{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I4JU4N3GRXC42772PP53KSM7UK","short_pith_number":"pith:I4JU4N3G","schema_version":"1.0","canonical_sha256":"47134e37668dc5cd7ffa7bfbb5499fa2980cb70950bcd96a56b7b29a161c5c0f","source":{"kind":"arxiv","id":"2407.01851","version":2},"attestation_state":"computed","paper":{"title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.CV","authors_text":"Dinesh Manocha, Jun Chen, Mohamed Elhoseiny, Ruohan Gao, Sanjoy Chowdhury, Sayan Nag, Subhrajyoti Dasgupta","submitted_at":"2024-07-01T23:32:25Z","abstract_excerpt":"Leveraging Large Language Models' remarkable proficiency in text-based tasks, recent works on Multi-modal LLMs (MLLMs) extend them to other modalities like vision and audio. However, the progress in these directions has been mostly focused on tasks that only require a coarse-grained understanding of the audio-visual semantics. We present Meerkat, an audio-visual LLM equipped with a fine-grained understanding of image and audio both spatially and temporally. With a new modality alignment module based on optimal transport and a cross-attention module that enforces audio-visual consistency, Meerk"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.01851","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T23:32:25Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"6860ae0dbc38c92c1422fb7aded5a6e14e0b9f74dd89bd35fccebff439821276","abstract_canon_sha256":"385f8b252546f4ce06f3922b1cd46ae02fdde582b481e44c78558c9ab456b422"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:36.859313Z","signature_b64":"UOQm7dWXWulgwAiBgkKN4QZAm2lhso7DXikCPADMCxxuA5FWzPySvk+RO1P3RQhUFUQcNg/FIDtsmwpkbxO3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47134e37668dc5cd7ffa7bfbb5499fa2980cb70950bcd96a56b7b29a161c5c0f","last_reissued_at":"2026-07-05T08:39:36.858897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:36.858897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.CV","authors_text":"Dinesh Manocha, Jun Chen, Mohamed Elhoseiny, Ruohan Gao, Sanjoy Chowdhury, Sayan Nag, Subhrajyoti Dasgupta","submitted_at":"2024-07-01T23:32:25Z","abstract_excerpt":"Leveraging Large Language Models' remarkable proficiency in text-based tasks, recent works on Multi-modal LLMs (MLLMs) extend them to other modalities like vision and audio. However, the progress in these directions has been mostly focused on tasks that only require a coarse-grained understanding of the audio-visual semantics. We present Meerkat, an audio-visual LLM equipped with a fine-grained understanding of image and audio both spatially and temporally. With a new modality alignment module based on optimal transport and a cross-attention module that enforces audio-visual consistency, Meerk"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01851","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/2407.01851/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.01851","created_at":"2026-07-05T08:39:36.858953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01851v2","created_at":"2026-07-05T08:39:36.858953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01851","created_at":"2026-07-05T08:39:36.858953+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4JU4N3GRXC4","created_at":"2026-07-05T08:39:36.858953+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4JU4N3GRXC42772","created_at":"2026-07-05T08:39:36.858953+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4JU4N3G","created_at":"2026-07-05T08:39:36.858953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15190","citing_title":"EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I4JU4N3GRXC42772PP53KSM7UK","json":"https://pith.science/pith/I4JU4N3GRXC42772PP53KSM7UK.json","graph_json":"https://pith.science/api/pith-number/I4JU4N3GRXC42772PP53KSM7UK/graph.json","events_json":"https://pith.science/api/pith-number/I4JU4N3GRXC42772PP53KSM7UK/events.json","paper":"https://pith.science/paper/I4JU4N3G"},"agent_actions":{"view_html":"https://pith.science/pith/I4JU4N3GRXC42772PP53KSM7UK","download_json":"https://pith.science/pith/I4JU4N3GRXC42772PP53KSM7UK.json","view_paper":"https://pith.science/paper/I4JU4N3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01851&json=true","fetch_graph":"https://pith.science/api/pith-number/I4JU4N3GRXC42772PP53KSM7UK/graph.json","fetch_events":"https://pith.science/api/pith-number/I4JU4N3GRXC42772PP53KSM7UK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4JU4N3GRXC42772PP53KSM7UK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4JU4N3GRXC42772PP53KSM7UK/action/storage_attestation","attest_author":"https://pith.science/pith/I4JU4N3GRXC42772PP53KSM7UK/action/author_attestation","sign_citation":"https://pith.science/pith/I4JU4N3GRXC42772PP53KSM7UK/action/citation_signature","submit_replication":"https://pith.science/pith/I4JU4N3GRXC42772PP53KSM7UK/action/replication_record"}},"created_at":"2026-07-05T08:39:36.858953+00:00","updated_at":"2026-07-05T08:39:36.858953+00:00"}