{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SPLJWFKMGXSW4VAVT5TN7T76M6","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":"65ae9d38e3889db2457afb54ca137ee624602955049d6dd3a2921b3952bceadd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-03T08:13:09Z","title_canon_sha256":"ecec78203f8f73b34db80b68252e5f53f1f154e372b5f411cfee132035f74f5e"},"schema_version":"1.0","source":{"id":"2008.00702","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.00702","created_at":"2026-07-05T01:24:10Z"},{"alias_kind":"arxiv_version","alias_value":"2008.00702v1","created_at":"2026-07-05T01:24:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.00702","created_at":"2026-07-05T01:24:10Z"},{"alias_kind":"pith_short_12","alias_value":"SPLJWFKMGXSW","created_at":"2026-07-05T01:24:10Z"},{"alias_kind":"pith_short_16","alias_value":"SPLJWFKMGXSW4VAV","created_at":"2026-07-05T01:24:10Z"},{"alias_kind":"pith_short_8","alias_value":"SPLJWFKM","created_at":"2026-07-05T01:24:10Z"}],"graph_snapshots":[{"event_id":"sha256:24ab4466f25e7b9015adb01e163a060ff6679f9f784ea36dcff3105e4fbc4ef4","target":"graph","created_at":"2026-07-05T01:24:10Z","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/2008.00702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we explore a multimodal semi-supervised learning approach for punctuation prediction by learning representations from large amounts of unlabelled audio and text data. Conventional approaches in speech processing typically use forced alignment to encoder per frame acoustic features to word level features and perform multimodal fusion of the resulting acoustic and lexical representations. As an alternative, we explore attention based multimodal fusion and compare its performance with forced alignment based fusion. Experiments conducted on the Fisher corpus show that our proposed ap","authors_text":"Dhanush Bekal, Katrin Kirchhoff, Monica Sunkara, Sravan Bodapati, Srikanth Ronanki","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-03T08:13:09Z","title":"Multimodal Semi-supervised Learning Framework for Punctuation Prediction in Conversational Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.00702","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":"sha256:96f6aa60a2a135a60472eb930b8fd5da06bb2322c39a631c92d8592dcbcf32a0","target":"record","created_at":"2026-07-05T01:24:10Z","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":"65ae9d38e3889db2457afb54ca137ee624602955049d6dd3a2921b3952bceadd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-03T08:13:09Z","title_canon_sha256":"ecec78203f8f73b34db80b68252e5f53f1f154e372b5f411cfee132035f74f5e"},"schema_version":"1.0","source":{"id":"2008.00702","kind":"arxiv","version":1}},"canonical_sha256":"93d69b154c35e56e54159f66dfcffe678d18b9373532c937cc3461ca5b73b13a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93d69b154c35e56e54159f66dfcffe678d18b9373532c937cc3461ca5b73b13a","first_computed_at":"2026-07-05T01:24:10.050745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:24:10.050745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ym9EvBbEexy1qvgA4iou1hSOz6hTj6P3Ip+uqfbtW6BaQtSqCg3Ujst8I6KeggKK/XtlHxoAJMuD5J+C3YApBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:24:10.051272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.00702","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96f6aa60a2a135a60472eb930b8fd5da06bb2322c39a631c92d8592dcbcf32a0","sha256:24ab4466f25e7b9015adb01e163a060ff6679f9f784ea36dcff3105e4fbc4ef4"],"state_sha256":"8a3369418ff385c2e6c50c5671dfadc6d11ebe06ae4400a2b309aa7e260fbcb8"}