{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XMKDR3AWI5MXFLYCYABXNKU6SD","short_pith_number":"pith:XMKDR3AW","canonical_record":{"source":{"id":"2410.03061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T00:53:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ad6475f39656b8f51f87f2f955533a0dfa9f6a58e9bb274afac54d3c83304119","abstract_canon_sha256":"a879aa11d5048405c93ea6ca38873712466fbe07119835b21c5aad78179e2bf9"},"schema_version":"1.0"},"canonical_sha256":"bb1438ec16475972af02c00376aa9e90c22820336131c9da82518a10603d3107","source":{"kind":"arxiv","id":"2410.03061","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03061","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03061v1","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03061","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"XMKDR3AWI5MX","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"XMKDR3AWI5MXFLYC","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"XMKDR3AW","created_at":"2026-07-05T09:15:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XMKDR3AWI5MXFLYCYABXNKU6SD","target":"record","payload":{"canonical_record":{"source":{"id":"2410.03061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T00:53:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ad6475f39656b8f51f87f2f955533a0dfa9f6a58e9bb274afac54d3c83304119","abstract_canon_sha256":"a879aa11d5048405c93ea6ca38873712466fbe07119835b21c5aad78179e2bf9"},"schema_version":"1.0"},"canonical_sha256":"bb1438ec16475972af02c00376aa9e90c22820336131c9da82518a10603d3107","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:43.592443Z","signature_b64":"dtNKlHcNmUWSJR/46kf9Dbwmo2IuGlQnuO4gjSI+vnYSJSWXit9GEgC0n4nJKmax+o0RVq7+g6/5iDkfn92SAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb1438ec16475972af02c00376aa9e90c22820336131c9da82518a10603d3107","last_reissued_at":"2026-07-05T09:15:43.591959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:43.591959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.03061","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o4ya8LC0MEaEXGzdjBOh4GHohgPAexLQvqE0cjKguDHPee34Wj8z1Wo98hut17p3rClQyB3wj1xi5OpL1SuWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:07:01.811206Z"},"content_sha256":"713f55b30a1c928690afeae88a5ef27afccbcb40e0043fb18d6f8e2fedf52aba","schema_version":"1.0","event_id":"sha256:713f55b30a1c928690afeae88a5ef27afccbcb40e0043fb18d6f8e2fedf52aba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XMKDR3AWI5MXFLYCYABXNKU6SD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Haofu Liao, Peng Tang, Ravi Kumar Satzoda, R. Manmatha, Srikar Appalaraju, Stefano Soatto, Sungnyun Kim, Vijay Mahadevan, Zhuowen Tu","submitted_at":"2024-10-04T00:53:32Z","abstract_excerpt":"Visual document understanding (VDU) is a challenging task that involves understanding documents across various modalities (text and image) and layouts (forms, tables, etc.). This study aims to enhance generalizability of small VDU models by distilling knowledge from LLMs. We identify that directly prompting LLMs often fails to generate informative and useful data. In response, we present a new framework (called DocKD) that enriches the data generation process by integrating external document knowledge. Specifically, we provide an LLM with various document elements like key-value pairs, layouts"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03061","kind":"arxiv","version":1},"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/2410.03061/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":"2026-07-05T09:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DJKQiNBS7TVFU9RCj2NCFi9bdmT1rYgB0hMJSttk3HwF8w/I15J/KhyA/8fVCQ/j35+Uz8mljZkc64gDh7kZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:07:01.811687Z"},"content_sha256":"320b69a1afed08ea14c89e5f01dc6bce3b76c75fc24644825126054eb7680424","schema_version":"1.0","event_id":"sha256:320b69a1afed08ea14c89e5f01dc6bce3b76c75fc24644825126054eb7680424"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XMKDR3AWI5MXFLYCYABXNKU6SD/bundle.json","state_url":"https://pith.science/pith/XMKDR3AWI5MXFLYCYABXNKU6SD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