{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IX3TRHYF3YISOPFULWTDIKEE3J","short_pith_number":"pith:IX3TRHYF","canonical_record":{"source":{"id":"2305.05836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-10T01:52:08Z","cross_cats_sorted":[],"title_canon_sha256":"17ee2cdd128947bf948d70dd159c24c04f057531422cb92587c7943d0d905afe","abstract_canon_sha256":"cf61e557a084dac7ffff0c629d6457489ef634934e2ce81513a923e1ffa5d959"},"schema_version":"1.0"},"canonical_sha256":"45f7389f05de11273cb45da6342884da6c23b6e850edb598cae595c3fad1edfb","source":{"kind":"arxiv","id":"2305.05836","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05836","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05836v1","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05836","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"IX3TRHYF3YIS","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"IX3TRHYF3YISOPFU","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"IX3TRHYF","created_at":"2026-07-05T06:08:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IX3TRHYF3YISOPFULWTDIKEE3J","target":"record","payload":{"canonical_record":{"source":{"id":"2305.05836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-10T01:52:08Z","cross_cats_sorted":[],"title_canon_sha256":"17ee2cdd128947bf948d70dd159c24c04f057531422cb92587c7943d0d905afe","abstract_canon_sha256":"cf61e557a084dac7ffff0c629d6457489ef634934e2ce81513a923e1ffa5d959"},"schema_version":"1.0"},"canonical_sha256":"45f7389f05de11273cb45da6342884da6c23b6e850edb598cae595c3fad1edfb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:56.478102Z","signature_b64":"+mIIf42NeF8pU27966Ti73qgtoRDTs2dN/9WD6b2EzfXVKlH1W3kQXXBSiG5zj7qz1Z40ttWE9v2SG6KB1GEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45f7389f05de11273cb45da6342884da6c23b6e850edb598cae595c3fad1edfb","last_reissued_at":"2026-07-05T06:08:56.477760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:56.477760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.05836","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":"2026-07-05T06:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xdBG+KTtT2OPrVWg2wWdpG/7JiEOyJPlPai7AZLZ0tAzD3P1HRkDXI0ldEw+SCm+kq70/wIbb8APKOK80yA4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:55:26.431196Z"},"content_sha256":"875880b8007f45b237061b949ce9b9883aa85ec2d06fb3113da5934077f14ae9","schema_version":"1.0","event_id":"sha256:875880b8007f45b237061b949ce9b9883aa85ec2d06fb3113da5934077f14ae9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IX3TRHYF3YISOPFULWTDIKEE3J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extracting Complex Named Entities in Legal Documents via Weakly Supervised Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Abhinav Agrawal, Hsiu-Wei Yang","submitted_at":"2023-05-10T01:52:08Z","abstract_excerpt":"Accurate Named Entity Recognition (NER) is crucial for various information retrieval tasks in industry. However, despite significant progress in traditional NER methods, the extraction of Complex Named Entities remains a relatively unexplored area. In this paper, we propose a novel system that combines object detection for Document Layout Analysis (DLA) with weakly supervised learning to address the challenge of extracting discontinuous complex named entities in legal documents. Notably, to the best of our knowledge, this is the first work to apply weak supervision to DLA. Our experimental res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05836","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/2305.05836/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":"2026-07-05T06:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wvtc5m3hoHYBiakK5Dt8mQJueI5YQT3aZIMnVKrSREFWtTYhl4rCnQO4GUmbfnekyg7TawqvinENYLvCJbT+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:55:26.431584Z"},"content_sha256":"7c39b7dad62312655eca85dfac4a4f6a047695d9deaebd87a387cb47936ce75d","schema_version":"1.0","event_id":"sha256:7c39b7dad62312655eca85dfac4a4f6a047695d9deaebd87a387cb47936ce75d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IX3TRHYF3YISOPFULWTDIKEE3J/bundle.json","state_url":"https://pith.science/pith/IX3TRHYF