{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7ETDDRS6GQPSLZQX5FJ7YQ3RNZ","short_pith_number":"pith:7ETDDRS6","canonical_record":{"source":{"id":"2305.19972","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-31T16:01:20Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"40e5b535d6acd69a4a245b2a2adc31a673f1872495d5302b7912cbd88251661d","abstract_canon_sha256":"1e0b1a42c27fe87b2d2268e1b05fe088a8fe73964da470f4d3787eb10b39dc50"},"schema_version":"1.0"},"canonical_sha256":"f92631c65e341f25e617e953fc43716e7950f6aee0156337e2535168f70e7cf6","source":{"kind":"arxiv","id":"2305.19972","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19972","created_at":"2026-07-05T07:25:23Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19972v2","created_at":"2026-07-05T07:25:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19972","created_at":"2026-07-05T07:25:23Z"},{"alias_kind":"pith_short_12","alias_value":"7ETDDRS6GQPS","created_at":"2026-07-05T07:25:23Z"},{"alias_kind":"pith_short_16","alias_value":"7ETDDRS6GQPSLZQX","created_at":"2026-07-05T07:25:23Z"},{"alias_kind":"pith_short_8","alias_value":"7ETDDRS6","created_at":"2026-07-05T07:25:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7ETDDRS6GQPSLZQX5FJ7YQ3RNZ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.19972","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-31T16:01:20Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"40e5b535d6acd69a4a245b2a2adc31a673f1872495d5302b7912cbd88251661d","abstract_canon_sha256":"1e0b1a42c27fe87b2d2268e1b05fe088a8fe73964da470f4d3787eb10b39dc50"},"schema_version":"1.0"},"canonical_sha256":"f92631c65e341f25e617e953fc43716e7950f6aee0156337e2535168f70e7cf6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:23.772908Z","signature_b64":"jT1iQFZGTjQAndr/jg9Rn/tI+1A7yv77bs2/S7fYJfuZjPeOEkAHtBtcpUHHbRAuUUGTbBcr6WJsM5ZI1SEJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f92631c65e341f25e617e953fc43716e7950f6aee0156337e2535168f70e7cf6","last_reissued_at":"2026-07-05T07:25:23.772418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:23.772418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.19972","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:25:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P7USKJ9s+b8zWZtiKLbL2jyFid0OCq6Xyzp86hKGzCJvvBkoqiR0eIfxUJ0lRdr7U7L/6K0qH5zYMzKqP+5ZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T04:15:37.351336Z"},"content_sha256":"0df034cde895e8f0182f195c8abe7bb6a689f517040b3f9e4103e5f9817f9247","schema_version":"1.0","event_id":"sha256:0df034cde895e8f0182f195c8abe7bb6a689f517040b3f9e4103e5f9817f9247"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7ETDDRS6GQPSLZQX5FJ7YQ3RNZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VILAS: Exploring the Effects of Vision and Language Context in Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"eess.AS","authors_text":"Bo Xu, Feilong Chen, Jing Shi, Linghui Meng, Minglun Han, Pin Lv, Ziyi Ni","submitted_at":"2023-05-31T16:01:20Z","abstract_excerpt":"Enhancing automatic speech recognition (ASR) performance by leveraging additional multimodal information has shown promising results in previous studies. However, most of these works have primarily focused on utilizing visual cues derived from human lip motions. In fact, context-dependent visual and linguistic cues can also benefit in many scenarios. In this paper, we first propose ViLaS (Vision and Language into Automatic Speech Recognition), a novel multimodal ASR model based on the continuous integrate-and-fire (CIF) mechanism, which can integrate visual and textual context simultaneously o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19972","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/2305.19972/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:25:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4DAPMxuz2qTiB3GJs/MHRkTX1iyv63sJCl2kkcMc6yXmVQopP6x5yqidFI4IwIdavGuYSi854X0DlJlwzCDvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T04:15:37.351912Z"},"content_sha256":"f0e6f435f970c0f60e536d6378ecef2e2989d113f9e6b62b72fd587c2adcfca3","schema_version":"1.0","event_id":"sha256:f0e6f435f970c0f60e536d6378ecef2e2989d113f9e6b62b72fd587c2adcfca3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7ETDDRS6GQPSLZQX5FJ7YQ3RNZ/bundle.json","state_url":"https://pith.science/pith/7ETDDRS6GQPSLZQX5FJ7YQ3RNZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7ETDDRS6GQPSLZQX5FJ7YQ3RNZ/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":"2026-08-22T04:15:37Z","links":{"resolver":"https://pith.science/pith/7ETDDRS6GQPSLZQX5FJ7YQ3RNZ","bundle":"https://pith.science/pith/7ETDDRS6GQPSLZQX5FJ7YQ3RNZ/bundle.json","state":"https://pith.science/pith/7ETDDRS6GQPSLZQX5FJ7YQ3RNZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7ETDDRS6GQPSLZQX5FJ7YQ3RNZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7ETDDRS6GQPSLZQX5FJ7YQ3RNZ","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":"1e0b1a42c27fe87b2d2268e1b05fe088a8fe73964da470f4d3787eb10b39dc50","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-31T16:01:20Z","title_canon_sha256":"40e5b535d6acd69a4a245b2a2adc31a673f1872495d5302b7912cbd88251661d"},"schema_version":"1.0","source":{"id":"2305.19972","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19972","created_at":"2026-07-05T07:25:23Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19972v2","created_at":"2026-07-05T07:25:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19972","created_at":"2026-07-05T07:25:23Z"},{"alias_kind":"pith_short_12","alias_value":"7ETDDRS6GQPS","created_at":"2026-07-05T07:25:23Z"},{"alias_kind":"pith_short_16","alias_value":"7ETDDRS6GQPSLZQX","created_at":"2026-07-05T07:25:23Z"},{"alias_kind":"pith_short_8","alias_value":"7ETDDRS6","created_at":"2026-07-05T07:25:23Z"}],"graph_snapshots":[{"event_id":"sha256:f0e6f435f970c0f60e536d6378ecef2e2989d113f9e6b62b72fd587c2adcfca3","target":"graph","created_at":"2026-07-05T07:25:23Z","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/2305.19972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Enhancing automatic speech recognition (ASR) performance by leveraging additional multimodal information has shown promising results in previous studies. However, most of these works have primarily focused on utilizing visual cues derived from human lip motions. In fact, context-dependent visual and linguistic cues can also benefit in many scenarios. In this paper, we first propose ViLaS (Vision and Language into Automatic Speech Recognition), a novel multimodal ASR model based on the continuous integrate-and-fire (CIF) mechanism, which can integrate visual and textual context simultaneously o","authors_text":"Bo Xu, Feilong Chen, Jing Shi, Linghui Meng, Minglun Han, Pin Lv, Ziyi Ni","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-31T16:01:20Z","title":"VILAS: Exploring the Effects of Vision and Language Context in Automatic Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19972","kind":"arxiv","version":2},"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":"sha256:0df034cde895e8f0182f195c8abe7bb6a689f517040b3f9e4103e5f9817f9247","target":"record","created_at":"2026-07-05T07:25:23Z","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":"1e0b1a42c27fe87b2d2268e1b05fe088a8fe73964da470f4d3787eb10b39dc50","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-31T16:01:20Z","title_canon_sha256":"40e5b535d6acd69a4a245b2a2adc31a673f1872495d5302b7912cbd88251661d"},"schema_version":"1.0","source":{"id":"2305.19972","kind":"arxiv","version":2}},"canonical_sha256":"f92631c65e341f25e617e953fc43716e7950f6aee0156337e2535168f70e7cf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f92631c65e341f25e617e953fc43716e7950f6aee0156337e2535168f70e7cf6","first_computed_at":"2026-07-05T07:25:23.772418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:23.772418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jT1iQFZGTjQAndr/jg9Rn/tI+1A7yv77bs2/S7fYJfuZjPeOEkAHtBtcpUHHbRAuUUGTbBcr6WJsM5ZI1SEJCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:23.772908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19972","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0df034cde895e8f0182f195c8abe7bb6a689f517040b3f9e4103e5f9817f9247","sha256:f0e6f435f970c0f60e536d6378ecef2e2989d113f9e6b62b72fd587c2adcfca3"],"state_sha256":"91da7b56df86f83a8fadd28f0f2c77cee8c01fef0639d723aa805388b3122f3c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0r/1SGfSZj19PEIU01Ah4SgL61ehE5euT2OqyTeLLE+gQQme6F/kFLMgbnBcyXGGpbm1nfXmC2JvY4dygmb5Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T04:15:37.356142Z","bundle_sha256":"ffe5084820fc3606da74720cb314070e8206a905e0f1ec2ffc4b32da7bea5083"}}