{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U22H3PXG7H4X34OGKMWKDPDYGC","short_pith_number":"pith:U22H3PXG","canonical_record":{"source":{"id":"2407.06606","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T07:15:56Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"549ed92183f38664a33916849f91d3aa1b0e58a993f6333c4eae5d7a75b39f95","abstract_canon_sha256":"13a3b6f88a7759970bf709ac5bf72eeca4e21e06edb817c363d832f025b4b7d6"},"schema_version":"1.0"},"canonical_sha256":"a6b47dbee6f9f97df1c6532ca1bc7830a8464cd614fdc761167245d0a0e3d8e3","source":{"kind":"arxiv","id":"2407.06606","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.06606","created_at":"2026-07-05T10:59:01Z"},{"alias_kind":"arxiv_version","alias_value":"2407.06606v4","created_at":"2026-07-05T10:59:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06606","created_at":"2026-07-05T10:59:01Z"},{"alias_kind":"pith_short_12","alias_value":"U22H3PXG7H4X","created_at":"2026-07-05T10:59:01Z"},{"alias_kind":"pith_short_16","alias_value":"U22H3PXG7H4X34OG","created_at":"2026-07-05T10:59:01Z"},{"alias_kind":"pith_short_8","alias_value":"U22H3PXG","created_at":"2026-07-05T10:59:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U22H3PXG7H4X34OGKMWKDPDYGC","target":"record","payload":{"canonical_record":{"source":{"id":"2407.06606","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T07:15:56Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"549ed92183f38664a33916849f91d3aa1b0e58a993f6333c4eae5d7a75b39f95","abstract_canon_sha256":"13a3b6f88a7759970bf709ac5bf72eeca4e21e06edb817c363d832f025b4b7d6"},"schema_version":"1.0"},"canonical_sha256":"a6b47dbee6f9f97df1c6532ca1bc7830a8464cd614fdc761167245d0a0e3d8e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:01.023925Z","signature_b64":"r8rdSZt5LooRuygWPwrNS7UEFCscR9B3ZiuJj8wvQWj+ichSV6X0+Guwo9CwoN44gxzIQRmYhCURNmFiJJl2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6b47dbee6f9f97df1c6532ca1bc7830a8464cd614fdc761167245d0a0e3d8e3","last_reissued_at":"2026-07-05T10:59:01.023495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:01.023495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.06606","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:59:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o2rcbc9aHKUtfri9r7bBB5dSLJyjTvlmtEQ97o+9JM6VwsbFhqnMzkgs24rVBNy61EnWyYvjwiOUKylVfQlcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:37:24.727154Z"},"content_sha256":"a7f43b94fb6e718dfe1634c6b97fe015728a3e86297fd3e3c1f00b1f8f0f5c48","schema_version":"1.0","event_id":"sha256:a7f43b94fb6e718dfe1634c6b97fe015728a3e86297fd3e3c1f00b1f8f0f5c48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U22H3PXG7H4X34OGKMWKDPDYGC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tailored Design of Audio-Visual Speech Recognition Models using Branchformers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Carlos-D. Mart\\'inez-Hinarejos, David Gimeno-G\\'omez","submitted_at":"2024-07-09T07:15:56Z","abstract_excerpt":"Recent advances in Audio-Visual Speech Recognition (AVSR) have led to unprecedented achievements in the field, improving the robustness of this type of system in adverse, noisy environments. In most cases, this task has been addressed through the design of models composed of two independent encoders, each dedicated to a specific modality. However, while recent works have explored unified audio-visual encoders, determining the optimal cross-modal architecture remains an ongoing challenge. Furthermore, such approaches often rely on models comprising vast amounts of parameters and high computatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06606","kind":"arxiv","version":4},"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/2407.06606/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":"2026-07-05T10:59:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rxo3vveUBd0kvxOa58BYIUiljBtCmA8HO6DoF+R7LiefevWOlrLM38L4bVDT9cykmgWQGKACT1MQ7u5pKTL8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:37:24.727529Z"},"content_sha256":"b28b48d86eae726c6395877985fd1f7b22470c8fcadea8dc387a4c8bc3facf86","schema_version":"1.0","event_id":"sha256:b28b48d86eae726c6395877985fd1f7b22470c8fcadea8dc387a4c8bc3facf86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U22H3PXG7H4X34OGKMWKDPDYGC/bundle.json","state_url":"https