{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MOXSPI7IAQEUV6CW2MXHVNKKBO","short_pith_number":"pith:MOXSPI7I","schema_version":"1.0","canonical_sha256":"63af27a3e804094af856d32e7ab54a0b80fc0466ebf8f47127c0b448005a2297","source":{"kind":"arxiv","id":"2501.15513","version":2},"attestation_state":"computed","paper":{"title":"TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Huang, Wenjun Wu, Xingjian Zhang, Xi Weng, Yihao Yue, Zhaoxin Fan","submitted_at":"2025-01-26T13:10:12Z","abstract_excerpt":"Video behavior recognition and scene understanding are fundamental tasks in multimodal intelligence, serving as critical building blocks for numerous real-world applications. Through large multimodal models (LMMs) have achieved remarkable progress in video understanding, most existing open-source models rely on over 7B parameters and require large-scale datasets for training, making them resource-intensive and inaccessible to many researchers. Furthermore, lightweight models face persistent challenges in effectively processing long visual sequences and temporal understanding. In this work, we "},"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":"2501.15513","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T13:10:12Z","cross_cats_sorted":[],"title_canon_sha256":"c356b28d023934e05a09cc63d4cb86d3e875cebb86b1dd37e17a2f78192e38e7","abstract_canon_sha256":"cbda01cb2e06a56f3bd6c2edfeb9014bf7483facab53c986c6107306699200ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:02.939700Z","signature_b64":"i67u2XNLkkd9t6xDM0CsBjuinE7sB60U5mjX3Sg+8+zHD3ZB4/IokJ6uLa526DIsMxOK8EJNXLJh+j+1v35NAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63af27a3e804094af856d32e7ab54a0b80fc0466ebf8f47127c0b448005a2297","last_reissued_at":"2026-07-05T11:19:02.939244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:02.939244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TinyLLaVA-Video: Towards Smaller LMMs for Video Understanding with Group Resampler","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Huang, Wenjun Wu, Xingjian Zhang, Xi Weng, Yihao Yue, Zhaoxin Fan","submitted_at":"2025-01-26T13:10:12Z","abstract_excerpt":"Video behavior recognition and scene understanding are fundamental tasks in multimodal intelligence, serving as critical building blocks for numerous real-world applications. Through large multimodal models (LMMs) have achieved remarkable progress in video understanding, most existing open-source models rely on over 7B parameters and require large-scale datasets for training, making them resource-intensive and inaccessible to many researchers. Furthermore, lightweight models face persistent challenges in effectively processing long visual sequences and temporal understanding. In this work, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15513","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/2501.15513/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":"2501.15513","created_at":"2026-07-05T11:19:02.939298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15513v2","created_at":"2026-07-05T11:19:02.939298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15513","created_at":"2026-07-05T11:19:02.939298+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOXSPI7IAQEU","created_at":"2026-07-05T11:19:02.939298+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOXSPI7IAQEUV6CW","created_at":"2026-07-05T11:19:02.939298+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOXSPI7I","created_at":"2026-07-05T11:19:02.939298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO","json":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO.json","graph_json":"https://pith.science/api/pith-number/MOXSPI7IAQEUV6CW2MXHVNKKBO/graph.json","events_json":"https://pith.science/api/pith-number/MOXSPI7IAQEUV6CW2MXHVNKKBO/events.json","paper":"https://pith.science/paper/MOXSPI7I"},"agent_actions":{"view_html":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO","download_json":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO.json","view_paper":"https://pith.science/paper/MOXSPI7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15513&json=true","fetch_graph":"https://pith.science/api/pith-number/MOXSPI7IAQEUV6CW2MXHVNKKBO/graph.json","fetch_events":"https://pith.science/api/pith-number/MOXSPI7IAQEUV6CW2MXHVNKKBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO/action/storage_attestation","attest_author":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO/action/author_attestation","sign_citation":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO/action/citation_signature","submit_replication":"https://pith.science/pith/MOXSPI7IAQEUV6CW2MXHVNKKBO/action/replication_record"}},"created_at":"2026-07-05T11:19:02.939298+00:00","updated_at":"2026-07-05T11:19:02.939298+00:00"}