{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TUMKEMBUKNEXPYPVXIFDZHPDDF","short_pith_number":"pith:TUMKEMBU","canonical_record":{"source":{"id":"2004.12302","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-26T07:43:15Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"c0b0d2b95a7371bbf812373c71d7dbc040ff9baea45fe4e54cf760c0a6137cd0","abstract_canon_sha256":"0a6bb9bd49a5595a5421cd68966d7ffcd24eccaece9f38053ad19a8f513b9ecf"},"schema_version":"1.0"},"canonical_sha256":"9d18a23034534977e1f5ba0a3c9de3195fba28ef7f7d3eea3a7c9f20fcfe1f30","source":{"kind":"arxiv","id":"2004.12302","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.12302","created_at":"2026-07-05T01:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2004.12302v2","created_at":"2026-07-05T01:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12302","created_at":"2026-07-05T01:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"TUMKEMBUKNEX","created_at":"2026-07-05T01:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"TUMKEMBUKNEXPYPV","created_at":"2026-07-05T01:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"TUMKEMBU","created_at":"2026-07-05T01:05:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TUMKEMBUKNEXPYPVXIFDZHPDDF","target":"record","payload":{"canonical_record":{"source":{"id":"2004.12302","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-26T07:43:15Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"c0b0d2b95a7371bbf812373c71d7dbc040ff9baea45fe4e54cf760c0a6137cd0","abstract_canon_sha256":"0a6bb9bd49a5595a5421cd68966d7ffcd24eccaece9f38053ad19a8f513b9ecf"},"schema_version":"1.0"},"canonical_sha256":"9d18a23034534977e1f5ba0a3c9de3195fba28ef7f7d3eea3a7c9f20fcfe1f30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:12.629632Z","signature_b64":"QD7NGcKc01tCfsG7JVRY8eCtBcdH0IyXb0u9VgH3gwnekHK9+5rVEvf1ODDvqTXEFaCR57k8SdEHIcjSYXbbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d18a23034534977e1f5ba0a3c9de3195fba28ef7f7d3eea3a7c9f20fcfe1f30","last_reissued_at":"2026-07-05T01:05:12.629184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:12.629184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.12302","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"apb8cUcWl9AE2H/vwmqohNzfrYR6zCTlXgut/HlOae5P7k9C8nrPFw6J8mba6MLARyvIk5laqdqIf0n/PdH3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T05:41:40.273282Z"},"content_sha256":"e3f051a7a925ae0dece4ffdb3e9fa53acbd87a8273753f2b24728755bc5a9b7a","schema_version":"1.0","event_id":"sha256:e3f051a7a925ae0dece4ffdb3e9fa53acbd87a8273753f2b24728755bc5a9b7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TUMKEMBUKNEXPYPVXIFDZHPDDF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Canwen Xu, Chenliang Li, Hongtao Wu, Jiaxin Pei, Yiyu Liu","submitted_at":"2020-04-26T07:43:15Z","abstract_excerpt":"Recently, large-scale datasets have vastly facilitated the development in nearly all domains of Natural Language Processing. However, there is currently no cross-task dataset in NLP, which hinders the development of multi-task learning. We propose MATINF, the first jointly labeled large-scale dataset for classification, question answering and summarization. MATINF contains 1.07 million question-answer pairs with human-labeled categories and user-generated question descriptions. Based on such rich information, MATINF is applicable for three major NLP tasks, including classification, question an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12302","kind":"arxiv","version":2},"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/2004.12302/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":"2026-07-05T01:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5iJ9EZ2PkUe1+eVZsTYE8UygLk9aYjygOroHvNbgxkzv0F8veQStFS7OE10KNbOWB7eENFTPv8W5SQo8iP2HAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T05:41:40.273693Z"},"content_sha256":"aa8a957554b03d081b13c906d66ce41e6914bc1ae0cd78bb89e230b78e956d3a","schema_version":"1.0","event_id":"sha256:aa8a957554b03d081b13c906d66ce41e6914bc1ae0cd78bb89e230b78e956d3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUMKEMBUKNEXPYPVXIFDZHPDDF/bundle.json","state_url":"https://pith.science/pith/TUMKEMBUKNEXPYPVXIFDZHPDDF