{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OG7YBAYQVA4DY3IBMF6QAYAXK4","short_pith_number":"pith:OG7YBAYQ","canonical_record":{"source":{"id":"2505.14336","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-20T13:20:55Z","cross_cats_sorted":["cs.CV","cs.MM","cs.SD"],"title_canon_sha256":"8817d31d86043d14f3dfd6d5f0c3c34d3157704b1d11b9681a0d2878029df9a0","abstract_canon_sha256":"4e45ba622b84e63632199ef579ed12618549537734199559f0cc56614be01f06"},"schema_version":"1.0"},"canonical_sha256":"71bf808310a8383c6d01617d006017572a22cd846d1d09040d70016b9a9ef6d1","source":{"kind":"arxiv","id":"2505.14336","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14336","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14336v2","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14336","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"pith_short_12","alias_value":"OG7YBAYQVA4D","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"pith_short_16","alias_value":"OG7YBAYQVA4DY3IB","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"pith_short_8","alias_value":"OG7YBAYQ","created_at":"2026-07-05T11:06:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OG7YBAYQVA4DY3IBMF6QAYAXK4","target":"record","payload":{"canonical_record":{"source":{"id":"2505.14336","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-20T13:20:55Z","cross_cats_sorted":["cs.CV","cs.MM","cs.SD"],"title_canon_sha256":"8817d31d86043d14f3dfd6d5f0c3c34d3157704b1d11b9681a0d2878029df9a0","abstract_canon_sha256":"4e45ba622b84e63632199ef579ed12618549537734199559f0cc56614be01f06"},"schema_version":"1.0"},"canonical_sha256":"71bf808310a8383c6d01617d006017572a22cd846d1d09040d70016b9a9ef6d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:33.353543Z","signature_b64":"nLWfgFozO3t1538EOpRqQnOLc587DOMWSeN67vzsUKW2FQPgQgNgxm0a+S0YC0WjxjlCKBBgHnd0V4zOYs8VAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71bf808310a8383c6d01617d006017572a22cd846d1d09040d70016b9a9ef6d1","last_reissued_at":"2026-07-05T11:06:33.353045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:33.353045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.14336","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":"2026-07-05T11:06:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FUie/Fjz2dvyYMInYIw8m+wwcIPNvSJJaCQ/636jnV7faWLaocoH5/gwk/emWHY7NaYGPbYH7ojsSf0yReNsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T01:00:36.563587Z"},"content_sha256":"09a1ac7a50e3997d4338b8dc75946dc8727cc8ac062b4194ef4e092348933297","schema_version":"1.0","event_id":"sha256:09a1ac7a50e3997d4338b8dc75946dc8727cc8ac062b4194ef4e092348933297"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OG7YBAYQVA4DY3IBMF6QAYAXK4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alessio Brutti, Daniele Falavigna, Minsu Kim, Stavros Petridis, Umberto Cappellazzo","submitted_at":"2025-05-20T13:20:55Z","abstract_excerpt":"Audio-Visual Speech Recognition (AVSR) enhances robustness in noisy environments by integrating visual cues. While recent advances integrate Large Language Models (LLMs) into AVSR, their high computational cost hinders deployment in resource-constrained settings. To address this, we propose Llama-SMoP, an efficient Multimodal LLM that employs a Sparse Mixture of Projectors (SMoP) module to scale model capacity without increasing inference costs. By incorporating sparsely-gated mixture-of-experts (MoE) projectors, Llama-SMoP enables the use of smaller LLMs while maintaining strong performance. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14336","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/2505.14336/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":"2026-07-05T11:06:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVOOKypySRWhEkIue5ESi49sY+Ha3F988JfTR19Quzi/yq+dpu90DyZN+UUvEiKVdVKnGIXcNUHh0kgItIXjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T01:00:36.563972Z"},"content_sha256":"60e52442fadfe34ff42d83c4aa91d5690d8808979efe4c2a461fe2cd2f1374f2","schema_version":"1.0","event_id":"sha256:60e52442fadfe34ff42d83c4aa91d5690d8808979efe4c2a461fe2cd2f1374f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OG7YBAYQVA4DY3IBMF6QAYAXK4/bundle.json","state_url":"https://pith.science/pith/OG7YBAYQVA4DY3IBMF6QAYAXK4