{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CR4EWVHKKDLXS6YS3MXSKUC4V6","short_pith_number":"pith:CR4EWVHK","canonical_record":{"source":{"id":"2502.02167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T09:43:40Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"e142eafc8b5f7df0eb70f7173459cd2d50bb172bf8fc8ec2bf0c78b5da12e0a0","abstract_canon_sha256":"a315f65a83502b28056b523530e5a1ea0e5f24d4dd02ae361844803227f2c4fa"},"schema_version":"1.0"},"canonical_sha256":"14784b54ea50d7797b12db2f25505cafbea52e4e47192e775d7a850b4494be0a","source":{"kind":"arxiv","id":"2502.02167","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02167","created_at":"2026-07-05T10:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02167v1","created_at":"2026-07-05T10:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02167","created_at":"2026-07-05T10:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"CR4EWVHKKDLX","created_at":"2026-07-05T10:09:24Z"},{"alias_kind":"pith_short_16","alias_value":"CR4EWVHKKDLXS6YS","created_at":"2026-07-05T10:09:24Z"},{"alias_kind":"pith_short_8","alias_value":"CR4EWVHK","created_at":"2026-07-05T10:09:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CR4EWVHKKDLXS6YS3MXSKUC4V6","target":"record","payload":{"canonical_record":{"source":{"id":"2502.02167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T09:43:40Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"e142eafc8b5f7df0eb70f7173459cd2d50bb172bf8fc8ec2bf0c78b5da12e0a0","abstract_canon_sha256":"a315f65a83502b28056b523530e5a1ea0e5f24d4dd02ae361844803227f2c4fa"},"schema_version":"1.0"},"canonical_sha256":"14784b54ea50d7797b12db2f25505cafbea52e4e47192e775d7a850b4494be0a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:24.974706Z","signature_b64":"fY1vPuT0QeG+e9dbPQLxQ6L9xTHqFjc1ipKxmpZjQbQ3DopIC8JRrI2ojqlC2oKzifurPjdIbJPUKFG35rSVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14784b54ea50d7797b12db2f25505cafbea52e4e47192e775d7a850b4494be0a","last_reissued_at":"2026-07-05T10:09:24.974210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:24.974210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.02167","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":"2026-07-05T10:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ax5VKWVP90aEAdA1hvApTHl1jvP1PJwXlN0QMarEhbBRsOacv5BnaSOBYllL7YIBSMEOmTTj6RZ1N878B8VxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:26:53.410135Z"},"content_sha256":"dda8d406407d6591018bf4e08038bf14e357cbc11101e90c240b650c60805763","schema_version":"1.0","event_id":"sha256:dda8d406407d6591018bf4e08038bf14e357cbc11101e90c240b650c60805763"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CR4EWVHKKDLXS6YS3MXSKUC4V6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilingual Attribute Extraction from News Web Pages","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Alexander Yatskov, Maksim Varlamov, Pavel Bedrin","submitted_at":"2025-02-04T09:43:40Z","abstract_excerpt":"This paper addresses the challenge of automatically extracting attributes from news article web pages across multiple languages. Recent neural network models have shown high efficacy in extracting information from semi-structured web pages. However, these models are predominantly applied to domains like e-commerce and are pre-trained using English data, complicating their application to web pages in other languages. We prepared a multilingual dataset comprising 3,172 marked-up news web pages across six languages (English, German, Russian, Chinese, Korean, and Arabic) from 161 websites. The dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02167","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/2502.02167/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":"2026-07-05T10:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hsk4PVPM7JheferDA2T21QVmlvHBQZP9WVori9Th/WmU3K540zbQjFIUI7sT3+yC/8kO60/B4NLkYQX7IuriBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:26:53.410670Z"},"content_sha256":"65699291ca6f0a7e517e4060c12ba94572f43825896b603380de36f7b93aa700","schema_version":"1.0","event_id":"sha256:65699291ca6f0a7e517e4060c12ba94572f43825896b603380de36f7b93aa700"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CR4EWVHKKDLXS6YS3MXSKUC4V6