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUMKEMBUKNEXPYPVXIFDZHPDDF/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":"2026-07-10T05:41:40Z","links":{"resolver":"https://pith.science/pith/TUMKEMBUKNEXPYPVXIFDZHPDDF","bundle":"https://pith.science/pith/TUMKEMBUKNEXPYPVXIFDZHPDDF/bundle.json","state":"https://pith.science/pith/TUMKEMBUKNEXPYPVXIFDZHPDDF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUMKEMBUKNEXPYPVXIFDZHPDDF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TUMKEMBUKNEXPYPVXIFDZHPDDF","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":"0a6bb9bd49a5595a5421cd68966d7ffcd24eccaece9f38053ad19a8f513b9ecf","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-26T07:43:15Z","title_canon_sha256":"c0b0d2b95a7371bbf812373c71d7dbc040ff9baea45fe4e54cf760c0a6137cd0"},"schema_version":"1.0","source":{"id":"2004.12302","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.12302","created_at":"2026-07-05T01:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2004.12302v2","created_at":"2026-07-05T01:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12302","created_at":"2026-07-05T01:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"TUMKEMBUKNEX","created_at":"2026-07-05T01:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"TUMKEMBUKNEXPYPV","created_at":"2026-07-05T01:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"TUMKEMBU","created_at":"2026-07-05T01:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:aa8a957554b03d081b13c906d66ce41e6914bc1ae0cd78bb89e230b78e956d3a","target":"graph","created_at":"2026-07-05T01:05:12Z","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/2004.12302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, large-scale datasets have vastly facilitated the development in nearly all domains of Natural Language Processing. However, there is currently no cross-task dataset in NLP, which hinders the development of multi-task learning. We propose MATINF, the first jointly labeled large-scale dataset for classification, question answering and summarization. MATINF contains 1.07 million question-answer pairs with human-labeled categories and user-generated question descriptions. Based on such rich information, MATINF is applicable for three major NLP tasks, including classification, question an","authors_text":"Canwen Xu, Chenliang Li, Hongtao Wu, Jiaxin Pei, Yiyu Liu","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-26T07:43:15Z","title":"MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12302","kind":"arxiv","version":2},"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:e3f051a7a925ae0dece4ffdb3e9fa53acbd87a8273753f2b24728755bc5a9b7a","target":"record","created_at":"2026-07-05T01:05:12Z","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":"0a6bb9bd49a5595a5421cd68966d7ffcd24eccaece9f38053ad19a8f513b9ecf","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-26T07:43:15Z","title_canon_sha256":"c0b0d2b95a7371bbf812373c71d7dbc040ff9baea45fe4e54cf760c0a6137cd0"},"schema_version":"1.0","source":{"id":"2004.12302","kind":"arxiv","version":2}},"canonical_sha256":"9d18a23034534977e1f5ba0a3c9de3195fba28ef7f7d3eea3a7c9f20fcfe1f30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d18a23034534977e1f5ba0a3c9de3195fba28ef7f7d3eea3a7c9f20fcfe1f30","first_computed_at":"2026-07-05T01:05:12.629184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:12.629184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QD7NGcKc01tCfsG7JVRY8eCtBcdH0IyXb0u9VgH3gwnekHK9+5rVEvf1ODDvqTXEFaCR57k8SdEHIcjSYXbbCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:12.629632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.12302","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3f051a7a925ae0dece4ffdb3e9fa53acbd87a8273753f2b24728755bc5a9b7a","sha256:aa8a957554b03d081b13c906d66ce41e6914bc1ae0cd78bb89e230b78e956d3a"],"state_sha256":"32d4829ef11705e45785107266b35b2bb06233c8b19731466cea261877c259a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K4gcUsRLTBqDXzRUCRRu/HuFjbiJk25cEiht3o+/uZMu/tHEwRMfrtdflpt1EhrchY17iSpjnJKp/bKxAVSDAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T05:41:40.275898Z","bundle_sha256":"8e7e9812349633f46a4296bc02ad8500d19597120a5f55b41a1df0b7e29f99bf"}}