{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VHSCLA65VAD7SBDI5JRR22RDOG","short_pith_number":"pith:VHSCLA65","schema_version":"1.0","canonical_sha256":"a9e42583dda807f90468ea631d6a23718946bc6189f84d83805e01ab90cb7f12","source":{"kind":"arxiv","id":"2406.08024","version":1},"attestation_state":"computed","paper":{"title":"Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lin Ma, Shaoxiang Chen, Shimin Chen, Yitian Yuan, Zequn Jie","submitted_at":"2024-06-12T09:22:45Z","abstract_excerpt":"Amidst the advancements in image-based Large Vision-Language Models (image-LVLM), the transition to video-based models (video-LVLM) is hindered by the limited availability of quality video data. This paper addresses the challenge by leveraging the visual commonalities between images and videos to efficiently evolve image-LVLMs into video-LVLMs. We present a cost-effective video-LVLM that enhances model architecture, introduces innovative training strategies, and identifies the most effective types of video instruction data. Our innovative weighted token sampler significantly compresses the vis"},"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":"2406.08024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T09:22:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fafc7d2ae5c6f63c0bea1649a05a2b863d2f00fa04b6d47b1f6ec988be15e5c4","abstract_canon_sha256":"0ae9f25bf4bd788ad8c84e0e70d78915547bc7c32ef386702d5f497ad4893cc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:53.261836Z","signature_b64":"ifoQG8qt9TpfuEnFSpuBYeJqdrTTw4SI4sA9NFhGvuY0E/HUsiKkXkS8vpTnjvLj/uh+wUe3U6GA7ybplu/HCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9e42583dda807f90468ea631d6a23718946bc6189f84d83805e01ab90cb7f12","last_reissued_at":"2026-07-05T08:30:53.261331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:53.261331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lin Ma, Shaoxiang Chen, Shimin Chen, Yitian Yuan, Zequn Jie","submitted_at":"2024-06-12T09:22:45Z","abstract_excerpt":"Amidst the advancements in image-based Large Vision-Language Models (image-LVLM), the transition to video-based models (video-LVLM) is hindered by the limited availability of quality video data. This paper addresses the challenge by leveraging the visual commonalities between images and videos to efficiently evolve image-LVLMs into video-LVLMs. We present a cost-effective video-LVLM that enhances model architecture, introduces innovative training strategies, and identifies the most effective types of video instruction data. Our innovative weighted token sampler significantly compresses the vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08024","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/2406.08024/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":"2406.08024","created_at":"2026-07-05T08:30:53.261394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08024v1","created_at":"2026-07-05T08:30:53.261394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08024","created_at":"2026-07-05T08:30:53.261394+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHSCLA65VAD7","created_at":"2026-07-05T08:30:53.261394+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHSCLA65VAD7SBDI","created_at":"2026-07-05T08:30:53.261394+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHSCLA65","created_at":"2026-07-05T08:30:53.261394+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/VHSCLA65VAD7SBDI5JRR22RDOG","json":"https://pith.science/pith/VHSCLA65VAD7SBDI5JRR22RDOG.json","graph_json":"https://pith.science/api/pith-number/VHSCLA65VAD7SBDI5JRR22RDOG/graph.json","events_json":"https://pith.science/api/pith-number/VHSCLA65VAD7SBDI5JRR22RDOG/events.json","paper":"https://pith.science/paper/VHSCLA65"},"agent_actions":{"view_html":"https://pith.science/pith/VHSCLA65VAD7SBDI5JRR22RDOG","download_json":"https://pith.science/pith/VHSCLA65VAD7SBDI5JRR22RDOG.json","view_paper":"https://pith.science/paper/VHSCLA65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08024&json=true","fetch_graph":"https://pith.science/api/pith-number/VHSCLA65VAD7SBDI5JRR22RDOG/graph.json","fetch_events":"https://pith.science/api/pith-number/VHSCLA65VAD7SBDI5JRR22RDOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHSCLA65VAD7SBDI5JRR22RDOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHSCLA65VAD7SBDI5JRR22RDOG/action/storage_attestation","attest_author":"https://pith.science/pith/VHSCLA65VAD7SBDI5JRR22RDOG/action/author_attestation","sign_citation":"https://pith.science/pith/VHSCLA65VAD7SBDI5JRR22RDOG/action/citation_signature","submit_replication":"https://pith.science/pith/VHSCLA65VAD7SBDI5JRR22RDOG/action/replication_record"}},"created_at":"2026-07-05T08:30:53.261394+00:00","updated_at":"2026-07-05T08:30:53.261394+00:00"}