{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:L7TOXXD3WCCZ2RMCPT72JNSNI2","short_pith_number":"pith:L7TOXXD3","canonical_record":{"source":{"id":"2406.15704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-22T01:36:11Z","cross_cats_sorted":[],"title_canon_sha256":"f9852db2f8430da1c8763ad4d9af924f9a75e2d45901f47119e4e93b9ef02ce4","abstract_canon_sha256":"bfe3e1126f7d0a218f87b6bad67b10fbfc746b0c10f8dd5ef445adbc71404f5d"},"schema_version":"1.0"},"canonical_sha256":"5fe6ebdc7bb0859d45827cffa4b64d46b1e81cf5d1f62d5e9935490f61fed5c3","source":{"kind":"arxiv","id":"2406.15704","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15704","created_at":"2026-07-05T08:35:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15704v1","created_at":"2026-07-05T08:35:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15704","created_at":"2026-07-05T08:35:26Z"},{"alias_kind":"pith_short_12","alias_value":"L7TOXXD3WCCZ","created_at":"2026-07-05T08:35:26Z"},{"alias_kind":"pith_short_16","alias_value":"L7TOXXD3WCCZ2RMC","created_at":"2026-07-05T08:35:26Z"},{"alias_kind":"pith_short_8","alias_value":"L7TOXXD3","created_at":"2026-07-05T08:35:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:L7TOXXD3WCCZ2RMCPT72JNSNI2","target":"record","payload":{"canonical_record":{"source":{"id":"2406.15704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-22T01:36:11Z","cross_cats_sorted":[],"title_canon_sha256":"f9852db2f8430da1c8763ad4d9af924f9a75e2d45901f47119e4e93b9ef02ce4","abstract_canon_sha256":"bfe3e1126f7d0a218f87b6bad67b10fbfc746b0c10f8dd5ef445adbc71404f5d"},"schema_version":"1.0"},"canonical_sha256":"5fe6ebdc7bb0859d45827cffa4b64d46b1e81cf5d1f62d5e9935490f61fed5c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:26.326906Z","signature_b64":"7r4MWhTHry28HKN9iTTqZ3+57xBg0U+e8ens9a6r1bml8Dua1W8bYMoxL9oW4V2YzYQXA7a7K906fKtGIUTmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fe6ebdc7bb0859d45827cffa4b64d46b1e81cf5d1f62d5e9935490f61fed5c3","last_reissued_at":"2026-07-05T08:35:26.326395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:26.326395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.15704","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":"2026-07-05T08:35:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4NmtnwjiGImmLFFQ9wPc1EmkyG1g+EMUht106aucrU2YANnAK6+LoLL5I5/bWdIqUHeA2Lx5jh1XxU4AP/L6CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:29:58.572057Z"},"content_sha256":"ec47019ae04f76182b0c3f1f381f76bb5e7436f1e68d6d7a17d5a37e664b0e9d","schema_version":"1.0","event_id":"sha256:ec47019ae04f76182b0c3f1f381f76bb5e7436f1e68d6d7a17d5a37e664b0e9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:L7TOXXD3WCCZ2RMCPT72JNSNI2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Lu Lu, Tian Tan, Wei Li, Wenyi Yu, Xianzhao Chen, Yuxuan Wang, Zejun Ma","submitted_at":"2024-06-22T01:36:11Z","abstract_excerpt":"Speech understanding as an element of the more generic video understanding using audio-visual large language models (av-LLMs) is a crucial yet understudied aspect. This paper proposes video-SALMONN, a single end-to-end av-LLM for video processing, which can understand not only visual frame sequences, audio events and music, but speech as well. To obtain fine-grained temporal information required by speech understanding, while keeping efficient for other video elements, this paper proposes a novel multi-resolution causal Q-Former (MRC Q-Former) structure to connect pre-trained audio-visual enco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15704","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/2406.15704/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":"2026-07-05T08:35:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g05RNBBSdbIO7R28Px9YCf74A7kEEp37z4XOd+ro0mG7DEj3IdYL42strxIP64csnkXup75a7Msou++uVYC6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:29:58.572618Z"},"content_sha256":"440ddb425ad8eaf205f1a4bb56805b0d3a8508517367e3a2b5dd46f77f4d4f7a","schema_version":"1.0","event_id":"sha256:440ddb425ad8eaf205f1a4bb56805b0d3a8508517367e3a2b5dd46f77f4d4f7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L7TOXXD3WCCZ2RMCPT72JNSNI2/bundle.json","state_url":"https://pith.science/pith/L7TOXXD3WCCZ2RMCPT72JNSNI