{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GNEH6KHNO5HKYKXG2BKI3EW2ZT","short_pith_number":"pith:GNEH6KHN","canonical_record":{"source":{"id":"2408.15045","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T13:13:38Z","cross_cats_sorted":[],"title_canon_sha256":"1e650ee67a7609f123c2ae73ad996798303d479ae83f9a0f9c5f7f7f9f215a3c","abstract_canon_sha256":"99f16fe5e92fdfcb379352a1ae6f6d41c17f4ee266d4bb7a6a13138470777e9f"},"schema_version":"1.0"},"canonical_sha256":"33487f28ed774eac2ae6d0548d92dacce5e3c3a01d342ceeb58836d537e76f90","source":{"kind":"arxiv","id":"2408.15045","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15045","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15045v3","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15045","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"pith_short_12","alias_value":"GNEH6KHNO5HK","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"pith_short_16","alias_value":"GNEH6KHNO5HKYKXG","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"pith_short_8","alias_value":"GNEH6KHN","created_at":"2026-07-05T10:34:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GNEH6KHNO5HKYKXG2BKI3EW2ZT","target":"record","payload":{"canonical_record":{"source":{"id":"2408.15045","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T13:13:38Z","cross_cats_sorted":[],"title_canon_sha256":"1e650ee67a7609f123c2ae73ad996798303d479ae83f9a0f9c5f7f7f9f215a3c","abstract_canon_sha256":"99f16fe5e92fdfcb379352a1ae6f6d41c17f4ee266d4bb7a6a13138470777e9f"},"schema_version":"1.0"},"canonical_sha256":"33487f28ed774eac2ae6d0548d92dacce5e3c3a01d342ceeb58836d537e76f90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:09.934047Z","signature_b64":"jeVY4Zw0BgHNIQVDtDp0exH+Rkah5NEkf1H6ndL5Jxdue0RxvuCn2NAeANPpnLtPOTnb2GGkRtxyH0tx/nf6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33487f28ed774eac2ae6d0548d92dacce5e3c3a01d342ceeb58836d537e76f90","last_reissued_at":"2026-07-05T10:34:09.933091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:09.933091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.15045","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":"2026-07-05T10:34:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m6jlkfwU5kazYyPjtztbYffKNJYIqbNRYfSVi5QfS5uNfd5H0/g5cBvcrqKdC9Pk/tVbDjd46dCr2hFhHBPOAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:24:41.682113Z"},"content_sha256":"5d7b1ef0769ee31e05b9d7b8e2ee8c13e58be951cafc0d545c12f0062173de99","schema_version":"1.0","event_id":"sha256:5d7b1ef0769ee31e05b9d7b8e2ee8c13e58be951cafc0d545c12f0062173de99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GNEH6KHNO5HKYKXG2BKI3EW2ZT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengyu Wang, Hongliang Li, Jiapeng Wang, Jun Huang, Lianwen Jin, Wenhui Liao","submitted_at":"2024-08-27T13:13:38Z","abstract_excerpt":"Text-rich document understanding (TDU) requires comprehensive analysis of documents containing substantial textual content and complex layouts. While Multimodal Large Language Models (MLLMs) have achieved fast progress in this domain, existing approaches either demand significant computational resources or struggle with effective multi-modal integration. In this paper, we introduce DocLayLLM, an efficient multi-modal extension of LLMs specifically designed for TDU. By lightly integrating visual patch tokens and 2D positional tokens into LLMs' input and encoding the document content using the L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15045","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/2408.15045/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":"2026-07-05T10:34:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6tw6PUo34Qi4zG9P4wE9wMy/B3r2N8kSaguzudlpvK8neasQddeie1ZA1eN6pcXzHZFOych9bSphOJX2gYhBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:24:41.682953Z"},"content_sha256":"79c85344cf5624c63e7b05568dcd2d7b385deeddbd9ce089e07cc62e53383455","schema_version":"1.0","event_id":"sha256:79c85344cf5624c63e7b05568dcd2d7b385deeddbd9ce089e07cc62e53383455"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GNEH6KHNO5HKYKXG2BKI3EW2ZT/bundle.json","state_url":"https://pith.science/pith/GNEH6KHNO