{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7C62S7VTFZM2IXPGYUVWPUXIVA","short_pith_number":"pith:7C62S7VT","canonical_record":{"source":{"id":"2306.08937","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T08:21:15Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"40fee562538c6c01dc49c76d844f67a90b20035e9aa0804436ce71b9563f0976","abstract_canon_sha256":"cada5e7b58535911a92925444657a221bb7b2c6222f41e65d81c7ce2de3614f0"},"schema_version":"1.0"},"canonical_sha256":"f8bda97eb32e59a45de6c52b67d2e8a81185f19e188c8b393f72ec1164f0ccbd","source":{"kind":"arxiv","id":"2306.08937","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08937","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08937v3","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08937","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"7C62S7VTFZM2","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"7C62S7VTFZM2IXPG","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"7C62S7VT","created_at":"2026-07-05T07:05:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7C62S7VTFZM2IXPGYUVWPUXIVA","target":"record","payload":{"canonical_record":{"source":{"id":"2306.08937","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T08:21:15Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"40fee562538c6c01dc49c76d844f67a90b20035e9aa0804436ce71b9563f0976","abstract_canon_sha256":"cada5e7b58535911a92925444657a221bb7b2c6222f41e65d81c7ce2de3614f0"},"schema_version":"1.0"},"canonical_sha256":"f8bda97eb32e59a45de6c52b67d2e8a81185f19e188c8b393f72ec1164f0ccbd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:31.400400Z","signature_b64":"3J/Q7qLeGprILOfj12Z1ellx5+YRYWyzu58WsSgKPKRWkd20XDbadZGwK4q+YCl8myUFm6WRDuhRssr6uMZVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8bda97eb32e59a45de6c52b67d2e8a81185f19e188c8b393f72ec1164f0ccbd","last_reissued_at":"2026-07-05T07:05:31.399870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:31.399870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.08937","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":"2026-07-05T07:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HDuSIHdxqJHThjlYkydMQUh+XN1f+kMeVcFrHlgQP9pPHFJsxtTbQ9jAe0XaVe2CWlP392uk/1t0UWupe/tpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:17:27.508545Z"},"content_sha256":"ae6a3b7dff846b5f7fc7859182a47f947333ec64e69a1c7798e674f3200d3b3a","schema_version":"1.0","event_id":"sha256:ae6a3b7dff846b5f7fc7859182a47f947333ec64e69a1c7798e674f3200d3b3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7C62S7VTFZM2IXPGYUVWPUXIVA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocumentNet: Bridging the Data Gap in Document Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Alexander G. Hauptmann, Hanjun Dai, Jiayi Chen, Jin Miao, Lijun Yu, Wei Wei, Xiaoyu Sun","submitted_at":"2023-06-15T08:21:15Z","abstract_excerpt":"Document understanding tasks, in particular, Visually-rich Document Entity Retrieval (VDER), have gained significant attention in recent years thanks to their broad applications in enterprise AI. However, publicly available data have been scarce for these tasks due to strict privacy constraints and high annotation costs. To make things worse, the non-overlapping entity spaces from different datasets hinder the knowledge transfer between document types. In this paper, we propose a method to collect massive-scale and weakly labeled data from the web to benefit the training of VDER models. The co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08937","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/2306.08937/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":"2026-07-05T07:05:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"giBbtZnkfQZQ3oc5w1WuL8puBjIF+Rng1t6Z/Dt0QunLTttrs+U5WAer4nZBPuXHyhXBSy99PgVXvjZLeR+AAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:17:27.509910Z"},"content_sha256":"fce58cdec1069a67780c66aa3456aecd7735fbe2749ccf849672227f8a942288","schema_version":"1.0","event_id":"sha256:fce58cdec1069a67780c66aa3456aecd7735fbe2749ccf849672227f8a942288"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7C62S7VTFZM2IXPGYUVWPUXIVA/bundle.json","state_url":"https://pith.science/pith