3YISOPFULWTDIKEE3J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IX3TRHYF3YISOPFULWTDIKEE3J/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":"2026-07-08T13:55:26Z","links":{"resolver":"https://pith.science/pith/IX3TRHYF3YISOPFULWTDIKEE3J","bundle":"https://pith.science/pith/IX3TRHYF3YISOPFULWTDIKEE3J/bundle.json","state":"https://pith.science/pith/IX3TRHYF3YISOPFULWTDIKEE3J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IX3TRHYF3YISOPFULWTDIKEE3J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IX3TRHYF3YISOPFULWTDIKEE3J","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":"cf61e557a084dac7ffff0c629d6457489ef634934e2ce81513a923e1ffa5d959","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-10T01:52:08Z","title_canon_sha256":"17ee2cdd128947bf948d70dd159c24c04f057531422cb92587c7943d0d905afe"},"schema_version":"1.0","source":{"id":"2305.05836","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05836","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05836v1","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05836","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"IX3TRHYF3YIS","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"IX3TRHYF3YISOPFU","created_at":"2026-07-05T06:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"IX3TRHYF","created_at":"2026-07-05T06:08:56Z"}],"graph_snapshots":[{"event_id":"sha256:7c39b7dad62312655eca85dfac4a4f6a047695d9deaebd87a387cb47936ce75d","target":"graph","created_at":"2026-07-05T06:08:56Z","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/2305.05836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate Named Entity Recognition (NER) is crucial for various information retrieval tasks in industry. However, despite significant progress in traditional NER methods, the extraction of Complex Named Entities remains a relatively unexplored area. In this paper, we propose a novel system that combines object detection for Document Layout Analysis (DLA) with weakly supervised learning to address the challenge of extracting discontinuous complex named entities in legal documents. Notably, to the best of our knowledge, this is the first work to apply weak supervision to DLA. Our experimental res","authors_text":"Abhinav Agrawal, Hsiu-Wei Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-10T01:52:08Z","title":"Extracting Complex Named Entities in Legal Documents via Weakly Supervised Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05836","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":"sha256:875880b8007f45b237061b949ce9b9883aa85ec2d06fb3113da5934077f14ae9","target":"record","created_at":"2026-07-05T06:08:56Z","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":"cf61e557a084dac7ffff0c629d6457489ef634934e2ce81513a923e1ffa5d959","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-10T01:52:08Z","title_canon_sha256":"17ee2cdd128947bf948d70dd159c24c04f057531422cb92587c7943d0d905afe"},"schema_version":"1.0","source":{"id":"2305.05836","kind":"arxiv","version":1}},"canonical_sha256":"45f7389f05de11273cb45da6342884da6c23b6e850edb598cae595c3fad1edfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45f7389f05de11273cb45da6342884da6c23b6e850edb598cae595c3fad1edfb","first_computed_at":"2026-07-05T06:08:56.477760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:56.477760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+mIIf42NeF8pU27966Ti73qgtoRDTs2dN/9WD6b2EzfXVKlH1W3kQXXBSiG5zj7qz1Z40ttWE9v2SG6KB1GEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:56.478102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.05836","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:875880b8007f45b237061b949ce9b9883aa85ec2d06fb3113da5934077f14ae9","sha256:7c39b7dad62312655eca85dfac4a4f6a047695d9deaebd87a387cb47936ce75d"],"state_sha256":"66c2c5a21f612943f90838b82f41af08df8aba974b970a1ec833ccb7e3c8c899"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ANM9pFcYxI9qj5I3oKFa2zafFXaAa1gKaiMEOwkXW7R3C/hcP8HknWnJAQrIzeGJ6sBVImmdE/T7w/NxYrnBCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T13:55:26.433718Z","bundle_sha256":"2f603e7232a000afc4d4fee9c598f5d3f802ee5c8de1c17436522e9ed8d9a15b"}}