{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5WCFTYZZBJ5DROXZNU7TFQJDRL","short_pith_number":"pith:5WCFTYZZ","canonical_record":{"source":{"id":"2412.09501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T17:50:39Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"09cea9b653be7d57e48021dfd033c79adf51a298103cf5cf39cb069e934e1652","abstract_canon_sha256":"4b6feb0631f1c1e94631496b0b1e4af3960bee874d148a10ef1689cfbf40d3c3"},"schema_version":"1.0"},"canonical_sha256":"ed8459e3390a7a38baf96d3f32c1238ae658217b99f5666e95b8213011a743ac","source":{"kind":"arxiv","id":"2412.09501","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09501","created_at":"2026-07-05T09:48:25Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09501v1","created_at":"2026-07-05T09:48:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09501","created_at":"2026-07-05T09:48:25Z"},{"alias_kind":"pith_short_12","alias_value":"5WCFTYZZBJ5D","created_at":"2026-07-05T09:48:25Z"},{"alias_kind":"pith_short_16","alias_value":"5WCFTYZZBJ5DROXZ","created_at":"2026-07-05T09:48:25Z"},{"alias_kind":"pith_short_8","alias_value":"5WCFTYZZ","created_at":"2026-07-05T09:48:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5WCFTYZZBJ5DROXZNU7TFQJDRL","target":"record","payload":{"canonical_record":{"source":{"id":"2412.09501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T17:50:39Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"09cea9b653be7d57e48021dfd033c79adf51a298103cf5cf39cb069e934e1652","abstract_canon_sha256":"4b6feb0631f1c1e94631496b0b1e4af3960bee874d148a10ef1689cfbf40d3c3"},"schema_version":"1.0"},"canonical_sha256":"ed8459e3390a7a38baf96d3f32c1238ae658217b99f5666e95b8213011a743ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:25.295218Z","signature_b64":"3p/fVGK2TpgajdtgdfdQC2DEKEzWZfLYt3JEC0c/oWa+rt3f1KOjXRlpwUjKojRvUAKcsjhATwQdKatTE/zOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed8459e3390a7a38baf96d3f32c1238ae658217b99f5666e95b8213011a743ac","last_reissued_at":"2026-07-05T09:48:25.294694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:25.294694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.09501","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":"2026-07-05T09:48:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KHCN6yJugOmrvojW/PIUBBZU7senD7ae/5CMMdKV9O2TCT3jPrfHcrGJpR+sustl9pgJN8XFRf/Re42lQa21DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:16:01.535228Z"},"content_sha256":"396a4db77213b3d6c7a24715dcd7be530d9ebe887a3e68dfd4d541430c652c53","schema_version":"1.0","event_id":"sha256:396a4db77213b3d6c7a24715dcd7be530d9ebe887a3e68dfd4d541430c652c53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5WCFTYZZBJ5DROXZNU7TFQJDRL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chengyao Wang, Eric Lo, Jiaya Jia, Jingyao Li, Longxiang Tang, Senqiao Yang, Shaozuo Yu, Shu Liu, Sitong Wu, Tianyuan Qu, Yanwei Li, Yuechen Zhang, Yukang Chen, Yuqi Liu, Zhisheng Zhong","submitted_at":"2024-12-12T17:50:39Z","abstract_excerpt":"As Multi-modal Large Language Models (MLLMs) evolve, expanding beyond single-domain capabilities is essential to meet the demands for more versatile and efficient AI. However, previous omni-models have insufficiently explored speech, neglecting its integration with multi-modality. We introduce Lyra, an efficient MLLM that enhances multimodal abilities, including advanced long-speech comprehension, sound understanding, cross-modality efficiency, and seamless speech interaction. To achieve efficiency and speech-centric capabilities, Lyra employs three strategies: (1) leveraging existing