/bundle.json","state_url":"https://pith.science/pith/CR4EWVHKKDLXS6YS3MXSKUC4V6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CR4EWVHKKDLXS6YS3MXSKUC4V6/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":"2026-08-22T13:26:53Z","links":{"resolver":"https://pith.science/pith/CR4EWVHKKDLXS6YS3MXSKUC4V6","bundle":"https://pith.science/pith/CR4EWVHKKDLXS6YS3MXSKUC4V6/bundle.json","state":"https://pith.science/pith/CR4EWVHKKDLXS6YS3MXSKUC4V6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CR4EWVHKKDLXS6YS3MXSKUC4V6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CR4EWVHKKDLXS6YS3MXSKUC4V6","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":"a315f65a83502b28056b523530e5a1ea0e5f24d4dd02ae361844803227f2c4fa","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T09:43:40Z","title_canon_sha256":"e142eafc8b5f7df0eb70f7173459cd2d50bb172bf8fc8ec2bf0c78b5da12e0a0"},"schema_version":"1.0","source":{"id":"2502.02167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02167","created_at":"2026-07-05T10:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02167v1","created_at":"2026-07-05T10:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02167","created_at":"2026-07-05T10:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"CR4EWVHKKDLX","created_at":"2026-07-05T10:09:24Z"},{"alias_kind":"pith_short_16","alias_value":"CR4EWVHKKDLXS6YS","created_at":"2026-07-05T10:09:24Z"},{"alias_kind":"pith_short_8","alias_value":"CR4EWVHK","created_at":"2026-07-05T10:09:24Z"}],"graph_snapshots":[{"event_id":"sha256:65699291ca6f0a7e517e4060c12ba94572f43825896b603380de36f7b93aa700","target":"graph","created_at":"2026-07-05T10:09:24Z","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/2502.02167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses the challenge of automatically extracting attributes from news article web pages across multiple languages. Recent neural network models have shown high efficacy in extracting information from semi-structured web pages. However, these models are predominantly applied to domains like e-commerce and are pre-trained using English data, complicating their application to web pages in other languages. We prepared a multilingual dataset comprising 3,172 marked-up news web pages across six languages (English, German, Russian, Chinese, Korean, and Arabic) from 161 websites. The dat","authors_text":"Alexander Yatskov, Maksim Varlamov, Pavel Bedrin","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T09:43:40Z","title":"Multilingual Attribute Extraction from News Web Pages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02167","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:dda8d406407d6591018bf4e08038bf14e357cbc11101e90c240b650c60805763","target":"record","created_at":"2026-07-05T10:09:24Z","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":"a315f65a83502b28056b523530e5a1ea0e5f24d4dd02ae361844803227f2c4fa","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T09:43:40Z","title_canon_sha256":"e142eafc8b5f7df0eb70f7173459cd2d50bb172bf8fc8ec2bf0c78b5da12e0a0"},"schema_version":"1.0","source":{"id":"2502.02167","kind":"arxiv","version":1}},"canonical_sha256":"14784b54ea50d7797b12db2f25505cafbea52e4e47192e775d7a850b4494be0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14784b54ea50d7797b12db2f25505cafbea52e4e47192e775d7a850b4494be0a","first_computed_at":"2026-07-05T10:09:24.974210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:24.974210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fY1vPuT0QeG+e9dbPQLxQ6L9xTHqFjc1ipKxmpZjQbQ3DopIC8JRrI2ojqlC2oKzifurPjdIbJPUKFG35rSVDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:24.974706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dda8d406407d6591018bf4e08038bf14e357cbc11101e90c240b650c60805763","sha256:65699291ca6f0a7e517e4060c12ba94572f43825896b603380de36f7b93aa700"],"state_sha256":"6a301fca1439f8058acf3bee8011b1f09fcf277ad58606eed18de64de96c529b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"paRGVZlLGR9qvq07R6nMUoRo9XkqNS5ree9xphCpCEv5pwIn/maffPVog81XjpV++m7ALoQ9D21Wsi7IC7dfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T13:26:53.415204Z","bundle_sha256":"80aa53696fe1d8056acc4249e9274dae42acb9285b493bd9b773fb544a31e414"}}