{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:73JYAKKE7DZHRDOFV3WY7R5JQB","short_pith_number":"pith:73JYAKKE","canonical_record":{"source":{"id":"2412.12902","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T13:26:31Z","cross_cats_sorted":[],"title_canon_sha256":"cfc0bbe91b82a23edc462cc0d9f39039a474750b165adb8bcdb67734b1543c8f","abstract_canon_sha256":"db93f9be8f2cea469f6068ce5398a83ddc5e9f4f854a399837dee778e3b457fc"},"schema_version":"1.0"},"canonical_sha256":"fed3802944f8f2788dc5aeed8fc7a9806276e8275d1da37f2ba21bfea786ff31","source":{"kind":"arxiv","id":"2412.12902","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12902","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12902v2","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12902","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_12","alias_value":"73JYAKKE7DZH","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_16","alias_value":"73JYAKKE7DZHRDOF","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_8","alias_value":"73JYAKKE","created_at":"2026-07-05T10:27:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:73JYAKKE7DZHRDOFV3WY7R5JQB","target":"record","payload":{"canonical_record":{"source":{"id":"2412.12902","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T13:26:31Z","cross_cats_sorted":[],"title_canon_sha256":"cfc0bbe91b82a23edc462cc0d9f39039a474750b165adb8bcdb67734b1543c8f","abstract_canon_sha256":"db93f9be8f2cea469f6068ce5398a83ddc5e9f4f854a399837dee778e3b457fc"},"schema_version":"1.0"},"canonical_sha256":"fed3802944f8f2788dc5aeed8fc7a9806276e8275d1da37f2ba21bfea786ff31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:21.912867Z","signature_b64":"SPJ1ouLRodd5Cl1QRfo4ERuLU6YCAxXLQnfPQ4xspt7C+FMYej53T52gc9tg9RqKc+9gelXyD4g84ALFwb2UCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fed3802944f8f2788dc5aeed8fc7a9806276e8275d1da37f2ba21bfea786ff31","last_reissued_at":"2026-07-05T10:27:21.912475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:21.912475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.12902","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":"2026-07-05T10:27:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h0X9DCsO+UIFxrvP8Xke1ffdNbVG48a6Bz1HIN2c+SRWk6SyH5alwJ25bKfsq++wzwxDKH8bCOHKMHDsVWjOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:31:35.715513Z"},"content_sha256":"8151ee250775fe899a20caee5add2070ae95d0a043c63fcad0d3e00918da3c2c","schema_version":"1.0","event_id":"sha256:8151ee250775fe899a20caee5add2070ae95d0a043c63fcad0d3e00918da3c2c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:73JYAKKE7DZHRDOFV3WY7R5JQB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DoPTA: Improving Document Layout Analysis using Patch-Text Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mausoom Sarkar, Nikitha SR, Tarun Ram Menta","submitted_at":"2024-12-17T13:26:31Z","abstract_excerpt":"The advent of multimodal learning has brought a significant improvement in document AI. Documents are now treated as multimodal entities, incorporating both textual and visual information for downstream analysis. However, works in this space are often focused on the textual aspect, using the visual space as auxiliary information. While some works have explored pure vision based techniques for document image understanding, they require OCR identified text as input during inference, or do not align with text in their learning procedure. Therefore, we present a novel image-text alignment techniqu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12902","kind":"arxiv","version":2},"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/2412.12902/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":"2026-07-05T10:27:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4ZrnS8iF1VTAL8sD0UaNFIguKBygNO45ELIEsIW6ZIF4V3tT1fikt8hg7eMPnQnI1at2f4gYZBaU3GWe/56VCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:31:35.716050Z"},"content_sha256":"862b376088429ab0519a8dbcdaa9b4da698b389c01402bb0c6a8cec326913b46","schema_version":"1.0","event_id":"sha256:862b376088429ab0519a8dbcdaa9b4da698b389c01402bb0c6a8cec326913b46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/73JYAKKE7DZHRDOFV3WY7R5JQB/bundle.json","state_url":"https://