{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7GLS5HEJYUXBUR72E4A76K7HRW","short_pith_number":"pith:7GLS5HEJ","canonical_record":{"source":{"id":"2407.01976","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T06:29:05Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"4d3ab0b080c3578ae5fff5b9ba9f760a0efd44ba3651f60f6612a50a98f8e06c","abstract_canon_sha256":"978a2bd2bf6617b11df644b951c9cd01cafd4afa6a2712cdd4fff2354dac0d3d"},"schema_version":"1.0"},"canonical_sha256":"f9972e9c89c52e1a47fa2701ff2be78d8d2bc8b3599bed66ddc22723b970d4da","source":{"kind":"arxiv","id":"2407.01976","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01976","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01976v3","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01976","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"7GLS5HEJYUXB","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"7GLS5HEJYUXBUR72","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"7GLS5HEJ","created_at":"2026-07-05T11:04:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7GLS5HEJYUXBUR72E4A76K7HRW","target":"record","payload":{"canonical_record":{"source":{"id":"2407.01976","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T06:29:05Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"4d3ab0b080c3578ae5fff5b9ba9f760a0efd44ba3651f60f6612a50a98f8e06c","abstract_canon_sha256":"978a2bd2bf6617b11df644b951c9cd01cafd4afa6a2712cdd4fff2354dac0d3d"},"schema_version":"1.0"},"canonical_sha256":"f9972e9c89c52e1a47fa2701ff2be78d8d2bc8b3599bed66ddc22723b970d4da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:38.207377Z","signature_b64":"Yg3vC0AII6Z5eY4NB4A/6T7dAeQX7ji8ml/HBOMECSMPYaRpBlFW6q8S0bYWHA/ClYp55oWQZqknQh/qjvf1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9972e9c89c52e1a47fa2701ff2be78d8d2bc8b3599bed66ddc22723b970d4da","last_reissued_at":"2026-07-05T11:04:38.206878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:38.206878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.01976","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xc0NpzDGfYkifJeG/nw7mraBmPAuwXjc85i74jdBT5YquAYnkmlJtg3gAc4mKy1/RDPJu1Cv0Ly2G8+hN+o7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:47:06.487192Z"},"content_sha256":"b74e792ff44050567106d65ef54805cd3c1c710025771e40dc6ce95f7e5349ce","schema_version":"1.0","event_id":"sha256:b74e792ff44050567106d65ef54805cd3c1c710025771e40dc6ce95f7e5349ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7GLS5HEJYUXBUR72E4A76K7HRW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CL","authors_text":"Binghong Wu, Can Huang, Haiyang Yu, Han Wang, Hao Feng, Hao Liu, Jinghui Lu, Jingqun Tang, Qi Liu, Yanjie Wang, YongJie Ye, Ziwei Yang","submitted_at":"2024-07-02T06:29:05Z","abstract_excerpt":"Recently, many studies have demonstrated that exclusively incorporating OCR-derived text and spatial layouts with large language models (LLMs) can be highly effective for document understanding tasks. However, existing methods that integrate spatial layouts with text have limitations, such as producing overly long text sequences or failing to fully leverage the autoregressive traits of LLMs. In this work, we introduce Interleaving Layout and Text in a Large Language Model (LayTextLLM)} for document understanding. LayTextLLM projects each bounding box to a single embedding and interleaves it wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01976","kind":"arxiv","version":3},"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/2407.01976/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":"2026-07-05T11:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4tlU0uh83hw+a2S38atGeTUjQutRv7sfqPu9zRrSjwweae9rT+V/4FSSrzzaKy49Oq/Fwr3tMWI5/XVyWbF2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:47:06.488015Z"},"content_sha256":"1bde4d29b1ebc2c36f2ed1ce39d3d00a2aaacd06c049f1c85c13da61c9745747","schema_version":"1.0","event_id":"sha256:1bde4d29b1ebc2c36f2ed1ce39d3d00a2aaacd06c049f1c85c13da61c9745747"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7GLS5HEJYUXBUR72E4A76K7HRW/bundle.json","state_url":"https://pith.science/pith/7GLS5HEJYUXBUR72E4A76K7HRW