{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SO5B7EZEKXLAIE7IYWCQ3ZOPHD","short_pith_number":"pith:SO5B7EZE","canonical_record":{"source":{"id":"2401.02992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-04T06:26:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d23e0b20e408d2060b260985c59fb63d6a16ecdcf6416152b654d3692dfc68c","abstract_canon_sha256":"1f5f71a982a2104c0f375efc6bc2452b0b0e14b6224414a714816762c9336054"},"schema_version":"1.0"},"canonical_sha256":"93ba1f932455d60413e8c5850de5cf38f50257e6f26d0b57328f7644ccde8fa3","source":{"kind":"arxiv","id":"2401.02992","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02992","created_at":"2026-07-05T07:31:00Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02992v1","created_at":"2026-07-05T07:31:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02992","created_at":"2026-07-05T07:31:00Z"},{"alias_kind":"pith_short_12","alias_value":"SO5B7EZEKXLA","created_at":"2026-07-05T07:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"SO5B7EZEKXLAIE7I","created_at":"2026-07-05T07:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"SO5B7EZE","created_at":"2026-07-05T07:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SO5B7EZEKXLAIE7IYWCQ3ZOPHD","target":"record","payload":{"canonical_record":{"source":{"id":"2401.02992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-04T06:26:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d23e0b20e408d2060b260985c59fb63d6a16ecdcf6416152b654d3692dfc68c","abstract_canon_sha256":"1f5f71a982a2104c0f375efc6bc2452b0b0e14b6224414a714816762c9336054"},"schema_version":"1.0"},"canonical_sha256":"93ba1f932455d60413e8c5850de5cf38f50257e6f26d0b57328f7644ccde8fa3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:00.641099Z","signature_b64":"A5Wkdot7SwoK3F3R4oHi1WvVhp1ldbZg72io4nQp8IiustpRTXt57PiQ6EPNr7MdpUVluqk6K9v68FrTbmBYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93ba1f932455d60413e8c5850de5cf38f50257e6f26d0b57328f7644ccde8fa3","last_reissued_at":"2026-07-05T07:31:00.640459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:00.640459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.02992","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":"2026-07-05T07:31:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mVdJNne3yi1F+fIR41yo91YQT29AjYuSvbegtN0FGV1eEYvCSY4Dk383LfYYYZiDcXX+/A5rtC61HldjypOEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:14:39.771443Z"},"content_sha256":"7d9fc45d3eeac5aa48537adaab8f3fd55c39a6d5059d1fe5084be348616b80e8","schema_version":"1.0","event_id":"sha256:7d9fc45d3eeac5aa48537adaab8f3fd55c39a6d5059d1fe5084be348616b80e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SO5B7EZEKXLAIE7IYWCQ3ZOPHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advanced Unstructured Data Processing for ESG Reports: A Methodology for Structured Transformation and Enhanced Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hang Yang, Jiahui Peng, Jianchuan Qi, Jing Gao, Jing Guo, Ming Xu, Nan Li, Ruiqiao Li, Xin Tong","submitted_at":"2024-01-04T06:26:59Z","abstract_excerpt":"In the evolving field of corporate sustainability, analyzing unstructured Environmental, Social, and Governance (ESG) reports is a complex challenge due to their varied formats and intricate content. This study introduces an innovative methodology utilizing the \"Unstructured Core Library\", specifically tailored to address these challenges by transforming ESG reports into structured, analyzable formats. Our approach significantly advances the existing research by offering high-precision text cleaning, adept identification and extraction of text from images, and standardization of tables within "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02992","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/2401.02992/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":"2026-07-05T07:31:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1QdV5vcSdR7xN3HtD3Vj6R7fh77miqc7Uv5lwJex6lfapOokaLXY+anO1dd2RJ6131f3FvxTdnWtsqHxG8C/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:14:39.772248Z"},"content_sha256":"16830e306a46b0c1fc6419454db2276fec6dce6702904eb0aee7b9ba52ff1303","schema_version":"1.0","event_id":"sha256:16830e306a46b0c1fc6419454db2276fec6dce6702904eb0aee7b9ba52ff1303"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SO5B7EZEKXLAIE7IYWCQ3ZOPHD/bundle.json","state_url":"https://pith.science/pith