XMKDR3AWI5MXFLYCYABXNKU6SD/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":"2026-08-14T18:07:01Z","links":{"resolver":"https://pith.science/pith/XMKDR3AWI5MXFLYCYABXNKU6SD","bundle":"https://pith.science/pith/XMKDR3AWI5MXFLYCYABXNKU6SD/bundle.json","state":"https://pith.science/pith/XMKDR3AWI5MXFLYCYABXNKU6SD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XMKDR3AWI5MXFLYCYABXNKU6SD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XMKDR3AWI5MXFLYCYABXNKU6SD","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":"a879aa11d5048405c93ea6ca38873712466fbe07119835b21c5aad78179e2bf9","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T00:53:32Z","title_canon_sha256":"ad6475f39656b8f51f87f2f955533a0dfa9f6a58e9bb274afac54d3c83304119"},"schema_version":"1.0","source":{"id":"2410.03061","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03061","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03061v1","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03061","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"XMKDR3AWI5MX","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"XMKDR3AWI5MXFLYC","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"XMKDR3AW","created_at":"2026-07-05T09:15:43Z"}],"graph_snapshots":[{"event_id":"sha256:320b69a1afed08ea14c89e5f01dc6bce3b76c75fc24644825126054eb7680424","target":"graph","created_at":"2026-07-05T09:15:43Z","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/2410.03061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual document understanding (VDU) is a challenging task that involves understanding documents across various modalities (text and image) and layouts (forms, tables, etc.). This study aims to enhance generalizability of small VDU models by distilling knowledge from LLMs. We identify that directly prompting LLMs often fails to generate informative and useful data. In response, we present a new framework (called DocKD) that enriches the data generation process by integrating external document knowledge. Specifically, we provide an LLM with various document elements like key-value pairs, layouts","authors_text":"Haofu Liao, Peng Tang, Ravi Kumar Satzoda, R. Manmatha, Srikar Appalaraju, Stefano Soatto, Sungnyun Kim, Vijay Mahadevan, Zhuowen Tu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T00:53:32Z","title":"DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03061","kind":"arxiv","version":1},"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":"sha256:713f55b30a1c928690afeae88a5ef27afccbcb40e0043fb18d6f8e2fedf52aba","target":"record","created_at":"2026-07-05T09:15:43Z","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":"a879aa11d5048405c93ea6ca38873712466fbe07119835b21c5aad78179e2bf9","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T00:53:32Z","title_canon_sha256":"ad6475f39656b8f51f87f2f955533a0dfa9f6a58e9bb274afac54d3c83304119"},"schema_version":"1.0","source":{"id":"2410.03061","kind":"arxiv","version":1}},"canonical_sha256":"bb1438ec16475972af02c00376aa9e90c22820336131c9da82518a10603d3107","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb1438ec16475972af02c00376aa9e90c22820336131c9da82518a10603d3107","first_computed_at":"2026-07-05T09:15:43.591959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:43.591959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dtNKlHcNmUWSJR/46kf9Dbwmo2IuGlQnuO4gjSI+vnYSJSWXit9GEgC0n4nJKmax+o0RVq7+g6/5iDkfn92SAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:43.592443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03061","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:713f55b30a1c928690afeae88a5ef27afccbcb40e0043fb18d6f8e2fedf52aba","sha256:320b69a1afed08ea14c89e5f01dc6bce3b76c75fc24644825126054eb7680424"],"state_sha256":"16ff55840b51d7896b241b3a5a3ba80a22616ef0d0cafb1b6999d19e6e4f221e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sSXN02OJfP2j9aaduaDEyPGB4UXtduppTV0eVVuXpckxMPBK5yp1+bETMyWou2cMfiPS/gpxl9msDsxHpcWnBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T18:07:01.816298Z","bundle_sha256":"6ea2dd16605542eeb8142e19052830f28756a4502ee0f22e079c91bde7d851d1"}}