{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QMO6E653HDOIZC5CZE4CKM2DGY","short_pith_number":"pith:QMO6E653","canonical_record":{"source":{"id":"2312.08198","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-13T15:03:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"759cc707879edb2f7ef68d80680a7b0a76bc828980f9f67a9c2b0da4c2602584","abstract_canon_sha256":"788fb070bc7a846c367dd11b2763a08ca8802c0aa9243b2489d149c65f4ea46f"},"schema_version":"1.0"},"canonical_sha256":"831de27bbb38dc8c8ba2c938253343362115d6fb9d2b20897ea779b0288b6041","source":{"kind":"arxiv","id":"2312.08198","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08198","created_at":"2026-07-05T07:23:42Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08198v1","created_at":"2026-07-05T07:23:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08198","created_at":"2026-07-05T07:23:42Z"},{"alias_kind":"pith_short_12","alias_value":"QMO6E653HDOI","created_at":"2026-07-05T07:23:42Z"},{"alias_kind":"pith_short_16","alias_value":"QMO6E653HDOIZC5C","created_at":"2026-07-05T07:23:42Z"},{"alias_kind":"pith_short_8","alias_value":"QMO6E653","created_at":"2026-07-05T07:23:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QMO6E653HDOIZC5CZE4CKM2DGY","target":"record","payload":{"canonical_record":{"source":{"id":"2312.08198","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-13T15:03:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"759cc707879edb2f7ef68d80680a7b0a76bc828980f9f67a9c2b0da4c2602584","abstract_canon_sha256":"788fb070bc7a846c367dd11b2763a08ca8802c0aa9243b2489d149c65f4ea46f"},"schema_version":"1.0"},"canonical_sha256":"831de27bbb38dc8c8ba2c938253343362115d6fb9d2b20897ea779b0288b6041","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:42.907736Z","signature_b64":"jxXJHib0sXQO7vbJlp+8ZDtcetgyWmG1dIHXEVQJHR2c/PBMjyF18oc71MJGi+3DmJ+dqqe2KSh1sFda1HuFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"831de27bbb38dc8c8ba2c938253343362115d6fb9d2b20897ea779b0288b6041","last_reissued_at":"2026-07-05T07:23:42.907298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:42.907298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.08198","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":"2026-07-05T07:23:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E3dphM2Vgxvep+uenLMeoP+YU+74YBao44bK4ZkwmDLPrCmQ9rOWOakx8m8Ea78FpNG7FE5RDlkPZJ0T4NcyAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:50:36.204235Z"},"content_sha256":"0117abf7166b24202ff4fd48071708031fd0bb2bd3b27ed4a5f9b9a1512841a5","schema_version":"1.0","event_id":"sha256:0117abf7166b24202ff4fd48071708031fd0bb2bd3b27ed4a5f9b9a1512841a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QMO6E653HDOIZC5CZE4CKM2DGY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Model-Based Data Acquisition for Subjective Multi-Task NLP Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jan Kocon, Julita Bielaniewicz, Kamil Kanclerz, Marcin Gruza, Przemys{\\l}aw Kazienko, Stanis{\\l}aw Wo\\'zniak","submitted_at":"2023-12-13T15:03:27Z","abstract_excerpt":"Data annotated by humans is a source of knowledge by describing the peculiarities of the problem and therefore fueling the decision process of the trained model. Unfortunately, the annotation process for subjective natural language processing (NLP) problems like offensiveness or emotion detection is often very expensive and time-consuming. One of the inevitable risks is to spend some of the funds and annotator effort on annotations that do not provide any additional knowledge about the specific task. To minimize these costs, we propose a new model-based approach that allows the selection of ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08198","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/2312.08198/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":"2026-07-05T07:23:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cuJFi+WFJIVIvhDh7DdzJKbtDLXjVVl2neWB9pWW+XFOdNzjbclVvjJN1IRt/+sgCHJSLH5UfPKL+VmhUQ0HCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:50:36.205147Z"},"content_sha256":"6485865ab9bb7f24863d50dedf791754067b6de24e6da48ba6bf9a631cc67ffe","schema_version":"1.0","event_id":"sha256:6485865ab9bb7f24863d50dedf791754067b6de24e6da48ba6bf9a631cc67ffe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QMO6E653HDOIZC5CZE4CKM2DGY/bundle.json","state_url":"https://pith.science