{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VWMSU2HLE6EBDLEOASC7IGGHHA","short_pith_number":"pith:VWMSU2HL","canonical_record":{"source":{"id":"2108.04539","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-10T09:30:23Z","cross_cats_sorted":[],"title_canon_sha256":"0e4577012e3e18bb47549be8bb95d27d233f8e3eec8cb7768c9f08be4e6951b9","abstract_canon_sha256":"eed30dca809ce639b5038175937c152116c4fcc39d7c87f380514d995f0d007f"},"schema_version":"1.0"},"canonical_sha256":"ad992a68eb278811ac8e0485f418c738129c975686f2a8cc3fc76c6f9de1cd48","source":{"kind":"arxiv","id":"2108.04539","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.04539","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"arxiv_version","alias_value":"2108.04539v5","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04539","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"pith_short_12","alias_value":"VWMSU2HLE6EB","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"pith_short_16","alias_value":"VWMSU2HLE6EBDLEO","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"pith_short_8","alias_value":"VWMSU2HL","created_at":"2026-07-05T04:11:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VWMSU2HLE6EBDLEOASC7IGGHHA","target":"record","payload":{"canonical_record":{"source":{"id":"2108.04539","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-10T09:30:23Z","cross_cats_sorted":[],"title_canon_sha256":"0e4577012e3e18bb47549be8bb95d27d233f8e3eec8cb7768c9f08be4e6951b9","abstract_canon_sha256":"eed30dca809ce639b5038175937c152116c4fcc39d7c87f380514d995f0d007f"},"schema_version":"1.0"},"canonical_sha256":"ad992a68eb278811ac8e0485f418c738129c975686f2a8cc3fc76c6f9de1cd48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:25.896362Z","signature_b64":"2809eaU70l357S4WocC3w/hbnQCtjJRbIYQDd/VPDbVEEacJidNWzdeplQAlUX0bbUAVRk3kSGosfkkqj9V0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad992a68eb278811ac8e0485f418c738129c975686f2a8cc3fc76c6f9de1cd48","last_reissued_at":"2026-07-05T04:11:25.895869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:25.895869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.04539","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:11:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QyDZV5zbl7mG3ZCtc4kOxZYAaBfRAVebq7KAh3NUCdrNK+YnMOaFsExYvLLqjdHFnAo0oaW34QetPTMvj7iOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:46:57.858863Z"},"content_sha256":"c3cb377f65ef1219ec3ea7fb54b92255bdabbc8f6411427b98729349e8d0dbb6","schema_version":"1.0","event_id":"sha256:c3cb377f65ef1219ec3ea7fb54b92255bdabbc8f6411427b98729349e8d0dbb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VWMSU2HLE6EBDLEOASC7IGGHHA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daehyun Nam, Donghyun Kim, Mingi Ji, Sungrae Park, Teakgyu Hong, Wonseok Hwang","submitted_at":"2021-08-10T09:30:23Z","abstract_excerpt":"Key information extraction (KIE) from document images requires understanding the contextual and spatial semantics of texts in two-dimensional (2D) space. Many recent studies try to solve the task by developing pre-trained language models focusing on combining visual features from document images with texts and their layout. On the other hand, this paper tackles the problem by going back to the basic: effective combination of text and layout. Specifically, we propose a pre-trained language model, named BROS (BERT Relying On Spatiality), that encodes relative positions of texts in 2D space and l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04539","kind":"arxiv","version":5},"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/2108.04539/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":"2026-07-05T04:11:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3NQjhxoQxzEKs4cpaqZoLWM94AuHfFSZeebPVSLJeAZLoIRHEWMEifw8N8gIQo4iLMuf/iSrWywox+iWnZPcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:46:57.859915Z"},"content_sha256":"cf8f5ee8768c4d7177288fa56176a0ffa9b2eb825f78291103b3620a8c19daa6","schema_version":"1.0","event_id":"sha256:cf8f5ee8768c4d7177288fa56176a0ffa9b2eb825f78291103b3620a8c19daa6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VWMSU2HLE6EBDLEOASC7IGGHHA/bundle.json","state_url":"https://pith.science/pith/VWMSU2HLE6EBDLEOASC7IGGHHA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VWMSU2HLE6EBDLEOASC7IGGHHA/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":"2026-08-12T06:46:57Z","links":{"resolver":"https://pith.science/pith/VWMSU2HLE6EBDLEOASC7IGGHHA","bundle":"https://pith.science/pith/VWMSU2HLE6EBDLEOASC7IGGHHA/bundle.json","state":"https://pith.science/pith/VWMSU2HLE6EBDLEOASC7IGGHHA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VWMSU2HLE6EBDLEOASC7IGGHHA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VWMSU2HLE6EBDLEOASC7IGGHHA","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":"eed30dca809ce639b5038175937c152116c4fcc39d7c87f380514d995f0d007f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-10T09:30:23Z","title_canon_sha256":"0e4577012e3e18bb47549be8bb95d27d233f8e3eec8cb7768c9f08be4e6951b9"},"schema_version":"1.0","source":{"id":"2108.04539","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.04539","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"arxiv_version","alias_value":"2108.04539v5","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04539","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"pith_short_12","alias_value":"VWMSU2HLE6EB","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"pith_short_16","alias_value":"VWMSU2HLE6EBDLEO","created_at":"2026-07-05T04:11:25Z"},{"alias_kind":"pith_short_8","alias_value":"VWMSU2HL","created_at":"2026-07-05T04:11:25Z"}],"graph_snapshots":[{"event_id":"sha256:cf8f5ee8768c4d7177288fa56176a0ffa9b2eb825f78291103b3620a8c19daa6","target":"graph","created_at":"2026-07-05T04:11:25Z","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/2108.04539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Key information extraction (KIE) from document images requires understanding the contextual and spatial semantics of texts in two-dimensional (2D) space. Many recent studies try to solve the task by developing pre-trained language models focusing on combining visual features from document images with texts and their layout. On the other hand, this paper tackles the problem by going back to the basic: effective combination of text and layout. Specifically, we propose a pre-trained language model, named BROS (BERT Relying On Spatiality), that encodes relative positions of texts in 2D space and l","authors_text":"Daehyun Nam, Donghyun Kim, Mingi Ji, Sungrae Park, Teakgyu Hong, Wonseok Hwang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-10T09:30:23Z","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04539","kind":"arxiv","version":5},"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:c3cb377f65ef1219ec3ea7fb54b92255bdabbc8f6411427b98729349e8d0dbb6","target":"record","created_at":"2026-07-05T04:11:25Z","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":"eed30dca809ce639b5038175937c152116c4fcc39d7c87f380514d995f0d007f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-10T09:30:23Z","title_canon_sha256":"0e4577012e3e18bb47549be8bb95d27d233f8e3eec8cb7768c9f08be4e6951b9"},"schema_version":"1.0","source":{"id":"2108.04539","kind":"arxiv","version":5}},"canonical_sha256":"ad992a68eb278811ac8e0485f418c738129c975686f2a8cc3fc76c6f9de1cd48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad992a68eb278811ac8e0485f418c738129c975686f2a8cc3fc76c6f9de1cd48","first_computed_at":"2026-07-05T04:11:25.895869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:11:25.895869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2809eaU70l357S4WocC3w/hbnQCtjJRbIYQDd/VPDbVEEacJidNWzdeplQAlUX0bbUAVRk3kSGosfkkqj9V0Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:11:25.896362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.04539","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3cb377f65ef1219ec3ea7fb54b92255bdabbc8f6411427b98729349e8d0dbb6","sha256:cf8f5ee8768c4d7177288fa56176a0ffa9b2eb825f78291103b3620a8c19daa6"],"state_sha256":"ec90fb011a4704607686749c3a88f52389de68e6181263bd4e09ac19ad7a7114"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X3iuPYhg8wOyXxLdkNJ1GkgVQ3hu1pf3nJ8KeL5DV7mDjAE6UN6KtG9i6yZPOXuoJn/xrb5yIQVKIMiX/BTBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T06:46:57.903670Z","bundle_sha256":"c9f76a6570405953a8dd5d5bac807943a1cbac63aeef880a595a5d5f1ecf436a"}}