{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:G5A76AQD3YAV7UEMTNT5OTQCFB","short_pith_number":"pith:G5A76AQD","canonical_record":{"source":{"id":"2308.02951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-05T20:33:39Z","cross_cats_sorted":[],"title_canon_sha256":"cdd6d6945e81c77406a6f8f2100ddc79170c8ba9613b50c00a3baee830861e96","abstract_canon_sha256":"e40147e928082dcac60d32400968edbb39c041e76139ff5af5fcc4d111a81403"},"schema_version":"1.0"},"canonical_sha256":"3741ff0203de015fd08c9b67d74e0228726cc3444cd86678009ddedb9798c9f0","source":{"kind":"arxiv","id":"2308.02951","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.02951","created_at":"2026-07-05T06:38:09Z"},{"alias_kind":"arxiv_version","alias_value":"2308.02951v1","created_at":"2026-07-05T06:38:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02951","created_at":"2026-07-05T06:38:09Z"},{"alias_kind":"pith_short_12","alias_value":"G5A76AQD3YAV","created_at":"2026-07-05T06:38:09Z"},{"alias_kind":"pith_short_16","alias_value":"G5A76AQD3YAV7UEM","created_at":"2026-07-05T06:38:09Z"},{"alias_kind":"pith_short_8","alias_value":"G5A76AQD","created_at":"2026-07-05T06:38:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:G5A76AQD3YAV7UEMTNT5OTQCFB","target":"record","payload":{"canonical_record":{"source":{"id":"2308.02951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-05T20:33:39Z","cross_cats_sorted":[],"title_canon_sha256":"cdd6d6945e81c77406a6f8f2100ddc79170c8ba9613b50c00a3baee830861e96","abstract_canon_sha256":"e40147e928082dcac60d32400968edbb39c041e76139ff5af5fcc4d111a81403"},"schema_version":"1.0"},"canonical_sha256":"3741ff0203de015fd08c9b67d74e0228726cc3444cd86678009ddedb9798c9f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:38:09.792869Z","signature_b64":"CfJsgU290TVaaAxD+6/SAh2j1KPjiVjiyIlPEutCv0XK0D3Br6CPAmrUNIPAacy4J+H6EAW+ZiBdyNzxd2FpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3741ff0203de015fd08c9b67d74e0228726cc3444cd86678009ddedb9798c9f0","last_reissued_at":"2026-07-05T06:38:09.792248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:38:09.792248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.02951","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":"2026-07-05T06:38:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z4yjKCRCrGXsmnXjLOpaBTWdgrbrPAwK4OyH9kfjug290aqQKGAl+bcAPMCmPnzJ97wd2KVTpYlBldZu2/NwBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T07:35:25.650414Z"},"content_sha256":"8c9f292b82689fa774ea6c64ba018b82e9d534ed7377140fc3f6035f231335d5","schema_version":"1.0","event_id":"sha256:8c9f292b82689fa774ea6c64ba018b82e9d534ed7377140fc3f6035f231335d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:G5A76AQD3YAV7UEMTNT5OTQCFB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Source (Pre-)Training for Cross-Domain Measurement, Unit and Context Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sebastian Martschat, Simone Paolo Ponzetto, Yueling Li","submitted_at":"2023-08-05T20:33:39Z","abstract_excerpt":"We present a cross-domain approach for automated measurement and context extraction based on pre-trained language models. We construct a multi-source, multi-domain corpus and train an end-to-end extraction pipeline. We then apply multi-source task-adaptive pre-training and fine-tuning to benchmark the cross-domain generalization capability of our model. Further, we conceptualize and apply a task-specific error analysis and derive insights for future work. Our results suggest that multi-source training leads to the best overall results, while single-source training yields the best results for t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02951","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/2308.02951/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":"2026-07-05T06:38:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"edEWryIqegyfBUIFGmpnx1Kc65Iws6ZpZXGCnKinw8FxwhuFj01QfryhQj2FM1ma4MK981jaLRv/Ol/twlx9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T07:35:25.650786Z"},"content_sha256":"b015dabb003d1c989951fc07bfe19ae538dd16cb0808e2b0d8f6ceda4d7da13f","schema_version":"1.0","event_id":"sha256:b015dabb003d1c989951fc07bfe19ae538dd16cb0808e2b0d8f6ceda4d7da13f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5A76AQD3YAV7UEMTNT5OTQCFB/bundle.json","state_url":"https://pith