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7GLS5HEJYUXBUR72E4A76K7HRW/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":"2026-08-08T21:47:06Z","links":{"resolver":"https://pith.science/pith/7GLS5HEJYUXBUR72E4A76K7HRW","bundle":"https://pith.science/pith/7GLS5HEJYUXBUR72E4A76K7HRW/bundle.json","state":"https://pith.science/pith/7GLS5HEJYUXBUR72E4A76K7HRW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7GLS5HEJYUXBUR72E4A76K7HRW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7GLS5HEJYUXBUR72E4A76K7HRW","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":"978a2bd2bf6617b11df644b951c9cd01cafd4afa6a2712cdd4fff2354dac0d3d","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T06:29:05Z","title_canon_sha256":"4d3ab0b080c3578ae5fff5b9ba9f760a0efd44ba3651f60f6612a50a98f8e06c"},"schema_version":"1.0","source":{"id":"2407.01976","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01976","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01976v3","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01976","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"7GLS5HEJYUXB","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"7GLS5HEJYUXBUR72","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"7GLS5HEJ","created_at":"2026-07-05T11:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:1bde4d29b1ebc2c36f2ed1ce39d3d00a2aaacd06c049f1c85c13da61c9745747","target":"graph","created_at":"2026-07-05T11:04:38Z","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/2407.01976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, many studies have demonstrated that exclusively incorporating OCR-derived text and spatial layouts with large language models (LLMs) can be highly effective for document understanding tasks. However, existing methods that integrate spatial layouts with text have limitations, such as producing overly long text sequences or failing to fully leverage the autoregressive traits of LLMs. In this work, we introduce Interleaving Layout and Text in a Large Language Model (LayTextLLM)} for document understanding. LayTextLLM projects each bounding box to a single embedding and interleaves it wi","authors_text":"Binghong Wu, Can Huang, Haiyang Yu, Han Wang, Hao Feng, Hao Liu, Jinghui Lu, Jingqun Tang, Qi Liu, Yanjie Wang, YongJie Ye, Ziwei Yang","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T06:29:05Z","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01976","kind":"arxiv","version":3},"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:b74e792ff44050567106d65ef54805cd3c1c710025771e40dc6ce95f7e5349ce","target":"record","created_at":"2026-07-05T11:04:38Z","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":"978a2bd2bf6617b11df644b951c9cd01cafd4afa6a2712cdd4fff2354dac0d3d","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T06:29:05Z","title_canon_sha256":"4d3ab0b080c3578ae5fff5b9ba9f760a0efd44ba3651f60f6612a50a98f8e06c"},"schema_version":"1.0","source":{"id":"2407.01976","kind":"arxiv","version":3}},"canonical_sha256":"f9972e9c89c52e1a47fa2701ff2be78d8d2bc8b3599bed66ddc22723b970d4da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9972e9c89c52e1a47fa2701ff2be78d8d2bc8b3599bed66ddc22723b970d4da","first_computed_at":"2026-07-05T11:04:38.206878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:38.206878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yg3vC0AII6Z5eY4NB4A/6T7dAeQX7ji8ml/HBOMECSMPYaRpBlFW6q8S0bYWHA/ClYp55oWQZqknQh/qjvf1Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:38.207377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01976","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b74e792ff44050567106d65ef54805cd3c1c710025771e40dc6ce95f7e5349ce","sha256:1bde4d29b1ebc2c36f2ed1ce39d3d00a2aaacd06c049f1c85c13da61c9745747"],"state_sha256":"ad046d05f7068b2c0407e0ee5ccbc2f9de834b8ef856d12a089bd3ea097f1a64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HAIcrp7LIp0aKi8arpu4C3rNO3a+JVSe2GqxQ6d7H/xOIO0BzOc7bzJhFz2XdSf9t+ip14l1mMYhc0vCjSI6CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:47:06.492594Z","bundle_sha256":"cd13cee1513b5f07b19fae03b0e3d67aab870484feca6db28e2c6184cbd21563"}}