{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NBRX7RHZAOHCE4PDGFAPVIW6TQ","short_pith_number":"pith:NBRX7RHZ","canonical_record":{"source":{"id":"2305.05486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T14:36:04Z","cross_cats_sorted":[],"title_canon_sha256":"b7836a8efa66da608336691b0669ec2a7326c4851ea8378b078667e10c7b7edc","abstract_canon_sha256":"95328fa49e8f0f3aa01aca2455c30804d067b85deaf574cbc595525d91ff0761"},"schema_version":"1.0"},"canonical_sha256":"68637fc4f9038e2271e33140faa2de9c3affd3e6a4aee6dfb358997f0d868132","source":{"kind":"arxiv","id":"2305.05486","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05486","created_at":"2026-07-05T06:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05486v1","created_at":"2026-07-05T06:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05486","created_at":"2026-07-05T06:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"NBRX7RHZAOHC","created_at":"2026-07-05T06:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"NBRX7RHZAOHCE4PD","created_at":"2026-07-05T06:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"NBRX7RHZ","created_at":"2026-07-05T06:08:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NBRX7RHZAOHCE4PDGFAPVIW6TQ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.05486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T14:36:04Z","cross_cats_sorted":[],"title_canon_sha256":"b7836a8efa66da608336691b0669ec2a7326c4851ea8378b078667e10c7b7edc","abstract_canon_sha256":"95328fa49e8f0f3aa01aca2455c30804d067b85deaf574cbc595525d91ff0761"},"schema_version":"1.0"},"canonical_sha256":"68637fc4f9038e2271e33140faa2de9c3affd3e6a4aee6dfb358997f0d868132","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:35.295346Z","signature_b64":"OM5nwGWiysznHg9GJ8W1QrqYXqmu3sDBp6Y8Dx1xLn+B4X+UCkouhdwbgeOpOtKvjlEcX0YAPGgFb0ENeM5rCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68637fc4f9038e2271e33140faa2de9c3affd3e6a4aee6dfb358997f0d868132","last_reissued_at":"2026-07-05T06:08:35.294936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:35.294936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.05486","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":"2026-07-05T06:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GD6egAAZp55EY0nWBsFnCa17cgWnNGieVXPLbf14q0U4lCZDbH4Lv0h+XDkFllSGUz+LNkRg4SleUUHCUCyVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:07:02.018903Z"},"content_sha256":"b3a8bdb3676c62a8ce74e404d946b3b66da17eb69c64fa67e472b7daa7385375","schema_version":"1.0","event_id":"sha256:b3a8bdb3676c62a8ce74e404d946b3b66da17eb69c64fa67e472b7daa7385375"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NBRX7RHZAOHCE4PDGFAPVIW6TQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MAUPQA: Massive Automatically-created Polish Question Answering Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Piotr Rybak","submitted_at":"2023-05-09T14:36:04Z","abstract_excerpt":"Recently, open-domain question answering systems have begun to rely heavily on annotated datasets to train neural passage retrievers. However, manually annotating such datasets is both difficult and time-consuming, which limits their availability for less popular languages. In this work, we experiment with several methods for automatically collecting weakly labeled datasets and show how they affect the performance of the neural passage retrieval models. As a result of our work, we publish the MAUPQA dataset, consisting of nearly 400,000 question-passage pairs for Polish, as well as the HerBERT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05486","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/2305.05486/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":"2026-07-05T06:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sdoyiT2Rr5u0OhYIKZN0hP8WF3O65by1GxblKcUd2ajK8Dn6jOt+Y0vroIK3L0hG+pyZX7T1hs+uZsKYAQwBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:07:02.019585Z"},"content_sha256":"dcb97d3f759571fd6be075a88b59b3e9aeadfce412eccc36e0be81bb34ea98b0","schema_version":"1.0","event_id":"sha256:dcb97d3f759571fd6be075a88b59b3e9aeadfce412eccc36e0be81bb34ea98b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NBRX7RHZAOHCE4PDGFAPVIW6TQ/bundle.json","state_url":"https://pith.science