{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GLQF6GJBQZ6INM54C5YTGBL7EO","short_pith_number":"pith:GLQF6GJB","canonical_record":{"source":{"id":"2310.05863","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-10-09T17:00:20Z","cross_cats_sorted":["cs.AI","cs.CV","cs.SD"],"title_canon_sha256":"5b8728044a9fbb3d4cf9fd9c92bcad6025ce7eac3e78d4f28ea28dc40dedc527","abstract_canon_sha256":"bd1ddbdde1cc8f1505dad7154f3e9d4dc1bfeed43c1876e6b4e4f003a6a66e7e"},"schema_version":"1.0"},"canonical_sha256":"32e05f1921867c86b3bc177133057f23b330cb66d4159b449b68ffc02120bab1","source":{"kind":"arxiv","id":"2310.05863","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05863","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05863v2","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05863","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"pith_short_12","alias_value":"GLQF6GJBQZ6I","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"pith_short_16","alias_value":"GLQF6GJBQZ6INM54","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"pith_short_8","alias_value":"GLQF6GJB","created_at":"2026-07-05T06:59:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GLQF6GJBQZ6INM54C5YTGBL7EO","target":"record","payload":{"canonical_record":{"source":{"id":"2310.05863","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-10-09T17:00:20Z","cross_cats_sorted":["cs.AI","cs.CV","cs.SD"],"title_canon_sha256":"5b8728044a9fbb3d4cf9fd9c92bcad6025ce7eac3e78d4f28ea28dc40dedc527","abstract_canon_sha256":"bd1ddbdde1cc8f1505dad7154f3e9d4dc1bfeed43c1876e6b4e4f003a6a66e7e"},"schema_version":"1.0"},"canonical_sha256":"32e05f1921867c86b3bc177133057f23b330cb66d4159b449b68ffc02120bab1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:01.692438Z","signature_b64":"YDOhksHtI+iFzrGdf5heNe1/D4OcAZ7B8fYklMPS8sb1SGTnIGN53JB5fRUpkCxiw+Y058qQ7fHIUHN+UngKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32e05f1921867c86b3bc177133057f23b330cb66d4159b449b68ffc02120bab1","last_reissued_at":"2026-07-05T06:59:01.691860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:01.691860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.05863","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":"2026-07-05T06:59:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T1KRDclvlgg2OEvXFqWdKwwER/WZiruouVYsiyenV/Ikc46BnF7LFdSf9Vyga7YE7Nnw9j0sRIb3HEVOrx6vCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T00:32:16.814565Z"},"content_sha256":"c5c69dda9a14b1a21f77f932010ad8e5b241f93b0efcd70d8dfd5792c7ea5a2b","schema_version":"1.0","event_id":"sha256:c5c69dda9a14b1a21f77f932010ad8e5b241f93b0efcd70d8dfd5792c7ea5a2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GLQF6GJBQZ6INM54C5YTGBL7EO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Lu Lu, Tian Tan, Wei Li, Wenyi Yu, Xianzhao Chen, Zejun Ma","submitted_at":"2023-10-09T17:00:20Z","abstract_excerpt":"Audio-visual large language models (LLM) have drawn significant attention, yet the fine-grained combination of both input streams is rather under-explored, which is challenging but necessary for LLMs to understand general video inputs. To this end, a fine-grained audio-visual joint representation (FAVOR) learning framework for multimodal LLMs is proposed in this paper, which extends a text-based LLM to simultaneously perceive speech and audio events in the audio input stream and images or videos in the visual input stream, at the frame level. To fuse the audio and visual feature streams into j"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05863","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/2310.05863/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":"2026-07-05T06:59:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6h2rCYlvdM/zWwe9TCC+YNVox7dTacvJN+sXn0dlLgAvrJKrwHVDNyHTUfljFAdRTaYHh7jN4OVd45Txez20Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T00:32:16.815456Z"},"content_sha256":"65a78fd6ae8d20cf6616e677c602976fb0cb962cabb3c6caa87c7a29d5c5958c","schema_version":"1.0","event_id":"sha256:65a78fd6ae8d20cf6616e677c602976fb0cb962cabb3c6caa87c7a29d5c5958c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GLQF6GJBQZ6INM54C5YTGBL7EO/bundle.json","state_url":"https://pith.science/pith/GLQF6GJBQZ6INM54C5YTGBL7EO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