.science/pith/G5A76AQD3YAV7UEMTNT5OTQCFB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5A76AQD3YAV7UEMTNT5OTQCFB/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":"2026-07-17T07:35:25Z","links":{"resolver":"https://pith.science/pith/G5A76AQD3YAV7UEMTNT5OTQCFB","bundle":"https://pith.science/pith/G5A76AQD3YAV7UEMTNT5OTQCFB/bundle.json","state":"https://pith.science/pith/G5A76AQD3YAV7UEMTNT5OTQCFB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5A76AQD3YAV7UEMTNT5OTQCFB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G5A76AQD3YAV7UEMTNT5OTQCFB","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":"e40147e928082dcac60d32400968edbb39c041e76139ff5af5fcc4d111a81403","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-05T20:33:39Z","title_canon_sha256":"cdd6d6945e81c77406a6f8f2100ddc79170c8ba9613b50c00a3baee830861e96"},"schema_version":"1.0","source":{"id":"2308.02951","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.02951","created_at":"2026-07-05T06:38:09Z"},{"alias_kind":"arxiv_version","alias_value":"2308.02951v1","created_at":"2026-07-05T06:38:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02951","created_at":"2026-07-05T06:38:09Z"},{"alias_kind":"pith_short_12","alias_value":"G5A76AQD3YAV","created_at":"2026-07-05T06:38:09Z"},{"alias_kind":"pith_short_16","alias_value":"G5A76AQD3YAV7UEM","created_at":"2026-07-05T06:38:09Z"},{"alias_kind":"pith_short_8","alias_value":"G5A76AQD","created_at":"2026-07-05T06:38:09Z"}],"graph_snapshots":[{"event_id":"sha256:b015dabb003d1c989951fc07bfe19ae538dd16cb0808e2b0d8f6ceda4d7da13f","target":"graph","created_at":"2026-07-05T06:38:09Z","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/2308.02951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a cross-domain approach for automated measurement and context extraction based on pre-trained language models. We construct a multi-source, multi-domain corpus and train an end-to-end extraction pipeline. We then apply multi-source task-adaptive pre-training and fine-tuning to benchmark the cross-domain generalization capability of our model. Further, we conceptualize and apply a task-specific error analysis and derive insights for future work. Our results suggest that multi-source training leads to the best overall results, while single-source training yields the best results for t","authors_text":"Sebastian Martschat, Simone Paolo Ponzetto, Yueling Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-05T20:33:39Z","title":"Multi-Source (Pre-)Training for Cross-Domain Measurement, Unit and Context Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02951","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":"sha256:8c9f292b82689fa774ea6c64ba018b82e9d534ed7377140fc3f6035f231335d5","target":"record","created_at":"2026-07-05T06:38:09Z","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":"e40147e928082dcac60d32400968edbb39c041e76139ff5af5fcc4d111a81403","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-05T20:33:39Z","title_canon_sha256":"cdd6d6945e81c77406a6f8f2100ddc79170c8ba9613b50c00a3baee830861e96"},"schema_version":"1.0","source":{"id":"2308.02951","kind":"arxiv","version":1}},"canonical_sha256":"3741ff0203de015fd08c9b67d74e0228726cc3444cd86678009ddedb9798c9f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3741ff0203de015fd08c9b67d74e0228726cc3444cd86678009ddedb9798c9f0","first_computed_at":"2026-07-05T06:38:09.792248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:38:09.792248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CfJsgU290TVaaAxD+6/SAh2j1KPjiVjiyIlPEutCv0XK0D3Br6CPAmrUNIPAacy4J+H6EAW+ZiBdyNzxd2FpBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:38:09.792869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.02951","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c9f292b82689fa774ea6c64ba018b82e9d534ed7377140fc3f6035f231335d5","sha256:b015dabb003d1c989951fc07bfe19ae538dd16cb0808e2b0d8f6ceda4d7da13f"],"state_sha256":"0cbb39aa3247104321750ac59b51669d25c0c7f35366b5edd688fd26878bb796"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V8LUqH5SDljirRsRPgRP4TewUTN3hJO6uGZCXoWfBTcuie7ITDyYVFzMoHmWNGuwZ/N5iYpyC2z8qmZMV6AzBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T07:35:25.652963Z","bundle_sha256":"96ca526c82b1a2b870be2a9f6f1b48186331e0e813c4e392bd4f0ab7275018f2"}}