{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KC7LJV2GRGQ5CJYFYCXZMDP4NA","short_pith_number":"pith:KC7LJV2G","canonical_record":{"source":{"id":"2401.12520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-23T06:30:05Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"2248faa361e5cf5599e7e705924793398604956b774d72061d6b0345e851d61c","abstract_canon_sha256":"53b17f453c609bdbd60735c92921731c6e0a0126ca1613f2f4e421c16718c43b"},"schema_version":"1.0"},"canonical_sha256":"50beb4d74689a1d12705c0af960dfc683071b1a8d24c0004c9eedd3837a5194d","source":{"kind":"arxiv","id":"2401.12520","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12520","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12520v1","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12520","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"pith_short_12","alias_value":"KC7LJV2GRGQ5","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"pith_short_16","alias_value":"KC7LJV2GRGQ5CJYF","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"pith_short_8","alias_value":"KC7LJV2G","created_at":"2026-07-05T07:36:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KC7LJV2GRGQ5CJYFYCXZMDP4NA","target":"record","payload":{"canonical_record":{"source":{"id":"2401.12520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-23T06:30:05Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"2248faa361e5cf5599e7e705924793398604956b774d72061d6b0345e851d61c","abstract_canon_sha256":"53b17f453c609bdbd60735c92921731c6e0a0126ca1613f2f4e421c16718c43b"},"schema_version":"1.0"},"canonical_sha256":"50beb4d74689a1d12705c0af960dfc683071b1a8d24c0004c9eedd3837a5194d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:31.862235Z","signature_b64":"F81ltmgJEKOKu/KnQqyB4q+2l4l/04+XBIAJo9eIhKdNdcFSqkc9Z98G3C+0p90Xj25qrjkUmCD4GRSFqR1tAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50beb4d74689a1d12705c0af960dfc683071b1a8d24c0004c9eedd3837a5194d","last_reissued_at":"2026-07-05T07:36:31.861754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:31.861754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.12520","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":"2026-07-05T07:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8kVkqj7vqXnH5SUgg0LwlSgHwQ9PNEI+I0OT6U8ap4WhK2nKhOUmK2zPcSvPtZ7JqILjyAzr5/oyca1S9Eq5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:32:17.097428Z"},"content_sha256":"aa9c6d9a36adb2cfb788b976750a77aec7fd34adbe49a51e0c5977f4890cf543","schema_version":"1.0","event_id":"sha256:aa9c6d9a36adb2cfb788b976750a77aec7fd34adbe49a51e0c5977f4890cf543"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KC7LJV2GRGQ5CJYFYCXZMDP4NA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Key Information Retrieval to Classify the Unstructured Data Content of Preferential Trade Agreements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Caiwen Ding, Dongjin Song, Jiahui Zhao, Sandro Steinbach, Stepan Gordeev, Zijie Pan, Ziyi Meng","submitted_at":"2024-01-23T06:30:05Z","abstract_excerpt":"With the rapid proliferation of textual data, predicting long texts has emerged as a significant challenge in the domain of natural language processing. Traditional text prediction methods encounter substantial difficulties when grappling with long texts, primarily due to the presence of redundant and irrelevant information, which impedes the model's capacity to capture pivotal insights from the text. To address this issue, we introduce a novel approach to long-text classification and prediction. Initially, we employ embedding techniques to condense the long texts, aiming to diminish the redun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12520","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/2401.12520/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":"2026-07-05T07:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xKJWnfnZzU1qvB/wcSgVTDLVdwmMFgrCx58bzG9f9hykYKCdEppKlPcEvkXzDZ692yxIPH9vbOqHKMfubHeyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:32:17.098691Z"},"content_sha256":"02436324d7d4ffef9434a30fdc69e63131a4b38f82ba8b7a29b6c80d382bfc17","schema_version":"1.0","event_id":"sha256:02436324d7d4ffef9434a30fdc69e63131a4b38f82ba8b7a29b6c80d382bfc17"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KC7LJV2GRGQ5CJYFYCXZMDP4NA/bundle.json","state_url":"https