{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PQT2374TLH7WVJVYLV3JRLEKQH","short_pith_number":"pith:PQT2374T","canonical_record":{"source":{"id":"2305.10928","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T12:40:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"028d730724df71bbff19f9962023ec3b5a9c84181971e9f770d9f522c9f9f389","abstract_canon_sha256":"d7c15d2c9b2a69acd1baa837a2541d48845c4c1d7189e997ae750c03024469a6"},"schema_version":"1.0"},"canonical_sha256":"7c27adff9359ff6aa6b85d7698ac8a81e9b4816af73fe9ba125250dcd9dab228","source":{"kind":"arxiv","id":"2305.10928","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10928","created_at":"2026-07-05T06:11:28Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10928v1","created_at":"2026-07-05T06:11:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10928","created_at":"2026-07-05T06:11:28Z"},{"alias_kind":"pith_short_12","alias_value":"PQT2374TLH7W","created_at":"2026-07-05T06:11:28Z"},{"alias_kind":"pith_short_16","alias_value":"PQT2374TLH7WVJVY","created_at":"2026-07-05T06:11:28Z"},{"alias_kind":"pith_short_8","alias_value":"PQT2374T","created_at":"2026-07-05T06:11:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PQT2374TLH7WVJVYLV3JRLEKQH","target":"record","payload":{"canonical_record":{"source":{"id":"2305.10928","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T12:40:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"028d730724df71bbff19f9962023ec3b5a9c84181971e9f770d9f522c9f9f389","abstract_canon_sha256":"d7c15d2c9b2a69acd1baa837a2541d48845c4c1d7189e997ae750c03024469a6"},"schema_version":"1.0"},"canonical_sha256":"7c27adff9359ff6aa6b85d7698ac8a81e9b4816af73fe9ba125250dcd9dab228","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:28.275164Z","signature_b64":"MuiuLYeFS0+oZFq10yd+31wgTzsRQ0M2ClgVR0Giqrp9xRUPVyX1g3Ndvac6z8YdtB3QmgbpJZjxSdU7bXpQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c27adff9359ff6aa6b85d7698ac8a81e9b4816af73fe9ba125250dcd9dab228","last_reissued_at":"2026-07-05T06:11:28.274634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:28.274634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.10928","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":"2026-07-05T06:11:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rc9xnow9S1AXPsnNY7ILvOpks3V12FHtFT2A2yz4WB0MEAIjeQ2GSCYVINWnwLGcKP1sKFyTASNmPxj3tnoiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:19:21.223231Z"},"content_sha256":"48d2bf689bd950908a2c2330084f44bc52a64230767a718becae5f774c67b851","schema_version":"1.0","event_id":"sha256:48d2bf689bd950908a2c2330084f44bc52a64230767a718becae5f774c67b851"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PQT2374TLH7WVJVYLV3JRLEKQH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilingual Event Extraction from Historical Newspaper Adverts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Isabelle Augenstein, Nadav Borenstein, Natalia da Silva Perez","submitted_at":"2023-05-18T12:40:41Z","abstract_excerpt":"NLP methods can aid historians in analyzing textual materials in greater volumes than manually feasible. Developing such methods poses substantial challenges though. First, acquiring large, annotated historical datasets is difficult, as only domain experts can reliably label them. Second, most available off-the-shelf NLP models are trained on modern language texts, rendering them significantly less effective when applied to historical corpora. This is particularly problematic for less well studied tasks, and for languages other than English. This paper addresses these challenges while focusing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10928","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/2305.10928/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":"2026-07-05T06:11:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MM4+Ekqt5Hh3iqHrUzNWdxWxqTF7GrnGF9z8GV3DfiKg2uQLJAYT6Mk5+aoPe9csfW2Qbab0CctqRm89cnYmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:19:21.223605Z"},"content_sha256":"7c0e8903bbd33382602f4f936c20d7423a1de76c3f2705d3eb2d9cb10ed50404","schema_version":"1.0","event_id":"sha256:7c0e8903bbd33382602f4f936c20d7423a1de76c3f2705d3eb2d9cb10ed50404"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQT2374TLH7WVJVYLV3JRLEKQH/bundle.json","state_url":"https://pith