{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KLZ6FPLPNCUZI4EWDUABJZO5AJ","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":"403f7b7d729467afdc00850ae5506e100e9a1380bf0d6add165288c5f419353d","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-08T01:13:14Z","title_canon_sha256":"c4423d51eeb29d2be95b1988d107a5ae4f85a26b42cd975b26c0514deca317f8"},"schema_version":"1.0","source":{"id":"2109.03381","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.03381","created_at":"2026-07-05T03:12:30Z"},{"alias_kind":"arxiv_version","alias_value":"2109.03381v1","created_at":"2026-07-05T03:12:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03381","created_at":"2026-07-05T03:12:30Z"},{"alias_kind":"pith_short_12","alias_value":"KLZ6FPLPNCUZ","created_at":"2026-07-05T03:12:30Z"},{"alias_kind":"pith_short_16","alias_value":"KLZ6FPLPNCUZI4EW","created_at":"2026-07-05T03:12:30Z"},{"alias_kind":"pith_short_8","alias_value":"KLZ6FPLP","created_at":"2026-07-05T03:12:30Z"}],"graph_snapshots":[{"event_id":"sha256:e919091bde092fd18ff729fddb4ff7c4c9d53785750e4572f8a95e35720c2bd8","target":"graph","created_at":"2026-07-05T03:12:30Z","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/2109.03381/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spoken question answering (SQA) requires fine-grained understanding of both spoken documents and questions for the optimal answer prediction. In this paper, we propose novel training schemes for spoken question answering with a self-supervised training stage and a contrastive representation learning stage. In the self-supervised stage, we propose three auxiliary self-supervised tasks, including utterance restoration, utterance insertion, and question discrimination, and jointly train the model to capture consistency and coherence among speech documents without any additional data or annotation","authors_text":"Chenyu You, Nuo Chen, Yuexian Zou","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-08T01:13:14Z","title":"Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03381","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:d8b643136316cacab852eb4515879cd9808a27f8fc9720e115e17c6e8242c6c7","target":"record","created_at":"2026-07-05T03:12:30Z","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":"403f7b7d729467afdc00850ae5506e100e9a1380bf0d6add165288c5f419353d","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-08T01:13:14Z","title_canon_sha256":"c4423d51eeb29d2be95b1988d107a5ae4f85a26b42cd975b26c0514deca317f8"},"schema_version":"1.0","source":{"id":"2109.03381","kind":"arxiv","version":1}},"canonical_sha256":"52f3e2bd6f68a99470961d0014e5dd0257074e27859aaf941a387c0947133a7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52f3e2bd6f68a99470961d0014e5dd0257074e27859aaf941a387c0947133a7f","first_computed_at":"2026-07-05T03:12:30.386669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:12:30.386669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MaY+IMTdz5rnbKnKDckiemem9fDX3xtyNlK0Oe0GQcYUaRkM0AEPLuuNR0L+ISCc85SSddejCrzHlkjU1u1+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:12:30.387199Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.03381","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8b643136316cacab852eb4515879cd9808a27f8fc9720e115e17c6e8242c6c7","sha256:e919091bde092fd18ff729fddb4ff7c4c9d53785750e4572f8a95e35720c2bd8"],"state_sha256":"311f4fc1a0a3f943fd563cfda1972bfcc7320ff22a384993af1f61e888357b70"}