{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ETZRMLNP5DMO4NM2EYDYOX6T4R","short_pith_number":"pith:ETZRMLNP","canonical_record":{"source":{"id":"2604.10077","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-11T07:50:20Z","cross_cats_sorted":[],"title_canon_sha256":"8d032f08e70fe42056efb15fda5540f3c2b3094fb983bfb20f887dfcd15484ee","abstract_canon_sha256":"bc8f6dc30f57e918c480cc051c0b5a57323340fa719521d7e67648e51c9b64df"},"schema_version":"1.0"},"canonical_sha256":"24f3162dafe8d8ee359a2607875fd3e457477f95fc7c789f82dde1d87ce41c1f","source":{"kind":"arxiv","id":"2604.10077","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.10077","created_at":"2026-05-25T02:02:15Z"},{"alias_kind":"arxiv_version","alias_value":"2604.10077v2","created_at":"2026-05-25T02:02:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.10077","created_at":"2026-05-25T02:02:15Z"},{"alias_kind":"pith_short_12","alias_value":"ETZRMLNP5DMO","created_at":"2026-05-25T02:02:15Z"},{"alias_kind":"pith_short_16","alias_value":"ETZRMLNP5DMO4NM2","created_at":"2026-05-25T02:02:15Z"},{"alias_kind":"pith_short_8","alias_value":"ETZRMLNP","created_at":"2026-05-25T02:02:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ETZRMLNP5DMO4NM2EYDYOX6T4R","target":"record","payload":{"canonical_record":{"source":{"id":"2604.10077","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-11T07:50:20Z","cross_cats_sorted":[],"title_canon_sha256":"8d032f08e70fe42056efb15fda5540f3c2b3094fb983bfb20f887dfcd15484ee","abstract_canon_sha256":"bc8f6dc30f57e918c480cc051c0b5a57323340fa719521d7e67648e51c9b64df"},"schema_version":"1.0"},"canonical_sha256":"24f3162dafe8d8ee359a2607875fd3e457477f95fc7c789f82dde1d87ce41c1f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:15.148415Z","signature_b64":"aZNaZxGLsGqGIYZVvzltFvBdaKnCMn4MnTqZJsnrSEa+sMYhpm+h8++THGy9G3OwzJuZ3r5nZ6I+Icfyavv/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24f3162dafe8d8ee359a2607875fd3e457477f95fc7c789f82dde1d87ce41c1f","last_reissued_at":"2026-05-25T02:02:15.147631Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:15.147631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.10077","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:02:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nnhdZBVdwfeHvQnKN++9sVcEJrTWaqogsxTyNztW9OC1umk4B8kJfHMhngC846D0qhGV0U+1OlkHz5fTd1FdBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T16:24:08.623377Z"},"content_sha256":"52281fd9f439a548d03bce30d6f2d3fad49c31cbc19643488b851d2036782549","schema_version":"1.0","event_id":"sha256:52281fd9f439a548d03bce30d6f2d3fad49c31cbc19643488b851d2036782549"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ETZRMLNP5DMO4NM2EYDYOX6T4R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocRevive: A Unified Pipeline for Document Text Restoration","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"A unified pipeline restores damaged document text by combining OCR, occlusion detection, inpainting and diffusion models while preserving visual style.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayan Banerjee, Josep Llados, Kunal Purkayastha, Umapada Pal","submitted_at":"2026-04-11T07:50:20Z","abstract_excerpt":"In Document Understanding, the challenge of reconstructing damaged, occluded, or incomplete text remains a critical yet unexplored problem. Subsequent document understanding tasks can benefit from a document reconstruction process. In response, this paper presents a novel unified pipeline combining state-of-the-art Optical Character Recognition (OCR), advanced image analysis, masked language modeling, and diffusion-based models to restore and reconstruct text while preserving visual integrity. We create a synthetic dataset of 30{,}078 degraded document images that simulates diverse document de"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"this paper presents a novel unified pipeline combining state-of-the-art Optical Character Recognition (OCR), advanced image analysis, masked language modeling, and diffusion-based models to restore and reconstruct text while preserving visual integrity.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The synthetic dataset of 30,078 degraded document images accurately simulates diverse real-world document degradation scenarios and that the combined models produce semantically coherent and visually matching reconstructions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DocRevive builds a unified pipeline using OCR, image analysis, language models, and diffusion to reconstruct degraded document text, backed by a 30k-image synthetic dataset and the UCSM metric.