GLQF6GJBQZ6INM54C5YTGBL7EO/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":"2026-08-20T00:32:16Z","links":{"resolver":"https://pith.science/pith/GLQF6GJBQZ6INM54C5YTGBL7EO","bundle":"https://pith.science/pith/GLQF6GJBQZ6INM54C5YTGBL7EO/bundle.json","state":"https://pith.science/pith/GLQF6GJBQZ6INM54C5YTGBL7EO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GLQF6GJBQZ6INM54C5YTGBL7EO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GLQF6GJBQZ6INM54C5YTGBL7EO","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":"bd1ddbdde1cc8f1505dad7154f3e9d4dc1bfeed43c1876e6b4e4f003a6a66e7e","cross_cats_sorted":["cs.AI","cs.CV","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-10-09T17:00:20Z","title_canon_sha256":"5b8728044a9fbb3d4cf9fd9c92bcad6025ce7eac3e78d4f28ea28dc40dedc527"},"schema_version":"1.0","source":{"id":"2310.05863","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05863","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05863v2","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05863","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"pith_short_12","alias_value":"GLQF6GJBQZ6I","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"pith_short_16","alias_value":"GLQF6GJBQZ6INM54","created_at":"2026-07-05T06:59:01Z"},{"alias_kind":"pith_short_8","alias_value":"GLQF6GJB","created_at":"2026-07-05T06:59:01Z"}],"graph_snapshots":[{"event_id":"sha256:65a78fd6ae8d20cf6616e677c602976fb0cb962cabb3c6caa87c7a29d5c5958c","target":"graph","created_at":"2026-07-05T06:59:01Z","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/2310.05863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual large language models (LLM) have drawn significant attention, yet the fine-grained combination of both input streams is rather under-explored, which is challenging but necessary for LLMs to understand general video inputs. To this end, a fine-grained audio-visual joint representation (FAVOR) learning framework for multimodal LLMs is proposed in this paper, which extends a text-based LLM to simultaneously perceive speech and audio events in the audio input stream and images or videos in the visual input stream, at the frame level. To fuse the audio and visual feature streams into j","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Lu Lu, Tian Tan, Wei Li, Wenyi Yu, Xianzhao Chen, Zejun Ma","cross_cats":["cs.AI","cs.CV","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-10-09T17:00:20Z","title":"Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05863","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:c5c69dda9a14b1a21f77f932010ad8e5b241f93b0efcd70d8dfd5792c7ea5a2b","target":"record","created_at":"2026-07-05T06:59:01Z","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":"bd1ddbdde1cc8f1505dad7154f3e9d4dc1bfeed43c1876e6b4e4f003a6a66e7e","cross_cats_sorted":["cs.AI","cs.CV","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-10-09T17:00:20Z","title_canon_sha256":"5b8728044a9fbb3d4cf9fd9c92bcad6025ce7eac3e78d4f28ea28dc40dedc527"},"schema_version":"1.0","source":{"id":"2310.05863","kind":"arxiv","version":2}},"canonical_sha256":"32e05f1921867c86b3bc177133057f23b330cb66d4159b449b68ffc02120bab1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32e05f1921867c86b3bc177133057f23b330cb66d4159b449b68ffc02120bab1","first_computed_at":"2026-07-05T06:59:01.691860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:01.691860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YDOhksHtI+iFzrGdf5heNe1/D4OcAZ7B8fYklMPS8sb1SGTnIGN53JB5fRUpkCxiw+Y058qQ7fHIUHN+UngKAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:01.692438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05863","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5c69dda9a14b1a21f77f932010ad8e5b241f93b0efcd70d8dfd5792c7ea5a2b","sha256:65a78fd6ae8d20cf6616e677c602976fb0cb962cabb3c6caa87c7a29d5c5958c"],"state_sha256":"0f6910240412dcec0b074a81957ce4fb4dde0b8fd08af68de2cd778a6c6f3819"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SRGnjRYaKEuYxHkKCz5YFJ5QL/KHoESbCopExvMt7pqD8ugXCaKaLsJh/zeMq1I4huGXoXzPt8l5lLtn8Un5Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T00:32:16.820647Z","bundle_sha256":"bbaaf55e23c2fb86889ce88a9a5ecbb7e20eb8cce77f9c70da8d546496fcfa65"}}