS","short_pith_number":"pith:QRFQEFAV","canonical_record":{"source":{"id":"2607.22679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-11T04:58:00Z","cross_cats_sorted":[],"title_canon_sha256":"aeee99def32c094932d17ccc8bd5199e3933358c387637f8bdd1e8b325295b3c","abstract_canon_sha256":"8ad69b58ebf8e952a24379c124edf21769fd14e17c87f3a453321306f36d80e5"},"schema_version":"1.0"},"canonical_sha256":"844b021415623e4b63ee4e2441f411549cbdd6d74b334cab86809668fe4896fc","source":{"kind":"arxiv","id":"2607.22679","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22679","created_at":"2026-07-28T00:21:48Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22679v1","created_at":"2026-07-28T00:21:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22679","created_at":"2026-07-28T00:21:48Z"},{"alias_kind":"pith_short_12","alias_value":"QRFQEFAVMI7E","created_at":"2026-07-28T00:21:48Z"},{"alias_kind":"pith_short_16","alias_value":"QRFQEFAVMI7EWY7O","created_at":"2026-07-28T00:21:48Z"},{"alias_kind":"pith_short_8","alias_value":"QRFQEFAV","created_at":"2026-07-28T00:21:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QRFQEFAVMI7EWY7OJYSED5ARKS","target":"record","payload":{"canonical_record":{"source":{"id":"2607.22679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-11T04:58:00Z","cross_cats_sorted":[],"title_canon_sha256":"aeee99def32c094932d17ccc8bd5199e3933358c387637f8bdd1e8b325295b3c","abstract_canon_sha256":"8ad69b58ebf8e952a24379c124edf21769fd14e17c87f3a453321306f36d80e5"},"schema_version":"1.0"},"canonical_sha256":"844b021415623e4b63ee4e2441f411549cbdd6d74b334cab86809668fe4896fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:48.758061Z","signature_b64":"Jwy8qW1/YZQOvX0yj6WqTzui4feNJr6Uk3kN7bYu/uMcI1+A3SyxLBD669ojf2eGKn1BA/qBXflBq+fEhZE4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"844b021415623e4b63ee4e2441f411549cbdd6d74b334cab86809668fe4896fc","last_reissued_at":"2026-07-28T00:21:48.757212Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:48.757212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.22679","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":"2026-07-28T00:21:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nytZl3tGhc6tDmJQc+M1iodRyz5F+S8RXazodnjUO8fALOUn5dLFSJzsH9s9kWwjVSywbQLkZ1uQ1jySGK36CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:26:07.364058Z"},"content_sha256":"d31850d927a8197d3e1a489420c67787643a5254dc83395cce0148d2b9bd7b0e","schema_version":"1.0","event_id":"sha256:d31850d927a8197d3e1a489420c67787643a5254dc83395cce0148d2b9bd7b0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QRFQEFAVMI7EWY7OJYSED5ARKS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DOSA: A Tree-Guided, Self-Regressive Framework for Long Document Structure Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Benjamin Sowell, Bohou Li, Henry Lindeman, Mark Lindblad, Mehul Shah","submitted_at":"2026-07-11T04:58:00Z","abstract_excerpt":"In visually-rich documents, information is encoded not only in individual page objects such as tables, headers, and text blocks, but also in the structural relations among them, making document structure analysis fundamental to information retrieval and document understanding. However, accurately inferring such relations remains challenging in multi-page documents with long-range dependencies and heterogeneous layouts. To address this, we propose a tree-guided and self-regressive framework, termed DOcument Structure Analyzer (DOSA), for inferring relations among page objects and reconstructing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22679","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/2607.22679/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":"2026-07-28T00:21:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lnBwVFsrHmYq/CLzl7RIHg0UaV6Srj5PzVJy9HD7bHoOjCnIkF5eeHX65dWdtpzRqZaFJJk4EKT3FNlVHMsHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:26:07.364568Z"},"content_sha256":"b5bec43e46c54d405e8a78eeb2161a8e21e716e749aefd5a7b57f62628dcb000","schema_version":"1.0","event_id":"sha256:b5bec43e46c54d405e8a78eeb2161a8e21e716e749aefd5a7b57f62628dcb000"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QRFQEFAVMI7EWY7OJYSED5ARKS/bundle.json","state_url":"https://pith.science/pith/QRFQEFAVMI7EWY7OJYSED5ARKS