{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:C7DX6DEL6H77YNCQOPJDPXXEGK","short_pith_number":"pith:C7DX6DEL","schema_version":"1.0","canonical_sha256":"17c77f0c8bf1fffc345073d237dee4329e2eb309fa1992ee18e2ff489dcaee60","source":{"kind":"arxiv","id":"2109.05897","version":2},"attestation_state":"computed","paper":{"title":"Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhilash Nandy, Kapil Sachdeva, Niloy Ganguly, Pawan Goyal, Shubham Maddhashiya, Soumya Sharma","submitted_at":"2021-09-13T12:11:39Z","abstract_excerpt":"Answering questions asked from instructional corpora such as E-manuals, recipe books, etc., has been far less studied than open-domain factoid context-based question answering. This can be primarily attributed to the absence of standard benchmark datasets. In this paper we meticulously create a large amount of data connected with E-manuals and develop suitable algorithm to exploit it. We collect E-Manual Corpus, a huge corpus of 307,957 E-manuals and pretrain RoBERTa on this large corpus. We create various benchmark QA datasets which include question answer pairs curated by experts based upon "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2109.05897","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-13T12:11:39Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"6b87e5912a595189e2a30e5d61bb8fb0affabfad33521ef9f1b01a65c268d5a8","abstract_canon_sha256":"e1cc467db912827e3c6e38878f83b39a0fc2d600ca35584f2d7ed8131c650b65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:51.182969Z","signature_b64":"3OXOc9ekt1MCiSQTiThkY3eRGqo7Zzp5jj3YJ0yW4JNyzzPO1K0NFvmLIlrboYjO5mGcO8aoMKLFTw7LrzffAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17c77f0c8bf1fffc345073d237dee4329e2eb309fa1992ee18e2ff489dcaee60","last_reissued_at":"2026-07-05T03:13:51.182548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:51.182548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhilash Nandy, Kapil Sachdeva, Niloy Ganguly, Pawan Goyal, Shubham Maddhashiya, Soumya Sharma","submitted_at":"2021-09-13T12:11:39Z","abstract_excerpt":"Answering questions asked from instructional corpora such as E-manuals, recipe books, etc., has been far less studied than open-domain factoid context-based question answering. This can be primarily attributed to the absence of standard benchmark datasets. In this paper we meticulously create a large amount of data connected with E-manuals and develop suitable algorithm to exploit it. We collect E-Manual Corpus, a huge corpus of 307,957 E-manuals and pretrain RoBERTa on this large corpus. We create various benchmark QA datasets which include question answer pairs curated by experts based upon "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05897","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/2109.05897/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2109.05897","created_at":"2026-07-05T03:13:51.182608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05897v2","created_at":"2026-07-05T03:13:51.182608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05897","created_at":"2026-07-05T03:13:51.182608+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7DX6DEL6H77","created_at":"2026-07-05T03:13:51.182608+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7DX6DEL6H77YNCQ","created_at":"2026-07-05T03:13:51.182608+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7DX6DEL","created_at":"2026-07-05T03:13:51.182608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23299","citing_title":"Data-efficient Meta-models for Evaluation of Context-based Questions and Answers in LLMs","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7DX6DEL6H77YNCQOPJDPXXEGK","json":"https://pith.science/pith/C7DX6DEL6H77YNCQOPJDPXXEGK.json","graph_json":"https://pith.science/api/pith-number/C7DX6DEL6H77YNCQOPJDPXXEGK/graph.json","events_json":"https://pith.science/api/pith-number/C7DX6DEL6H77YNCQOPJDPXXEGK/events.json","paper":"https://pith.science/paper/C7DX6DEL"},"agent_actions":{"view_html":"https://pith.science/pith/C7DX6DEL6H77YNCQOPJDPXXEGK","download_json":"https://pith.science/pith/C7DX6DEL6H77YNCQOPJDPXXEGK.json","view_paper":"https://pith.science/paper/C7DX6DEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05897&json=true","fetch_graph":"https://pith.science/api/pith-number/C7DX6DEL6H77YNCQOPJDPXXEGK/graph.json","fetch_events":"https://pith.science/api/pith-number/C7DX6DEL6H77YNCQOPJDPXXEGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7DX6DEL6H77YNCQOPJDPXXEGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7DX6DEL6H77YNCQOPJDPXXEGK/action/storage_attestation","attest_author":"https://pith.science/pith/C7DX6DEL6H77YNCQOPJDPXXEGK/action/author_attestation","sign_citation":"https://pith.science/pith/C7DX6DEL6H77YNCQOPJDPXXEGK/action/citation_signature","submit_replication":"https://pith.science/pith/C7DX6DEL6H77YNCQOPJDPXXEGK/action/replication_record"}},"created_at":"2026-07-05T03:13:51.182608+00:00","updated_at":"2026-07-05T03:13:51.182608+00:00"}