{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7EKO4LB5CJLNCCAYOQCOLYHC34","short_pith_number":"pith:7EKO4LB5","canonical_record":{"source":{"id":"2410.06682","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T08:44:47Z","cross_cats_sorted":["cs.CL","eess.IV"],"title_canon_sha256":"47ed19da2bbaadb3c9ef428c7c9da294bf56777f9076ed29cdafc62c96c137f0","abstract_canon_sha256":"0f8c3cd009af8592b5cbf4933f0cd9c0e2cafd36d89cb60fe304f9d4d927e2b5"},"schema_version":"1.0"},"canonical_sha256":"f914ee2c3d1256d108187404e5e0e2df17d6904e5ded243b867db807dbae61c6","source":{"kind":"arxiv","id":"2410.06682","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06682","created_at":"2026-07-05T09:18:54Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06682v2","created_at":"2026-07-05T09:18:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06682","created_at":"2026-07-05T09:18:54Z"},{"alias_kind":"pith_short_12","alias_value":"7EKO4LB5CJLN","created_at":"2026-07-05T09:18:54Z"},{"alias_kind":"pith_short_16","alias_value":"7EKO4LB5CJLNCCAY","created_at":"2026-07-05T09:18:54Z"},{"alias_kind":"pith_short_8","alias_value":"7EKO4LB5","created_at":"2026-07-05T09:18:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7EKO4LB5CJLNCCAYOQCOLYHC34","target":"record","payload":{"canonical_record":{"source":{"id":"2410.06682","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T08:44:47Z","cross_cats_sorted":["cs.CL","eess.IV"],"title_canon_sha256":"47ed19da2bbaadb3c9ef428c7c9da294bf56777f9076ed29cdafc62c96c137f0","abstract_canon_sha256":"0f8c3cd009af8592b5cbf4933f0cd9c0e2cafd36d89cb60fe304f9d4d927e2b5"},"schema_version":"1.0"},"canonical_sha256":"f914ee2c3d1256d108187404e5e0e2df17d6904e5ded243b867db807dbae61c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:54.153980Z","signature_b64":"DjS0XNZ/XDfT/TBS36CPzdDqZAZQb8U0+pfMkQ9rsh1z00ytuAhBM0MBDrf8vBqlg4pbkwm60JR2g/SG1AccBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f914ee2c3d1256d108187404e5e0e2df17d6904e5ded243b867db807dbae61c6","last_reissued_at":"2026-07-05T09:18:54.153535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:54.153535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.06682","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":"2026-07-05T09:18:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aSMqIBRGDhmYI2h+zUXAZWmWbFm7asYgBi1hl7QyOYAjJ4xz25BzKMYzORkUoqYMfiGyKKwXQ1lFpkYXu4KEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:09:43.739404Z"},"content_sha256":"c8b46cc7161636287439bccdfbe2fadbfb86b28688c3c81b2778ce51c0159579","schema_version":"1.0","event_id":"sha256:c8b46cc7161636287439bccdfbe2fadbfb86b28688c3c81b2778ce51c0159579"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7EKO4LB5CJLNCCAYOQCOLYHC34","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.IV"],"primary_cat":"cs.CV","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Jimin Zhuang, Wei Li, Yixuan Li, Yudong Yang, Zujun Ma","submitted_at":"2024-10-09T08:44:47Z","abstract_excerpt":"Videos contain a wealth of information, and generating detailed and accurate descriptions in natural language is a key aspect of video understanding. In this paper, we present video-SALMONN 2, an advanced audio-visual large language model (LLM) with low-rank adaptation (LoRA) designed for enhanced video (with paired audio) captioning through directed preference optimization (DPO). We propose new metrics to evaluate the completeness and accuracy of video descriptions, which are optimized using DPO. To further improve training, we introduce a novel multi-round DPO (mrDPO) approach, which involve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06682","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/2410.06682/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":"2026-07-05T09:18:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5svcXSSWhUgSjiZgr+NPZIH4rfVGTlAtD0QDKxQ53jZmI3XZuaPWf/w3X1hHEnvK+qggBZ7wyH8phAFBW5ceBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:09:43.739922Z"},"content_sha256":"9c65f7a13460693499b4b91a76d94b3d5ddf621f0aab6046f76ebc46ff2656bf","schema_version":"1.0","event_id":"sha256:9c65f7a13460693499b4b91a76d94b3d5ddf621f0aab6046f76ebc46ff2656bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7EKO4LB5CJLNCCAYOQCOLYHC34/bundle.json","state_url":"https://pith.science/pith/7EKO4LB5CJLNCCAYOQCOLYHC34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