/pith/QMO6E653HDOIZC5CZE4CKM2DGY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QMO6E653HDOIZC5CZE4CKM2DGY/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":"2026-08-19T05:50:36Z","links":{"resolver":"https://pith.science/pith/QMO6E653HDOIZC5CZE4CKM2DGY","bundle":"https://pith.science/pith/QMO6E653HDOIZC5CZE4CKM2DGY/bundle.json","state":"https://pith.science/pith/QMO6E653HDOIZC5CZE4CKM2DGY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QMO6E653HDOIZC5CZE4CKM2DGY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QMO6E653HDOIZC5CZE4CKM2DGY","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":"788fb070bc7a846c367dd11b2763a08ca8802c0aa9243b2489d149c65f4ea46f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-13T15:03:27Z","title_canon_sha256":"759cc707879edb2f7ef68d80680a7b0a76bc828980f9f67a9c2b0da4c2602584"},"schema_version":"1.0","source":{"id":"2312.08198","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08198","created_at":"2026-07-05T07:23:42Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08198v1","created_at":"2026-07-05T07:23:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08198","created_at":"2026-07-05T07:23:42Z"},{"alias_kind":"pith_short_12","alias_value":"QMO6E653HDOI","created_at":"2026-07-05T07:23:42Z"},{"alias_kind":"pith_short_16","alias_value":"QMO6E653HDOIZC5C","created_at":"2026-07-05T07:23:42Z"},{"alias_kind":"pith_short_8","alias_value":"QMO6E653","created_at":"2026-07-05T07:23:42Z"}],"graph_snapshots":[{"event_id":"sha256:6485865ab9bb7f24863d50dedf791754067b6de24e6da48ba6bf9a631cc67ffe","target":"graph","created_at":"2026-07-05T07:23:42Z","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/2312.08198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data annotated by humans is a source of knowledge by describing the peculiarities of the problem and therefore fueling the decision process of the trained model. Unfortunately, the annotation process for subjective natural language processing (NLP) problems like offensiveness or emotion detection is often very expensive and time-consuming. One of the inevitable risks is to spend some of the funds and annotator effort on annotations that do not provide any additional knowledge about the specific task. To minimize these costs, we propose a new model-based approach that allows the selection of ta","authors_text":"Jan Kocon, Julita Bielaniewicz, Kamil Kanclerz, Marcin Gruza, Przemys{\\l}aw Kazienko, Stanis{\\l}aw Wo\\'zniak","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-13T15:03:27Z","title":"Towards Model-Based Data Acquisition for Subjective Multi-Task NLP Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08198","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":"sha256:0117abf7166b24202ff4fd48071708031fd0bb2bd3b27ed4a5f9b9a1512841a5","target":"record","created_at":"2026-07-05T07:23:42Z","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":"788fb070bc7a846c367dd11b2763a08ca8802c0aa9243b2489d149c65f4ea46f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-13T15:03:27Z","title_canon_sha256":"759cc707879edb2f7ef68d80680a7b0a76bc828980f9f67a9c2b0da4c2602584"},"schema_version":"1.0","source":{"id":"2312.08198","kind":"arxiv","version":1}},"canonical_sha256":"831de27bbb38dc8c8ba2c938253343362115d6fb9d2b20897ea779b0288b6041","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"831de27bbb38dc8c8ba2c938253343362115d6fb9d2b20897ea779b0288b6041","first_computed_at":"2026-07-05T07:23:42.907298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:42.907298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jxXJHib0sXQO7vbJlp+8ZDtcetgyWmG1dIHXEVQJHR2c/PBMjyF18oc71MJGi+3DmJ+dqqe2KSh1sFda1HuFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:42.907736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08198","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0117abf7166b24202ff4fd48071708031fd0bb2bd3b27ed4a5f9b9a1512841a5","sha256:6485865ab9bb7f24863d50dedf791754067b6de24e6da48ba6bf9a631cc67ffe"],"state_sha256":"6395e0ed8b4818ecdec3d934b3e8474af97040c190070e497040105be99b7bf1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3T/bI2f5+m1CkyKO8iInJq1volioLY1gdDq5gqMBkh/yT8Pq4EZcQ2Ar2m6XyFPOJDCIxFAgOoppH0pu5oCgAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T05:50:36.211398Z","bundle_sha256":"946610dddf15ddfbe2f1a00905b09ae514d5de0c90f3ba02da49580c86ae4b58"}}