://pith.science/pith/KC7LJV2GRGQ5CJYFYCXZMDP4NA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KC7LJV2GRGQ5CJYFYCXZMDP4NA/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":"2026-08-16T20:32:17Z","links":{"resolver":"https://pith.science/pith/KC7LJV2GRGQ5CJYFYCXZMDP4NA","bundle":"https://pith.science/pith/KC7LJV2GRGQ5CJYFYCXZMDP4NA/bundle.json","state":"https://pith.science/pith/KC7LJV2GRGQ5CJYFYCXZMDP4NA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KC7LJV2GRGQ5CJYFYCXZMDP4NA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KC7LJV2GRGQ5CJYFYCXZMDP4NA","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":"53b17f453c609bdbd60735c92921731c6e0a0126ca1613f2f4e421c16718c43b","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-23T06:30:05Z","title_canon_sha256":"2248faa361e5cf5599e7e705924793398604956b774d72061d6b0345e851d61c"},"schema_version":"1.0","source":{"id":"2401.12520","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12520","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12520v1","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12520","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"pith_short_12","alias_value":"KC7LJV2GRGQ5","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"pith_short_16","alias_value":"KC7LJV2GRGQ5CJYF","created_at":"2026-07-05T07:36:31Z"},{"alias_kind":"pith_short_8","alias_value":"KC7LJV2G","created_at":"2026-07-05T07:36:31Z"}],"graph_snapshots":[{"event_id":"sha256:02436324d7d4ffef9434a30fdc69e63131a4b38f82ba8b7a29b6c80d382bfc17","target":"graph","created_at":"2026-07-05T07:36:31Z","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/2401.12520/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid proliferation of textual data, predicting long texts has emerged as a significant challenge in the domain of natural language processing. Traditional text prediction methods encounter substantial difficulties when grappling with long texts, primarily due to the presence of redundant and irrelevant information, which impedes the model's capacity to capture pivotal insights from the text. To address this issue, we introduce a novel approach to long-text classification and prediction. Initially, we employ embedding techniques to condense the long texts, aiming to diminish the redun","authors_text":"Caiwen Ding, Dongjin Song, Jiahui Zhao, Sandro Steinbach, Stepan Gordeev, Zijie Pan, Ziyi Meng","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-23T06:30:05Z","title":"Key Information Retrieval to Classify the Unstructured Data Content of Preferential Trade Agreements"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12520","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:aa9c6d9a36adb2cfb788b976750a77aec7fd34adbe49a51e0c5977f4890cf543","target":"record","created_at":"2026-07-05T07:36:31Z","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":"53b17f453c609bdbd60735c92921731c6e0a0126ca1613f2f4e421c16718c43b","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-23T06:30:05Z","title_canon_sha256":"2248faa361e5cf5599e7e705924793398604956b774d72061d6b0345e851d61c"},"schema_version":"1.0","source":{"id":"2401.12520","kind":"arxiv","version":1}},"canonical_sha256":"50beb4d74689a1d12705c0af960dfc683071b1a8d24c0004c9eedd3837a5194d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50beb4d74689a1d12705c0af960dfc683071b1a8d24c0004c9eedd3837a5194d","first_computed_at":"2026-07-05T07:36:31.861754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:31.861754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F81ltmgJEKOKu/KnQqyB4q+2l4l/04+XBIAJo9eIhKdNdcFSqkc9Z98G3C+0p90Xj25qrjkUmCD4GRSFqR1tAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:31.862235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12520","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa9c6d9a36adb2cfb788b976750a77aec7fd34adbe49a51e0c5977f4890cf543","sha256:02436324d7d4ffef9434a30fdc69e63131a4b38f82ba8b7a29b6c80d382bfc17"],"state_sha256":"65533d40c5e3810e508cf463699e1275832aadfe49452e36b5789a4669ac77f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SLesY4p8jcA4/4VwpVCh8K7tdn48y9tQZNyswSXlz56TeAcD3gmsPzw1ZfdgtnjEvB9q821O9Lcm7UxboNUQBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:32:17.110901Z","bundle_sha256":"9bb22c9ca8c44f32861bd2397d858ffb38f05f096728ed62eb290d0f47465af9"}}