7EKO4LB5CJLNCCAYOQCOLYHC34/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":"2026-08-03T18:09:43Z","links":{"resolver":"https://pith.science/pith/7EKO4LB5CJLNCCAYOQCOLYHC34","bundle":"https://pith.science/pith/7EKO4LB5CJLNCCAYOQCOLYHC34/bundle.json","state":"https://pith.science/pith/7EKO4LB5CJLNCCAYOQCOLYHC34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7EKO4LB5CJLNCCAYOQCOLYHC34/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7EKO4LB5CJLNCCAYOQCOLYHC34","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":"0f8c3cd009af8592b5cbf4933f0cd9c0e2cafd36d89cb60fe304f9d4d927e2b5","cross_cats_sorted":["cs.CL","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T08:44:47Z","title_canon_sha256":"47ed19da2bbaadb3c9ef428c7c9da294bf56777f9076ed29cdafc62c96c137f0"},"schema_version":"1.0","source":{"id":"2410.06682","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06682","created_at":"2026-07-05T09:18:54Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06682v2","created_at":"2026-07-05T09:18:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06682","created_at":"2026-07-05T09:18:54Z"},{"alias_kind":"pith_short_12","alias_value":"7EKO4LB5CJLN","created_at":"2026-07-05T09:18:54Z"},{"alias_kind":"pith_short_16","alias_value":"7EKO4LB5CJLNCCAY","created_at":"2026-07-05T09:18:54Z"},{"alias_kind":"pith_short_8","alias_value":"7EKO4LB5","created_at":"2026-07-05T09:18:54Z"}],"graph_snapshots":[{"event_id":"sha256:9c65f7a13460693499b4b91a76d94b3d5ddf621f0aab6046f76ebc46ff2656bf","target":"graph","created_at":"2026-07-05T09:18:54Z","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/2410.06682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Videos contain a wealth of information, and generating detailed and accurate descriptions in natural language is a key aspect of video understanding. In this paper, we present video-SALMONN 2, an advanced audio-visual large language model (LLM) with low-rank adaptation (LoRA) designed for enhanced video (with paired audio) captioning through directed preference optimization (DPO). We propose new metrics to evaluate the completeness and accuracy of video descriptions, which are optimized using DPO. To further improve training, we introduce a novel multi-round DPO (mrDPO) approach, which involve","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Jimin Zhuang, Wei Li, Yixuan Li, Yudong Yang, Zujun Ma","cross_cats":["cs.CL","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T08:44:47Z","title":"Enhancing Multimodal LLM for Detailed and Accurate Video Captioning using Multi-Round Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06682","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:c8b46cc7161636287439bccdfbe2fadbfb86b28688c3c81b2778ce51c0159579","target":"record","created_at":"2026-07-05T09:18:54Z","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":"0f8c3cd009af8592b5cbf4933f0cd9c0e2cafd36d89cb60fe304f9d4d927e2b5","cross_cats_sorted":["cs.CL","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T08:44:47Z","title_canon_sha256":"47ed19da2bbaadb3c9ef428c7c9da294bf56777f9076ed29cdafc62c96c137f0"},"schema_version":"1.0","source":{"id":"2410.06682","kind":"arxiv","version":2}},"canonical_sha256":"f914ee2c3d1256d108187404e5e0e2df17d6904e5ded243b867db807dbae61c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f914ee2c3d1256d108187404e5e0e2df17d6904e5ded243b867db807dbae61c6","first_computed_at":"2026-07-05T09:18:54.153535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:54.153535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DjS0XNZ/XDfT/TBS36CPzdDqZAZQb8U0+pfMkQ9rsh1z00ytuAhBM0MBDrf8vBqlg4pbkwm60JR2g/SG1AccBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:54.153980Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06682","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8b46cc7161636287439bccdfbe2fadbfb86b28688c3c81b2778ce51c0159579","sha256:9c65f7a13460693499b4b91a76d94b3d5ddf621f0aab6046f76ebc46ff2656bf"],"state_sha256":"780f0de62b1ec9f00f1d746189e492761a285811e5594981bdc417cf50eb51ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uafbiaIcwwjL2/e1QYOGAyVsRBDmeMlq7Njt+7VksCzv3tQswh/MzT7LkojSOSOCh3cprbRJ8I/L3VgVAutzDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:09:43.743830Z","bundle_sha256":"8a5d9f65bb32cc9d3b9d1e85e5d5e8ee6a9c0ded8ca360a00c2eff2eab27c109"}}