.science/pith/PQT2374TLH7WVJVYLV3JRLEKQH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQT2374TLH7WVJVYLV3JRLEKQH/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":"2026-08-03T20:19:21Z","links":{"resolver":"https://pith.science/pith/PQT2374TLH7WVJVYLV3JRLEKQH","bundle":"https://pith.science/pith/PQT2374TLH7WVJVYLV3JRLEKQH/bundle.json","state":"https://pith.science/pith/PQT2374TLH7WVJVYLV3JRLEKQH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQT2374TLH7WVJVYLV3JRLEKQH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PQT2374TLH7WVJVYLV3JRLEKQH","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":"d7c15d2c9b2a69acd1baa837a2541d48845c4c1d7189e997ae750c03024469a6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T12:40:41Z","title_canon_sha256":"028d730724df71bbff19f9962023ec3b5a9c84181971e9f770d9f522c9f9f389"},"schema_version":"1.0","source":{"id":"2305.10928","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10928","created_at":"2026-07-05T06:11:28Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10928v1","created_at":"2026-07-05T06:11:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10928","created_at":"2026-07-05T06:11:28Z"},{"alias_kind":"pith_short_12","alias_value":"PQT2374TLH7W","created_at":"2026-07-05T06:11:28Z"},{"alias_kind":"pith_short_16","alias_value":"PQT2374TLH7WVJVY","created_at":"2026-07-05T06:11:28Z"},{"alias_kind":"pith_short_8","alias_value":"PQT2374T","created_at":"2026-07-05T06:11:28Z"}],"graph_snapshots":[{"event_id":"sha256:7c0e8903bbd33382602f4f936c20d7423a1de76c3f2705d3eb2d9cb10ed50404","target":"graph","created_at":"2026-07-05T06:11:28Z","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/2305.10928/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"NLP methods can aid historians in analyzing textual materials in greater volumes than manually feasible. Developing such methods poses substantial challenges though. First, acquiring large, annotated historical datasets is difficult, as only domain experts can reliably label them. Second, most available off-the-shelf NLP models are trained on modern language texts, rendering them significantly less effective when applied to historical corpora. This is particularly problematic for less well studied tasks, and for languages other than English. This paper addresses these challenges while focusing","authors_text":"Isabelle Augenstein, Nadav Borenstein, Natalia da Silva Perez","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T12:40:41Z","title":"Multilingual Event Extraction from Historical Newspaper Adverts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10928","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":"sha256:48d2bf689bd950908a2c2330084f44bc52a64230767a718becae5f774c67b851","target":"record","created_at":"2026-07-05T06:11:28Z","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":"d7c15d2c9b2a69acd1baa837a2541d48845c4c1d7189e997ae750c03024469a6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T12:40:41Z","title_canon_sha256":"028d730724df71bbff19f9962023ec3b5a9c84181971e9f770d9f522c9f9f389"},"schema_version":"1.0","source":{"id":"2305.10928","kind":"arxiv","version":1}},"canonical_sha256":"7c27adff9359ff6aa6b85d7698ac8a81e9b4816af73fe9ba125250dcd9dab228","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c27adff9359ff6aa6b85d7698ac8a81e9b4816af73fe9ba125250dcd9dab228","first_computed_at":"2026-07-05T06:11:28.274634Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:28.274634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MuiuLYeFS0+oZFq10yd+31wgTzsRQ0M2ClgVR0Giqrp9xRUPVyX1g3Ndvac6z8YdtB3QmgbpJZjxSdU7bXpQCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:28.275164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10928","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48d2bf689bd950908a2c2330084f44bc52a64230767a718becae5f774c67b851","sha256:7c0e8903bbd33382602f4f936c20d7423a1de76c3f2705d3eb2d9cb10ed50404"],"state_sha256":"532eda3c2812a27e40faa38980edcd8d82026276cf2f295455347a60588c3c6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cTSv3c/XqtL+BLOC0xyX/WzM2DbuoRnirEVCR5nB7KQI81kWcYhND2150hr94gsrWlDMpARE1TEDU56rDl5CBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:19:21.226174Z","bundle_sha256":"8e059e32d8879d3a404982bb16833672f2666eab3c60d4112f081aafe7bd9862"}}