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A unified pipeline restores damaged document text by combining OCR, occlusion detection, inpainting and diffusion models while preserving visual style.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"53b04187e5fc2a61ee5d16ed2351916a47e47ee158b49f332806e6fc695476fb"},"source":{"id":"2604.10077","kind":"arxiv","version":2},"verdict":{"id":"f778cabf-32e4-4761-8f26-7bef4b6977ec","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T16:54:31.437139Z","strongest_claim":"this paper presents a novel unified pipeline combining state-of-the-art Optical Character Recognition (OCR), advanced image analysis, masked language modeling, and diffusion-based models to restore and reconstruct text while preserving visual integrity.","one_line_summary":"DocRevive builds a unified pipeline using OCR, image analysis, language models, and diffusion to reconstruct degraded document text, backed by a 30k-image synthetic dataset and the UCSM metric.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The synthetic dataset of 30,078 degraded document images accurately simulates diverse real-world document degradation scenarios and that the combined models produce semantically coherent and visually matching reconstructions.","pith_extraction_headline":"A unified pipeline restores damaged document text by combining OCR, occlusion detection, inpainting and diffusion models while preserving visual style."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.10077/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":"f778cabf-32e4-4761-8f26-7bef4b6977ec"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:02:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VyI/c31+FxozKw11Il+SD5yBqRnb/dW+CAUDjRxT4KX/y73nmuYFXTJE5Cfz72qHXt8GV2orAfRfhN4uHwweAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T16:24:08.623846Z"},"content_sha256":"dcc06788f1f7aeb87213ba318c8a97bfc4eb87a9e9de0dbc83ae30694333e502","schema_version":"1.0","event_id":"sha256:dcc06788f1f7aeb87213ba318c8a97bfc4eb87a9e9de0dbc83ae30694333e502"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ETZRMLNP5DMO4NM2EYDYOX6T4R/bundle.json","state_url":"https://pith.science/pith/ETZRMLNP5DMO4NM2EYDYOX6T4R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ETZRMLNP5DMO4NM2EYDYOX6T4R/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":"2026-06-04T16:24:08Z","links":{"resolver":"https://pith.science/pith/ETZRMLNP5DMO4NM2EYDYOX6T4R","bundle":"https://pith.science/pith/ETZRMLNP5DMO4NM2EYDYOX6T4R/bundle.json","state":"https://pith.science/pith/ETZRMLNP5DMO4NM2EYDYOX6T4R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ETZRMLNP5DMO4NM2EYDYOX6T4R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ETZRMLNP5DMO4NM2EYDYOX6T4R","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":"bc8f6dc30f57e918c480cc051c0b5a57323340fa719521d7e67648e51c9b64df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-11T07:50:20Z","title_canon_sha256":"8d032f08e70fe42056efb15fda5540f3c2b3094fb983bfb20f887dfcd15484ee"},"schema_version":"1.0","source":{"id":"2604.10077","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.10077","created_at":"2026-05-25T02:02:15Z"},{"alias_kind":"arxiv_version","alias_value":"2604.10077v2","created_at":"2026-05-25T02:02:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.10077","created_at":"2026-05-25T02:02:15Z"},{"alias_kind":"pith_short_12","alias_value":"ETZRMLNP5DMO","created_at":"2026-05-25T02:02:15Z"},{"alias_kind":"pith_short_16","alias_value":"ETZRMLNP5DMO4NM2","created_at":"2026-05-25T02:02:15Z"},{"alias_kind":"pith_short_8","alias_value":"ETZRMLNP","created_at":"2026-05-25T02:02:15Z"}],"graph_snapshots":[{"event_id":"sha256:dcc06788f1f7aeb87213ba318c8a97bfc4eb87a9e9de0dbc83ae30694333e502","target":"graph","created_at":"2026-05-25T02:02:15Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"this paper presents a novel unified pipeline combining state-of-the-art Optical Character Recognition (OCR), advanced image analysis, masked language modeling, and diffusion-based models to restore and reconstruct text while preserving visual integrity."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The synthetic dataset of 30,078 degraded document images accurately simulates diverse real-world document degradation scenarios and that the combined models produce semantically coherent and visually matching reconstructions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DocRevive builds a unified pipeline using OCR, image analysis, language models, and diffusion to reconstruct degraded document text, backed by a 30k-image synthetic dataset and the UCSM metric."