{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:36QXD2SZ26MPSRW24AGY7PEBHH","short_pith_number":"pith:36QXD2SZ","canonical_record":{"source":{"id":"1803.04840","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-13T14:35:00Z","cross_cats_sorted":[],"title_canon_sha256":"eacc1e7db22f24af372697e1daf37e6c3bff062f3d24d7b4aa39ffc5a65eb195","abstract_canon_sha256":"a1e2adf97134c613759dbcce961793729aab86933dd78ee11398b9dd4bfd2e4e"},"schema_version":"1.0"},"canonical_sha256":"dfa171ea59d798f946dae00d8fbc8139e413d38772ab3b3a7133bf04035c2e7b","source":{"kind":"arxiv","id":"1803.04840","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.04840","created_at":"2026-05-18T00:21:17Z"},{"alias_kind":"arxiv_version","alias_value":"1803.04840v1","created_at":"2026-05-18T00:21:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.04840","created_at":"2026-05-18T00:21:17Z"},{"alias_kind":"pith_short_12","alias_value":"36QXD2SZ26MP","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"36QXD2SZ26MPSRW2","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"36QXD2SZ","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:36QXD2SZ26MPSRW24AGY7PEBHH","target":"record","payload":{"canonical_record":{"source":{"id":"1803.04840","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-13T14:35:00Z","cross_cats_sorted":[],"title_canon_sha256":"eacc1e7db22f24af372697e1daf37e6c3bff062f3d24d7b4aa39ffc5a65eb195","abstract_canon_sha256":"a1e2adf97134c613759dbcce961793729aab86933dd78ee11398b9dd4bfd2e4e"},"schema_version":"1.0"},"canonical_sha256":"dfa171ea59d798f946dae00d8fbc8139e413d38772ab3b3a7133bf04035c2e7b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:17.601913Z","signature_b64":"rn0Mki6+npjQX8lXNEiOZp/znKechqHVhINx0Scszo13Z5R/XGNl96gOfqElINJFiEYSrPl6CdZUM8wLKotZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfa171ea59d798f946dae00d8fbc8139e413d38772ab3b3a7133bf04035c2e7b","last_reissued_at":"2026-05-18T00:21:17.601438Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:17.601438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.04840","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:21:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XXvc3+xqDqQF3FvWZo6YnFOtjRjUEn60NXfVNvVmfd9djWfvzHcwMY7UddtzdiK3GVGxImh1XBUg5QM67Y11Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T10:21:28.580102Z"},"content_sha256":"6196bc3014b98a39334c38c7e5d0766fede75862378ab500dcd77bfa359cee4e","schema_version":"1.0","event_id":"sha256:6196bc3014b98a39334c38c7e5d0766fede75862378ab500dcd77bfa359cee4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:36QXD2SZ26MPSRW24AGY7PEBHH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Resource aware design of a deep convolutional-recurrent neural network for speech recognition through audio-visual sensor fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bert Moons, Marian Verhelst, Matthijs Van keirsbilck","submitted_at":"2018-03-13T14:35:00Z","abstract_excerpt":"Today's Automatic Speech Recognition systems only rely on acoustic signals and often don't perform well under noisy conditions. Performing multi-modal speech recognition - processing acoustic speech signals and lip-reading video simultaneously - significantly enhances the performance of such systems, especially in noisy environments. This work presents the design of such an audio-visual system for Automated Speech Recognition, taking memory and computation requirements into account. First, a Long-Short-Term-Memory neural network for acoustic speech recognition is designed. Second, Convolutiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.04840","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:21:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qo87lnGaj/DTqxMXjmy0HfPVhzhY0NyQGuvb/6qJTiqztoKA7RYVjk8C0pmi/jYKaFYbawuhEv3IDYf1xd13Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T10:21:28.580461Z"},"content_sha256":"bb1b5c03296a33ca0d8f0a0fd8756073fd7f7586ecfca3ac94cad9173e57dc71","schema_version":"1.0","event_id":"sha256:bb1b5c03296a33ca0d8f0a0fd8756073fd7f7586ecfca3ac94cad9173e57dc71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/36QXD2SZ26MPSRW24AGY7PEBHH/bundle.json","state_url":"https://pith.science/pith/36QXD2SZ26MPSRW24AGY7PEBHH