/7C62S7VTFZM2IXPGYUVWPUXIVA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7C62S7VTFZM2IXPGYUVWPUXIVA/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":"2026-08-11T03:17:27Z","links":{"resolver":"https://pith.science/pith/7C62S7VTFZM2IXPGYUVWPUXIVA","bundle":"https://pith.science/pith/7C62S7VTFZM2IXPGYUVWPUXIVA/bundle.json","state":"https://pith.science/pith/7C62S7VTFZM2IXPGYUVWPUXIVA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7C62S7VTFZM2IXPGYUVWPUXIVA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7C62S7VTFZM2IXPGYUVWPUXIVA","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":"cada5e7b58535911a92925444657a221bb7b2c6222f41e65d81c7ce2de3614f0","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T08:21:15Z","title_canon_sha256":"40fee562538c6c01dc49c76d844f67a90b20035e9aa0804436ce71b9563f0976"},"schema_version":"1.0","source":{"id":"2306.08937","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08937","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08937v3","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08937","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"7C62S7VTFZM2","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"7C62S7VTFZM2IXPG","created_at":"2026-07-05T07:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"7C62S7VT","created_at":"2026-07-05T07:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:fce58cdec1069a67780c66aa3456aecd7735fbe2749ccf849672227f8a942288","target":"graph","created_at":"2026-07-05T07:05:31Z","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/2306.08937/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document understanding tasks, in particular, Visually-rich Document Entity Retrieval (VDER), have gained significant attention in recent years thanks to their broad applications in enterprise AI. However, publicly available data have been scarce for these tasks due to strict privacy constraints and high annotation costs. To make things worse, the non-overlapping entity spaces from different datasets hinder the knowledge transfer between document types. In this paper, we propose a method to collect massive-scale and weakly labeled data from the web to benefit the training of VDER models. The co","authors_text":"Alexander G. Hauptmann, Hanjun Dai, Jiayi Chen, Jin Miao, Lijun Yu, Wei Wei, Xiaoyu Sun","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T08:21:15Z","title":"DocumentNet: Bridging the Data Gap in Document Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08937","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:ae6a3b7dff846b5f7fc7859182a47f947333ec64e69a1c7798e674f3200d3b3a","target":"record","created_at":"2026-07-05T07:05:31Z","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":"cada5e7b58535911a92925444657a221bb7b2c6222f41e65d81c7ce2de3614f0","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T08:21:15Z","title_canon_sha256":"40fee562538c6c01dc49c76d844f67a90b20035e9aa0804436ce71b9563f0976"},"schema_version":"1.0","source":{"id":"2306.08937","kind":"arxiv","version":3}},"canonical_sha256":"f8bda97eb32e59a45de6c52b67d2e8a81185f19e188c8b393f72ec1164f0ccbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8bda97eb32e59a45de6c52b67d2e8a81185f19e188c8b393f72ec1164f0ccbd","first_computed_at":"2026-07-05T07:05:31.399870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:31.399870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3J/Q7qLeGprILOfj12Z1ellx5+YRYWyzu58WsSgKPKRWkd20XDbadZGwK4q+YCl8myUFm6WRDuhRssr6uMZVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:31.400400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08937","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae6a3b7dff846b5f7fc7859182a47f947333ec64e69a1c7798e674f3200d3b3a","sha256:fce58cdec1069a67780c66aa3456aecd7735fbe2749ccf849672227f8a942288"],"state_sha256":"4e5fd540331da3f3d0f9f82af18ad19cb34cdd18c0923c15057986cc230b0e79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tp1YcXYjWzJx9cQNvAmoi3Z4mO2PIkbMOZQBtN1P/gC1xMYd2iUjkf9bnnYyZFWo2BFMOf/mbwEX0axTunrhBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:17:27.580085Z","bundle_sha256":"2c8ac40f93e305ddc33ba8b4e878430ec8a97fc6fb6e2b2955450def5bcc8278"}}