/SO5B7EZEKXLAIE7IYWCQ3ZOPHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SO5B7EZEKXLAIE7IYWCQ3ZOPHD/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":"2026-08-03T20:14:39Z","links":{"resolver":"https://pith.science/pith/SO5B7EZEKXLAIE7IYWCQ3ZOPHD","bundle":"https://pith.science/pith/SO5B7EZEKXLAIE7IYWCQ3ZOPHD/bundle.json","state":"https://pith.science/pith/SO5B7EZEKXLAIE7IYWCQ3ZOPHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SO5B7EZEKXLAIE7IYWCQ3ZOPHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SO5B7EZEKXLAIE7IYWCQ3ZOPHD","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":"1f5f71a982a2104c0f375efc6bc2452b0b0e14b6224414a714816762c9336054","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-04T06:26:59Z","title_canon_sha256":"6d23e0b20e408d2060b260985c59fb63d6a16ecdcf6416152b654d3692dfc68c"},"schema_version":"1.0","source":{"id":"2401.02992","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02992","created_at":"2026-07-05T07:31:00Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02992v1","created_at":"2026-07-05T07:31:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02992","created_at":"2026-07-05T07:31:00Z"},{"alias_kind":"pith_short_12","alias_value":"SO5B7EZEKXLA","created_at":"2026-07-05T07:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"SO5B7EZEKXLAIE7I","created_at":"2026-07-05T07:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"SO5B7EZE","created_at":"2026-07-05T07:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:16830e306a46b0c1fc6419454db2276fec6dce6702904eb0aee7b9ba52ff1303","target":"graph","created_at":"2026-07-05T07:31:00Z","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/2401.02992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the evolving field of corporate sustainability, analyzing unstructured Environmental, Social, and Governance (ESG) reports is a complex challenge due to their varied formats and intricate content. This study introduces an innovative methodology utilizing the \"Unstructured Core Library\", specifically tailored to address these challenges by transforming ESG reports into structured, analyzable formats. Our approach significantly advances the existing research by offering high-precision text cleaning, adept identification and extraction of text from images, and standardization of tables within ","authors_text":"Hang Yang, Jiahui Peng, Jianchuan Qi, Jing Gao, Jing Guo, Ming Xu, Nan Li, Ruiqiao Li, Xin Tong","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-04T06:26:59Z","title":"Advanced Unstructured Data Processing for ESG Reports: A Methodology for Structured Transformation and Enhanced Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02992","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":"sha256:7d9fc45d3eeac5aa48537adaab8f3fd55c39a6d5059d1fe5084be348616b80e8","target":"record","created_at":"2026-07-05T07:31:00Z","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":"1f5f71a982a2104c0f375efc6bc2452b0b0e14b6224414a714816762c9336054","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-04T06:26:59Z","title_canon_sha256":"6d23e0b20e408d2060b260985c59fb63d6a16ecdcf6416152b654d3692dfc68c"},"schema_version":"1.0","source":{"id":"2401.02992","kind":"arxiv","version":1}},"canonical_sha256":"93ba1f932455d60413e8c5850de5cf38f50257e6f26d0b57328f7644ccde8fa3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93ba1f932455d60413e8c5850de5cf38f50257e6f26d0b57328f7644ccde8fa3","first_computed_at":"2026-07-05T07:31:00.640459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:31:00.640459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A5Wkdot7SwoK3F3R4oHi1WvVhp1ldbZg72io4nQp8IiustpRTXt57PiQ6EPNr7MdpUVluqk6K9v68FrTbmBYDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:31:00.641099Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.02992","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d9fc45d3eeac5aa48537adaab8f3fd55c39a6d5059d1fe5084be348616b80e8","sha256:16830e306a46b0c1fc6419454db2276fec6dce6702904eb0aee7b9ba52ff1303"],"state_sha256":"506e838aefa0650a105c7ed77917cf9f2fcdf6381219760d6f2c24169d41768b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7DuK+nUl2T07QfCF5G8XDq/0TvwegD3RG/Hmh7OAaG87I/CM3m85EnbG0ng4JOtOn8vrbRLxf5+9e6A1ujJ4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:14:39.833182Z","bundle_sha256":"d3dd3f18c54d73f66206aaad59d0d9c47683defb5d73acd64b39b931f6daf410"}}