pith.science/pith/73JYAKKE7DZHRDOFV3WY7R5JQB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/73JYAKKE7DZHRDOFV3WY7R5JQB/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":"2026-08-18T10:31:35Z","links":{"resolver":"https://pith.science/pith/73JYAKKE7DZHRDOFV3WY7R5JQB","bundle":"https://pith.science/pith/73JYAKKE7DZHRDOFV3WY7R5JQB/bundle.json","state":"https://pith.science/pith/73JYAKKE7DZHRDOFV3WY7R5JQB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/73JYAKKE7DZHRDOFV3WY7R5JQB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:73JYAKKE7DZHRDOFV3WY7R5JQB","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":"db93f9be8f2cea469f6068ce5398a83ddc5e9f4f854a399837dee778e3b457fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T13:26:31Z","title_canon_sha256":"cfc0bbe91b82a23edc462cc0d9f39039a474750b165adb8bcdb67734b1543c8f"},"schema_version":"1.0","source":{"id":"2412.12902","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12902","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12902v2","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12902","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_12","alias_value":"73JYAKKE7DZH","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_16","alias_value":"73JYAKKE7DZHRDOF","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_8","alias_value":"73JYAKKE","created_at":"2026-07-05T10:27:21Z"}],"graph_snapshots":[{"event_id":"sha256:862b376088429ab0519a8dbcdaa9b4da698b389c01402bb0c6a8cec326913b46","target":"graph","created_at":"2026-07-05T10:27:21Z","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/2412.12902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of multimodal learning has brought a significant improvement in document AI. Documents are now treated as multimodal entities, incorporating both textual and visual information for downstream analysis. However, works in this space are often focused on the textual aspect, using the visual space as auxiliary information. While some works have explored pure vision based techniques for document image understanding, they require OCR identified text as input during inference, or do not align with text in their learning procedure. Therefore, we present a novel image-text alignment techniqu","authors_text":"Mausoom Sarkar, Nikitha SR, Tarun Ram Menta","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T13:26:31Z","title":"DoPTA: Improving Document Layout Analysis using Patch-Text Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12902","kind":"arxiv","version":2},"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":"sha256:8151ee250775fe899a20caee5add2070ae95d0a043c63fcad0d3e00918da3c2c","target":"record","created_at":"2026-07-05T10:27:21Z","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":"db93f9be8f2cea469f6068ce5398a83ddc5e9f4f854a399837dee778e3b457fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T13:26:31Z","title_canon_sha256":"cfc0bbe91b82a23edc462cc0d9f39039a474750b165adb8bcdb67734b1543c8f"},"schema_version":"1.0","source":{"id":"2412.12902","kind":"arxiv","version":2}},"canonical_sha256":"fed3802944f8f2788dc5aeed8fc7a9806276e8275d1da37f2ba21bfea786ff31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fed3802944f8f2788dc5aeed8fc7a9806276e8275d1da37f2ba21bfea786ff31","first_computed_at":"2026-07-05T10:27:21.912475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:21.912475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SPJ1ouLRodd5Cl1QRfo4ERuLU6YCAxXLQnfPQ4xspt7C+FMYej53T52gc9tg9RqKc+9gelXyD4g84ALFwb2UCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:21.912867Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12902","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8151ee250775fe899a20caee5add2070ae95d0a043c63fcad0d3e00918da3c2c","sha256:862b376088429ab0519a8dbcdaa9b4da698b389c01402bb0c6a8cec326913b46"],"state_sha256":"4d1ab750c229fefc6c116c8a4eec9c2f953d25ade141bfaef0603ab622e5c29c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pntFwHL4jzEy0rGjqYu3easrqHgE4DmpFW+W0YdnfRvdEbi6qeT+NBqB0sxKayRUVFZn2kBh8R8GxBYeVG5TCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T10:31:35.719542Z","bundle_sha256":"c31476de732355836a8d74579ac9fe83fec5f5d92847b267f0671f3fc9dd97a9"}}