5HKYKXG2BKI3EW2ZT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GNEH6KHNO5HKYKXG2BKI3EW2ZT/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":"2026-08-07T01:24:41Z","links":{"resolver":"https://pith.science/pith/GNEH6KHNO5HKYKXG2BKI3EW2ZT","bundle":"https://pith.science/pith/GNEH6KHNO5HKYKXG2BKI3EW2ZT/bundle.json","state":"https://pith.science/pith/GNEH6KHNO5HKYKXG2BKI3EW2ZT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GNEH6KHNO5HKYKXG2BKI3EW2ZT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GNEH6KHNO5HKYKXG2BKI3EW2ZT","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":"99f16fe5e92fdfcb379352a1ae6f6d41c17f4ee266d4bb7a6a13138470777e9f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T13:13:38Z","title_canon_sha256":"1e650ee67a7609f123c2ae73ad996798303d479ae83f9a0f9c5f7f7f9f215a3c"},"schema_version":"1.0","source":{"id":"2408.15045","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15045","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15045v3","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15045","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"pith_short_12","alias_value":"GNEH6KHNO5HK","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"pith_short_16","alias_value":"GNEH6KHNO5HKYKXG","created_at":"2026-07-05T10:34:09Z"},{"alias_kind":"pith_short_8","alias_value":"GNEH6KHN","created_at":"2026-07-05T10:34:09Z"}],"graph_snapshots":[{"event_id":"sha256:79c85344cf5624c63e7b05568dcd2d7b385deeddbd9ce089e07cc62e53383455","target":"graph","created_at":"2026-07-05T10:34:09Z","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/2408.15045/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-rich document understanding (TDU) requires comprehensive analysis of documents containing substantial textual content and complex layouts. While Multimodal Large Language Models (MLLMs) have achieved fast progress in this domain, existing approaches either demand significant computational resources or struggle with effective multi-modal integration. In this paper, we introduce DocLayLLM, an efficient multi-modal extension of LLMs specifically designed for TDU. By lightly integrating visual patch tokens and 2D positional tokens into LLMs' input and encoding the document content using the L","authors_text":"Chengyu Wang, Hongliang Li, Jiapeng Wang, Jun Huang, Lianwen Jin, Wenhui Liao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T13:13:38Z","title":"DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15045","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":"sha256:5d7b1ef0769ee31e05b9d7b8e2ee8c13e58be951cafc0d545c12f0062173de99","target":"record","created_at":"2026-07-05T10:34:09Z","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":"99f16fe5e92fdfcb379352a1ae6f6d41c17f4ee266d4bb7a6a13138470777e9f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T13:13:38Z","title_canon_sha256":"1e650ee67a7609f123c2ae73ad996798303d479ae83f9a0f9c5f7f7f9f215a3c"},"schema_version":"1.0","source":{"id":"2408.15045","kind":"arxiv","version":3}},"canonical_sha256":"33487f28ed774eac2ae6d0548d92dacce5e3c3a01d342ceeb58836d537e76f90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33487f28ed774eac2ae6d0548d92dacce5e3c3a01d342ceeb58836d537e76f90","first_computed_at":"2026-07-05T10:34:09.933091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:09.933091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jeVY4Zw0BgHNIQVDtDp0exH+Rkah5NEkf1H6ndL5Jxdue0RxvuCn2NAeANPpnLtPOTnb2GGkRtxyH0tx/nf6BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:09.934047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15045","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d7b1ef0769ee31e05b9d7b8e2ee8c13e58be951cafc0d545c12f0062173de99","sha256:79c85344cf5624c63e7b05568dcd2d7b385deeddbd9ce089e07cc62e53383455"],"state_sha256":"8815aae2bf0543e95dd2a5d2a806314e6d680d2e64e39db2142b604652061ccb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nzhFVWG64InU7snO+/h48xi1ZkOuBSwV5U+jUDSnKY59aKy0qfAtGaFmxzyfv2K/UTgrC0MN6k8sSsdxJsx/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:24:41.689550Z","bundle_sha256":"4132d70dc83574f96bd5b7d87341204291fec63c73b301473e8616e781fb51a3"}}