open-sou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09501","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.09501/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":"2026-07-05T09:48:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3qMLd4SDodTI5nSZk1AuLKMb38osUD+OUpXLshA9hZP6Dsoa7Nuan424/l/j7bN2jy3WsMwyTO9QLEFJGAWdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:16:01.535776Z"},"content_sha256":"cda25eed5025b000faa38924693a7001c26ed2a20e8401641c001d36ace7428b","schema_version":"1.0","event_id":"sha256:cda25eed5025b000faa38924693a7001c26ed2a20e8401641c001d36ace7428b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL/bundle.json","state_url":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL/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":"2026-08-03T19:16:01Z","links":{"resolver":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL","bundle":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL/bundle.json","state":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5WCFTYZZBJ5DROXZNU7TFQJDRL","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":"4b6feb0631f1c1e94631496b0b1e4af3960bee874d148a10ef1689cfbf40d3c3","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T17:50:39Z","title_canon_sha256":"09cea9b653be7d57e48021dfd033c79adf51a298103cf5cf39cb069e934e1652"},"schema_version":"1.0","source":{"id":"2412.09501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09501","created_at":"2026-07-05T09:48:25Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09501v1","created_at":"2026-07-05T09:48:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09501","created_at":"2026-07-05T09:48:25Z"},{"alias_kind":"pith_short_12","alias_value":"5WCFTYZZBJ5D","created_at":"2026-07-05T09:48:25Z"},{"alias_kind":"pith_short_16","alias_value":"5WCFTYZZBJ5DROXZ","created_at":"2026-07-05T09:48:25Z"},{"alias_kind":"pith_short_8","alias_value":"5WCFTYZZ","created_at":"2026-07-05T09:48:25Z"}],"graph_snapshots":[{"event_id":"sha256:cda25eed5025b000faa38924693a7001c26ed2a20e8401641c001d36ace7428b","target":"graph","created_at":"2026-07-05T09:48:25Z","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/2412.09501/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Multi-modal Large Language Models (MLLMs) evolve, expanding beyond single-domain capabilities is essential to meet the demands for more versatile and efficient AI. However, previous omni-models have insufficiently explored speech, neglecting its integration with multi-modality. We introduce Lyra, an efficient MLLM that enhances multimodal abilities, including advanced long-speech comprehension, sound understanding, cross-modality efficiency, and seamless speech interaction. To achieve efficiency and speech-centric capabilities, Lyra employs three strategies: (1) leveraging existing open-sou","authors_text":"Chengyao Wang, Eric Lo, Jiaya Jia, Jingyao Li, Longxiang Tang, Senqiao Yang, Shaozuo Yu, Shu Liu, Sitong Wu, Tianyuan Qu, Yanwei Li, Yuechen Zhang, Yukang Chen, Yuqi Liu, Zhisheng Zhong","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T17:50:39Z","title":"Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09501","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":"sha256:396a4db77213b3d6c7a24715dcd7be530d9ebe887a3e68dfd4d541430c652c53","target":"record","created_at":"2026-07-05T09:48:25Z","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":"4b6feb0631f1c1e94631496b0b1e4af3960bee874d148a10ef1689cfbf40d3c3","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T17:50:39Z","title_canon_sha256":"09cea9b653be7d57e48021dfd033c79adf51a298103cf5cf39cb069e934e1652"},"schema_version":"1.0","source":{"id":"2412.09501","kind":"arxiv","version":1}},"canonical_sha256":"ed8459e3390a7a38baf96d3f32c1238ae658217b99f5666e95b8213011a743ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed8459e3390a7a38baf96d3f32c1238ae658217b99f5666e95b8213011a743ac","first_computed_at":"2026-07-05T09:48:25.294694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:25.294694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3p/fVGK2TpgajdtgdfdQC2DEKEzWZfLYt3JEC0c/oWa+rt3f1KOjXRlpwUjKojRvUAKcsjhATwQdKatTE/zOCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:25.295218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:396a4db77213b3d6c7a24715dcd7be530d9ebe887a3e68dfd4d541430c652c53","sha256:cda25eed5025b000faa38924693a7001c26ed2a20e8401641c001d36ace7428b"],"state_sha256":"7bd1fdbacf46cd90044d1739296944cd76d6536a394a78daf5277dba2cd56b56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eCKm15x9A+zRUWcqKvVaEO5aG8m9rWP9gO2ZTSbfDtRx0Bd629JkDfmSrzFb/xEFSQ7ty0lORE0KDW7ZZffbCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:16:01.541119Z","bundle_sha256":"8a8ab38eaf43e4cb46fe4cd66008a7c8cf0f8d7483da235e81db46177d837ca5"}}