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/36QXD2SZ26MPSRW24AGY7PEBHH/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":"2026-05-19T10:21:28Z","links":{"resolver":"https://pith.science/pith/36QXD2SZ26MPSRW24AGY7PEBHH","bundle":"https://pith.science/pith/36QXD2SZ26MPSRW24AGY7PEBHH/bundle.json","state":"https://pith.science/pith/36QXD2SZ26MPSRW24AGY7PEBHH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/36QXD2SZ26MPSRW24AGY7PEBHH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:36QXD2SZ26MPSRW24AGY7PEBHH","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":"a1e2adf97134c613759dbcce961793729aab86933dd78ee11398b9dd4bfd2e4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-13T14:35:00Z","title_canon_sha256":"eacc1e7db22f24af372697e1daf37e6c3bff062f3d24d7b4aa39ffc5a65eb195"},"schema_version":"1.0","source":{"id":"1803.04840","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.04840","created_at":"2026-05-18T00:21:17Z"},{"alias_kind":"arxiv_version","alias_value":"1803.04840v1","created_at":"2026-05-18T00:21:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.04840","created_at":"2026-05-18T00:21:17Z"},{"alias_kind":"pith_short_12","alias_value":"36QXD2SZ26MP","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"36QXD2SZ26MPSRW2","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"36QXD2SZ","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:bb1b5c03296a33ca0d8f0a0fd8756073fd7f7586ecfca3ac94cad9173e57dc71","target":"graph","created_at":"2026-05-18T00:21:17Z","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"},"paper":{"abstract_excerpt":"Today's Automatic Speech Recognition systems only rely on acoustic signals and often don't perform well under noisy conditions. Performing multi-modal speech recognition - processing acoustic speech signals and lip-reading video simultaneously - significantly enhances the performance of such systems, especially in noisy environments. This work presents the design of such an audio-visual system for Automated Speech Recognition, taking memory and computation requirements into account. First, a Long-Short-Term-Memory neural network for acoustic speech recognition is designed. Second, Convolutiona","authors_text":"Bert Moons, Marian Verhelst, Matthijs Van keirsbilck","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-13T14:35:00Z","title":"Resource aware design of a deep convolutional-recurrent neural network for speech recognition through audio-visual sensor fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.04840","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":"sha256:6196bc3014b98a39334c38c7e5d0766fede75862378ab500dcd77bfa359cee4e","target":"record","created_at":"2026-05-18T00:21:17Z","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":"a1e2adf97134c613759dbcce961793729aab86933dd78ee11398b9dd4bfd2e4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-13T14:35:00Z","title_canon_sha256":"eacc1e7db22f24af372697e1daf37e6c3bff062f3d24d7b4aa39ffc5a65eb195"},"schema_version":"1.0","source":{"id":"1803.04840","kind":"arxiv","version":1}},"canonical_sha256":"dfa171ea59d798f946dae00d8fbc8139e413d38772ab3b3a7133bf04035c2e7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfa171ea59d798f946dae00d8fbc8139e413d38772ab3b3a7133bf04035c2e7b","first_computed_at":"2026-05-18T00:21:17.601438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:21:17.601438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rn0Mki6+npjQX8lXNEiOZp/znKechqHVhINx0Scszo13Z5R/XGNl96gOfqElINJFiEYSrPl6CdZUM8wLKotZCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:21:17.601913Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.04840","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6196bc3014b98a39334c38c7e5d0766fede75862378ab500dcd77bfa359cee4e","sha256:bb1b5c03296a33ca0d8f0a0fd8756073fd7f7586ecfca3ac94cad9173e57dc71"],"state_sha256":"74b62378c919a9f6d1601aa431657406e1200fc839eae3fc6a1f045dc50b4bf8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6PDfwlgif5x5QkNDH0K8hTzgM6+aQCHDq1FYObD+COjL+ypxhncw0fDVPtLggpHStbBf6Un91ZhGx5ejwEgsCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T10:21:28.582034Z","bundle_sha256":"b3e85558d2bb038d10b86b642a1075955af3ae8f108f5d1003198d4a0ce3deb8"}}