2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L7TOXXD3WCCZ2RMCPT72JNSNI2/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":"2026-08-08T12:29:58Z","links":{"resolver":"https://pith.science/pith/L7TOXXD3WCCZ2RMCPT72JNSNI2","bundle":"https://pith.science/pith/L7TOXXD3WCCZ2RMCPT72JNSNI2/bundle.json","state":"https://pith.science/pith/L7TOXXD3WCCZ2RMCPT72JNSNI2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L7TOXXD3WCCZ2RMCPT72JNSNI2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L7TOXXD3WCCZ2RMCPT72JNSNI2","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":"bfe3e1126f7d0a218f87b6bad67b10fbfc746b0c10f8dd5ef445adbc71404f5d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-22T01:36:11Z","title_canon_sha256":"f9852db2f8430da1c8763ad4d9af924f9a75e2d45901f47119e4e93b9ef02ce4"},"schema_version":"1.0","source":{"id":"2406.15704","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15704","created_at":"2026-07-05T08:35:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15704v1","created_at":"2026-07-05T08:35:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15704","created_at":"2026-07-05T08:35:26Z"},{"alias_kind":"pith_short_12","alias_value":"L7TOXXD3WCCZ","created_at":"2026-07-05T08:35:26Z"},{"alias_kind":"pith_short_16","alias_value":"L7TOXXD3WCCZ2RMC","created_at":"2026-07-05T08:35:26Z"},{"alias_kind":"pith_short_8","alias_value":"L7TOXXD3","created_at":"2026-07-05T08:35:26Z"}],"graph_snapshots":[{"event_id":"sha256:440ddb425ad8eaf205f1a4bb56805b0d3a8508517367e3a2b5dd46f77f4d4f7a","target":"graph","created_at":"2026-07-05T08:35:26Z","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/2406.15704/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech understanding as an element of the more generic video understanding using audio-visual large language models (av-LLMs) is a crucial yet understudied aspect. This paper proposes video-SALMONN, a single end-to-end av-LLM for video processing, which can understand not only visual frame sequences, audio events and music, but speech as well. To obtain fine-grained temporal information required by speech understanding, while keeping efficient for other video elements, this paper proposes a novel multi-resolution causal Q-Former (MRC Q-Former) structure to connect pre-trained audio-visual enco","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Lu Lu, Tian Tan, Wei Li, Wenyi Yu, Xianzhao Chen, Yuxuan Wang, Zejun Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-22T01:36:11Z","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15704","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:ec47019ae04f76182b0c3f1f381f76bb5e7436f1e68d6d7a17d5a37e664b0e9d","target":"record","created_at":"2026-07-05T08:35:26Z","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":"bfe3e1126f7d0a218f87b6bad67b10fbfc746b0c10f8dd5ef445adbc71404f5d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-22T01:36:11Z","title_canon_sha256":"f9852db2f8430da1c8763ad4d9af924f9a75e2d45901f47119e4e93b9ef02ce4"},"schema_version":"1.0","source":{"id":"2406.15704","kind":"arxiv","version":1}},"canonical_sha256":"5fe6ebdc7bb0859d45827cffa4b64d46b1e81cf5d1f62d5e9935490f61fed5c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fe6ebdc7bb0859d45827cffa4b64d46b1e81cf5d1f62d5e9935490f61fed5c3","first_computed_at":"2026-07-05T08:35:26.326395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:26.326395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7r4MWhTHry28HKN9iTTqZ3+57xBg0U+e8ens9a6r1bml8Dua1W8bYMoxL9oW4V2YzYQXA7a7K906fKtGIUTmAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:26.326906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15704","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec47019ae04f76182b0c3f1f381f76bb5e7436f1e68d6d7a17d5a37e664b0e9d","sha256:440ddb425ad8eaf205f1a4bb56805b0d3a8508517367e3a2b5dd46f77f4d4f7a"],"state_sha256":"a82a6b7a33cdc861f641db9d6b2c85938ace30a9384e8f04673cd3a9dd269118"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7YA9syOwNCKOR4YtXsR4dXzBqhw9sZDPJXnE/A5whShREgPH+PX3d6qG54DmynfENSvFIdGpJwCidVAI9GVjCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:29:58.577719Z","bundle_sha256":"f56c29aafe62de783c31cbf2e7ae5ed43242852f003a4c994bbfe6f150009f45"}}