://pith.science/pith/U22H3PXG7H4X34OGKMWKDPDYGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U22H3PXG7H4X34OGKMWKDPDYGC/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":"2026-08-18T05:37:24Z","links":{"resolver":"https://pith.science/pith/U22H3PXG7H4X34OGKMWKDPDYGC","bundle":"https://pith.science/pith/U22H3PXG7H4X34OGKMWKDPDYGC/bundle.json","state":"https://pith.science/pith/U22H3PXG7H4X34OGKMWKDPDYGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U22H3PXG7H4X34OGKMWKDPDYGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U22H3PXG7H4X34OGKMWKDPDYGC","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":"13a3b6f88a7759970bf709ac5bf72eeca4e21e06edb817c363d832f025b4b7d6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T07:15:56Z","title_canon_sha256":"549ed92183f38664a33916849f91d3aa1b0e58a993f6333c4eae5d7a75b39f95"},"schema_version":"1.0","source":{"id":"2407.06606","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.06606","created_at":"2026-07-05T10:59:01Z"},{"alias_kind":"arxiv_version","alias_value":"2407.06606v4","created_at":"2026-07-05T10:59:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06606","created_at":"2026-07-05T10:59:01Z"},{"alias_kind":"pith_short_12","alias_value":"U22H3PXG7H4X","created_at":"2026-07-05T10:59:01Z"},{"alias_kind":"pith_short_16","alias_value":"U22H3PXG7H4X34OG","created_at":"2026-07-05T10:59:01Z"},{"alias_kind":"pith_short_8","alias_value":"U22H3PXG","created_at":"2026-07-05T10:59:01Z"}],"graph_snapshots":[{"event_id":"sha256:b28b48d86eae726c6395877985fd1f7b22470c8fcadea8dc387a4c8bc3facf86","target":"graph","created_at":"2026-07-05T10:59:01Z","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/2407.06606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Audio-Visual Speech Recognition (AVSR) have led to unprecedented achievements in the field, improving the robustness of this type of system in adverse, noisy environments. In most cases, this task has been addressed through the design of models composed of two independent encoders, each dedicated to a specific modality. However, while recent works have explored unified audio-visual encoders, determining the optimal cross-modal architecture remains an ongoing challenge. Furthermore, such approaches often rely on models comprising vast amounts of parameters and high computatio","authors_text":"Carlos-D. Mart\\'inez-Hinarejos, David Gimeno-G\\'omez","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T07:15:56Z","title":"Tailored Design of Audio-Visual Speech Recognition Models using Branchformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06606","kind":"arxiv","version":4},"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:a7f43b94fb6e718dfe1634c6b97fe015728a3e86297fd3e3c1f00b1f8f0f5c48","target":"record","created_at":"2026-07-05T10:59:01Z","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":"13a3b6f88a7759970bf709ac5bf72eeca4e21e06edb817c363d832f025b4b7d6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T07:15:56Z","title_canon_sha256":"549ed92183f38664a33916849f91d3aa1b0e58a993f6333c4eae5d7a75b39f95"},"schema_version":"1.0","source":{"id":"2407.06606","kind":"arxiv","version":4}},"canonical_sha256":"a6b47dbee6f9f97df1c6532ca1bc7830a8464cd614fdc761167245d0a0e3d8e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6b47dbee6f9f97df1c6532ca1bc7830a8464cd614fdc761167245d0a0e3d8e3","first_computed_at":"2026-07-05T10:59:01.023495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:01.023495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r8rdSZt5LooRuygWPwrNS7UEFCscR9B3ZiuJj8wvQWj+ichSV6X0+Guwo9CwoN44gxzIQRmYhCURNmFiJJl2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:01.023925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.06606","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7f43b94fb6e718dfe1634c6b97fe015728a3e86297fd3e3c1f00b1f8f0f5c48","sha256:b28b48d86eae726c6395877985fd1f7b22470c8fcadea8dc387a4c8bc3facf86"],"state_sha256":"cc2da1b142579fecb2c2b77ff35529107b07e355229ec314fb288b8dea4953f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BSOLhPdk/h9hNN//jO+RRxR043YaHT1XagtBiyZQNivSznp0AppPG93oDMvvxEamnC5FfUecvbR4YjK6NGjlAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T05:37:24.730105Z","bundle_sha256":"9c7c60ab264e0977f6eba1804f8514aae301ac463a622c07d4fe366fb895e658"}}