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OG7YBAYQVA4DY3IBMF6QAYAXK4/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":"2026-07-26T01:00:36Z","links":{"resolver":"https://pith.science/pith/OG7YBAYQVA4DY3IBMF6QAYAXK4","bundle":"https://pith.science/pith/OG7YBAYQVA4DY3IBMF6QAYAXK4/bundle.json","state":"https://pith.science/pith/OG7YBAYQVA4DY3IBMF6QAYAXK4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OG7YBAYQVA4DY3IBMF6QAYAXK4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OG7YBAYQVA4DY3IBMF6QAYAXK4","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":"4e45ba622b84e63632199ef579ed12618549537734199559f0cc56614be01f06","cross_cats_sorted":["cs.CV","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-20T13:20:55Z","title_canon_sha256":"8817d31d86043d14f3dfd6d5f0c3c34d3157704b1d11b9681a0d2878029df9a0"},"schema_version":"1.0","source":{"id":"2505.14336","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14336","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14336v2","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14336","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"pith_short_12","alias_value":"OG7YBAYQVA4D","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"pith_short_16","alias_value":"OG7YBAYQVA4DY3IB","created_at":"2026-07-05T11:06:33Z"},{"alias_kind":"pith_short_8","alias_value":"OG7YBAYQ","created_at":"2026-07-05T11:06:33Z"}],"graph_snapshots":[{"event_id":"sha256:60e52442fadfe34ff42d83c4aa91d5690d8808979efe4c2a461fe2cd2f1374f2","target":"graph","created_at":"2026-07-05T11:06:33Z","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/2505.14336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Speech Recognition (AVSR) enhances robustness in noisy environments by integrating visual cues. While recent advances integrate Large Language Models (LLMs) into AVSR, their high computational cost hinders deployment in resource-constrained settings. To address this, we propose Llama-SMoP, an efficient Multimodal LLM that employs a Sparse Mixture of Projectors (SMoP) module to scale model capacity without increasing inference costs. By incorporating sparsely-gated mixture-of-experts (MoE) projectors, Llama-SMoP enables the use of smaller LLMs while maintaining strong performance. ","authors_text":"Alessio Brutti, Daniele Falavigna, Minsu Kim, Stavros Petridis, Umberto Cappellazzo","cross_cats":["cs.CV","cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-20T13:20:55Z","title":"Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14336","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":"sha256:09a1ac7a50e3997d4338b8dc75946dc8727cc8ac062b4194ef4e092348933297","target":"record","created_at":"2026-07-05T11:06:33Z","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":"4e45ba622b84e63632199ef579ed12618549537734199559f0cc56614be01f06","cross_cats_sorted":["cs.CV","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-20T13:20:55Z","title_canon_sha256":"8817d31d86043d14f3dfd6d5f0c3c34d3157704b1d11b9681a0d2878029df9a0"},"schema_version":"1.0","source":{"id":"2505.14336","kind":"arxiv","version":2}},"canonical_sha256":"71bf808310a8383c6d01617d006017572a22cd846d1d09040d70016b9a9ef6d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71bf808310a8383c6d01617d006017572a22cd846d1d09040d70016b9a9ef6d1","first_computed_at":"2026-07-05T11:06:33.353045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:33.353045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nLWfgFozO3t1538EOpRqQnOLc587DOMWSeN67vzsUKW2FQPgQgNgxm0a+S0YC0WjxjlCKBBgHnd0V4zOYs8VAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:33.353543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14336","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09a1ac7a50e3997d4338b8dc75946dc8727cc8ac062b4194ef4e092348933297","sha256:60e52442fadfe34ff42d83c4aa91d5690d8808979efe4c2a461fe2cd2f1374f2"],"state_sha256":"bd01e5880d69f4ad1127a6e6eebb17ad15f57ce57db6e2a6975d6612c8c6aa67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TVh+aa/fWbPP+s2NwIjVHzVyIcRbfNAj+0bKYZ8ELS0lyPnctiVFy6oQLGpbQmgLXFewJqlA36G3Mz7lwWOEDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T01:00:36.566142Z","bundle_sha256":"929302b4531d828b222a4e803cd28fede3c4272ff8dcdb89ddec9465994f830b"}}