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A unified pipeline restores damaged document text by combining OCR, occlusion detection, inpainting and diffusion models while preserving visual style."}],"snapshot_sha256":"53b04187e5fc2a61ee5d16ed2351916a47e47ee158b49f332806e6fc695476fb"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.10077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Document Understanding, the challenge of reconstructing damaged, occluded, or incomplete text remains a critical yet unexplored problem. Subsequent document understanding tasks can benefit from a document reconstruction process. In response, this paper presents a novel unified pipeline combining state-of-the-art Optical Character Recognition (OCR), advanced image analysis, masked language modeling, and diffusion-based models to restore and reconstruct text while preserving visual integrity. We create a synthetic dataset of 30{,}078 degraded document images that simulates diverse document de","authors_text":"Ayan Banerjee, Josep Llados, Kunal Purkayastha, Umapada Pal","cross_cats":[],"headline":"A unified pipeline restores damaged document text by combining OCR, occlusion detection, inpainting and diffusion models while preserving visual style.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-11T07:50:20Z","title":"DocRevive: A Unified Pipeline for Document Text Restoration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.10077","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T16:54:31.437139Z","id":"f778cabf-32e4-4761-8f26-7bef4b6977ec","model_set":{"reader":"grok-4.3"},"one_line_summary":"DocRevive builds a unified pipeline using OCR, image analysis, language models, and diffusion to reconstruct degraded document text, backed by a 30k-image synthetic dataset and the UCSM metric.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A unified pipeline restores damaged document text by combining OCR, occlusion detection, inpainting and diffusion models while preserving visual style.","strongest_claim":"this paper presents a novel unified pipeline combining state-of-the-art Optical Character Recognition (OCR), advanced image analysis, masked language modeling, and diffusion-based models to restore and reconstruct text while preserving visual integrity.","weakest_assumption":"The synthetic dataset of 30,078 degraded document images accurately simulates diverse real-world document degradation scenarios and that the combined models produce semantically coherent and visually matching reconstructions."}},"verdict_id":"f778cabf-32e4-4761-8f26-7bef4b6977ec"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:52281fd9f439a548d03bce30d6f2d3fad49c31cbc19643488b851d2036782549","target":"record","created_at":"2026-05-25T02:02:15Z","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":"bc8f6dc30f57e918c480cc051c0b5a57323340fa719521d7e67648e51c9b64df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-11T07:50:20Z","title_canon_sha256":"8d032f08e70fe42056efb15fda5540f3c2b3094fb983bfb20f887dfcd15484ee"},"schema_version":"1.0","source":{"id":"2604.10077","kind":"arxiv","version":2}},"canonical_sha256":"24f3162dafe8d8ee359a2607875fd3e457477f95fc7c789f82dde1d87ce41c1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24f3162dafe8d8ee359a2607875fd3e457477f95fc7c789f82dde1d87ce41c1f","first_computed_at":"2026-05-25T02:02:15.147631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:15.147631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aZNaZxGLsGqGIYZVvzltFvBdaKnCMn4MnTqZJsnrSEa+sMYhpm+h8++THGy9G3OwzJuZ3r5nZ6I+Icfyavv/Ag==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:15.148415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.10077","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52281fd9f439a548d03bce30d6f2d3fad49c31cbc19643488b851d2036782549","sha256:dcc06788f1f7aeb87213ba318c8a97bfc4eb87a9e9de0dbc83ae30694333e502"],"state_sha256":"2452683dee24970cc69cd7c1f59992ca7a7f0d87d71f162f12722c90a860ab95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hEEo4/S1JCmAKrULfYPDxAorX5Qdx5PosrPYo5z7ZYSFWb94zoK759F3iZV+hY7XheJucJD/ylecfm2v1DgBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T16:24:08.626141Z","bundle_sha256":"f88bcb24c057b8e6027a853797193940e980041effba7b6b9156815785bda724"}}