/pith/NBRX7RHZAOHCE4PDGFAPVIW6TQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NBRX7RHZAOHCE4PDGFAPVIW6TQ/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":"2026-08-06T09:07:02Z","links":{"resolver":"https://pith.science/pith/NBRX7RHZAOHCE4PDGFAPVIW6TQ","bundle":"https://pith.science/pith/NBRX7RHZAOHCE4PDGFAPVIW6TQ/bundle.json","state":"https://pith.science/pith/NBRX7RHZAOHCE4PDGFAPVIW6TQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NBRX7RHZAOHCE4PDGFAPVIW6TQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NBRX7RHZAOHCE4PDGFAPVIW6TQ","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":"95328fa49e8f0f3aa01aca2455c30804d067b85deaf574cbc595525d91ff0761","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T14:36:04Z","title_canon_sha256":"b7836a8efa66da608336691b0669ec2a7326c4851ea8378b078667e10c7b7edc"},"schema_version":"1.0","source":{"id":"2305.05486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05486","created_at":"2026-07-05T06:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05486v1","created_at":"2026-07-05T06:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05486","created_at":"2026-07-05T06:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"NBRX7RHZAOHC","created_at":"2026-07-05T06:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"NBRX7RHZAOHCE4PD","created_at":"2026-07-05T06:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"NBRX7RHZ","created_at":"2026-07-05T06:08:35Z"}],"graph_snapshots":[{"event_id":"sha256:dcb97d3f759571fd6be075a88b59b3e9aeadfce412eccc36e0be81bb34ea98b0","target":"graph","created_at":"2026-07-05T06:08:35Z","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/2305.05486/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, open-domain question answering systems have begun to rely heavily on annotated datasets to train neural passage retrievers. However, manually annotating such datasets is both difficult and time-consuming, which limits their availability for less popular languages. In this work, we experiment with several methods for automatically collecting weakly labeled datasets and show how they affect the performance of the neural passage retrieval models. As a result of our work, we publish the MAUPQA dataset, consisting of nearly 400,000 question-passage pairs for Polish, as well as the HerBERT","authors_text":"Piotr Rybak","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T14:36:04Z","title":"MAUPQA: Massive Automatically-created Polish Question Answering Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05486","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:b3a8bdb3676c62a8ce74e404d946b3b66da17eb69c64fa67e472b7daa7385375","target":"record","created_at":"2026-07-05T06:08:35Z","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":"95328fa49e8f0f3aa01aca2455c30804d067b85deaf574cbc595525d91ff0761","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T14:36:04Z","title_canon_sha256":"b7836a8efa66da608336691b0669ec2a7326c4851ea8378b078667e10c7b7edc"},"schema_version":"1.0","source":{"id":"2305.05486","kind":"arxiv","version":1}},"canonical_sha256":"68637fc4f9038e2271e33140faa2de9c3affd3e6a4aee6dfb358997f0d868132","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68637fc4f9038e2271e33140faa2de9c3affd3e6a4aee6dfb358997f0d868132","first_computed_at":"2026-07-05T06:08:35.294936Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:35.294936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OM5nwGWiysznHg9GJ8W1QrqYXqmu3sDBp6Y8Dx1xLn+B4X+UCkouhdwbgeOpOtKvjlEcX0YAPGgFb0ENeM5rCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:35.295346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.05486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3a8bdb3676c62a8ce74e404d946b3b66da17eb69c64fa67e472b7daa7385375","sha256:dcb97d3f759571fd6be075a88b59b3e9aeadfce412eccc36e0be81bb34ea98b0"],"state_sha256":"225a8a73908df9e9969c3797a77a319919d74b59f9c4a268d92a53b72ad5cb3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tN9oipOA1Xpddo1I0NqfEy37CFs0Ut6dy5dV7kuEWJALsUOqJKMPYhHLXHB8L9ciOD3fpYqFM8buRkzu3GJjAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:07:02.026540Z","bundle_sha256":"58a0bdcc883d80b92fca136b9098889ac6e5b8444dc52e35b3664b9428471119"}}