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QRFQEFAVMI7EWY7OJYSED5ARKS/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":"2026-08-05T13:26:07Z","links":{"resolver":"https://pith.science/pith/QRFQEFAVMI7EWY7OJYSED5ARKS","bundle":"https://pith.science/pith/QRFQEFAVMI7EWY7OJYSED5ARKS/bundle.json","state":"https://pith.science/pith/QRFQEFAVMI7EWY7OJYSED5ARKS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QRFQEFAVMI7EWY7OJYSED5ARKS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QRFQEFAVMI7EWY7OJYSED5ARKS","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":"8ad69b58ebf8e952a24379c124edf21769fd14e17c87f3a453321306f36d80e5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-11T04:58:00Z","title_canon_sha256":"aeee99def32c094932d17ccc8bd5199e3933358c387637f8bdd1e8b325295b3c"},"schema_version":"1.0","source":{"id":"2607.22679","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22679","created_at":"2026-07-28T00:21:48Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22679v1","created_at":"2026-07-28T00:21:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22679","created_at":"2026-07-28T00:21:48Z"},{"alias_kind":"pith_short_12","alias_value":"QRFQEFAVMI7E","created_at":"2026-07-28T00:21:48Z"},{"alias_kind":"pith_short_16","alias_value":"QRFQEFAVMI7EWY7O","created_at":"2026-07-28T00:21:48Z"},{"alias_kind":"pith_short_8","alias_value":"QRFQEFAV","created_at":"2026-07-28T00:21:48Z"}],"graph_snapshots":[{"event_id":"sha256:b5bec43e46c54d405e8a78eeb2161a8e21e716e749aefd5a7b57f62628dcb000","target":"graph","created_at":"2026-07-28T00:21:48Z","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/2607.22679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In visually-rich documents, information is encoded not only in individual page objects such as tables, headers, and text blocks, but also in the structural relations among them, making document structure analysis fundamental to information retrieval and document understanding. However, accurately inferring such relations remains challenging in multi-page documents with long-range dependencies and heterogeneous layouts. To address this, we propose a tree-guided and self-regressive framework, termed DOcument Structure Analyzer (DOSA), for inferring relations among page objects and reconstructing","authors_text":"Benjamin Sowell, Bohou Li, Henry Lindeman, Mark Lindblad, Mehul Shah","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-11T04:58:00Z","title":"DOSA: A Tree-Guided, Self-Regressive Framework for Long Document Structure Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22679","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:d31850d927a8197d3e1a489420c67787643a5254dc83395cce0148d2b9bd7b0e","target":"record","created_at":"2026-07-28T00:21:48Z","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":"8ad69b58ebf8e952a24379c124edf21769fd14e17c87f3a453321306f36d80e5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-11T04:58:00Z","title_canon_sha256":"aeee99def32c094932d17ccc8bd5199e3933358c387637f8bdd1e8b325295b3c"},"schema_version":"1.0","source":{"id":"2607.22679","kind":"arxiv","version":1}},"canonical_sha256":"844b021415623e4b63ee4e2441f411549cbdd6d74b334cab86809668fe4896fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"844b021415623e4b63ee4e2441f411549cbdd6d74b334cab86809668fe4896fc","first_computed_at":"2026-07-28T00:21:48.757212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:21:48.757212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jwy8qW1/YZQOvX0yj6WqTzui4feNJr6Uk3kN7bYu/uMcI1+A3SyxLBD669ojf2eGKn1BA/qBXflBq+fEhZE4BQ==","signature_status":"signed_v1","signed_at":"2026-07-28T00:21:48.758061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22679","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d31850d927a8197d3e1a489420c67787643a5254dc83395cce0148d2b9bd7b0e","sha256:b5bec43e46c54d405e8a78eeb2161a8e21e716e749aefd5a7b57f62628dcb000"],"state_sha256":"40442a3baa2bf24923e4091498ff754492b04d6d6ef670e9628c4d1f16b387ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jwfX1XPQ+x3T2uWj8VVJL6ajZB/yADc1nXgVFIeX66kTzspUfORboKA6QKsY+ombYc6NXe55YkHIDZVzhZPnDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:26:07.369213Z","bundle_sha256":"9d41b92dbb46d65a88659d63d5676e2dbe18617a7cc2b5f22a4dc2414fed4714"}}