{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GDVUOPGAGUOIIZNTMRSRYDJU2T","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":"2a26cb46ee044c2ea83bfb18957d6525518b90b95a7bbf1db2d273e9a7cce040","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-07-03T13:32:24Z","title_canon_sha256":"64432ce6f4cc5b59d32e4fff88ae143a50a3516346d7e21f541255ae92a5bd35"},"schema_version":"1.0","source":{"id":"2207.01039","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.01039","created_at":"2026-07-05T04:37:07Z"},{"alias_kind":"arxiv_version","alias_value":"2207.01039v1","created_at":"2026-07-05T04:37:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01039","created_at":"2026-07-05T04:37:07Z"},{"alias_kind":"pith_short_12","alias_value":"GDVUOPGAGUOI","created_at":"2026-07-05T04:37:07Z"},{"alias_kind":"pith_short_16","alias_value":"GDVUOPGAGUOIIZNT","created_at":"2026-07-05T04:37:07Z"},{"alias_kind":"pith_short_8","alias_value":"GDVUOPGA","created_at":"2026-07-05T04:37:07Z"}],"graph_snapshots":[{"event_id":"sha256:6af05b21fe161ac803810a8b6dacad46421a9591c3d011504a63b98f409f530a","target":"graph","created_at":"2026-07-05T04:37:07Z","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/2207.01039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Leveraging context information is an intuitive idea to improve performance on conversational automatic speech recognition(ASR). Previous works usually adopt recognized hypotheses of historical utterances as preceding context, which may bias the current recognized hypothesis due to the inevitable historicalrecognition errors. To avoid this problem, we propose an audio-textual cross-modal representation extractor to learn contextual representations directly from preceding speech. Specifically, it consists of two modal-related encoders, extracting high-level latent features from speech and the co","authors_text":"Kun Wei, Lei Xie, Long Ma, Sining Sun, Yike Zhang","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-07-03T13:32:24Z","title":"Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01039","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":"sha256:8ebc9aca946409e51a8c7f9136338eb3477570e2f815f9591b34613a1a364a0a","target":"record","created_at":"2026-07-05T04:37:07Z","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":"2a26cb46ee044c2ea83bfb18957d6525518b90b95a7bbf1db2d273e9a7cce040","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-07-03T13:32:24Z","title_canon_sha256":"64432ce6f4cc5b59d32e4fff88ae143a50a3516346d7e21f541255ae92a5bd35"},"schema_version":"1.0","source":{"id":"2207.01039","kind":"arxiv","version":1}},"canonical_sha256":"30eb473cc0351c8465b364651c0d34d4c05e70b9e42ff06a90438f52cf80b537","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30eb473cc0351c8465b364651c0d34d4c05e70b9e42ff06a90438f52cf80b537","first_computed_at":"2026-07-05T04:37:07.299914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:37:07.299914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z048A0vcfTUQIxbOFN3mAzI1mB1GdR7Mdj/nmmNoCSIpBe4ygjt7+oRp2CtwZGlcnMiH1DNJIv7KSKAEmL9/AA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:37:07.300292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.01039","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ebc9aca946409e51a8c7f9136338eb3477570e2f815f9591b34613a1a364a0a","sha256:6af05b21fe161ac803810a8b6dacad46421a9591c3d011504a63b98f409f530a"],"state_sha256":"6a9fb971602e381fd1f1e4b228f0929125927d6db4f081ea6ca5804ef89ca7ae"}