{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BFS466APOIUH3TTW2LKLE2ABZU","short_pith_number":"pith:BFS466AP","schema_version":"1.0","canonical_sha256":"0965cf780f72287dce76d2d4b26801cd36ea72acb83cf87a7f3d8d34d020b224","source":{"kind":"arxiv","id":"2605.19137","version":1},"attestation_state":"computed","paper":{"title":"Towards Data-Efficient Video Pre-training with Frozen Image Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gijs Dubbelman, Niccol\\`o Cavagnero, Svetlana Orlova","submitted_at":"2026-05-18T21:35:09Z","abstract_excerpt":"Video foundation models achieve strong performance across many video understanding tasks, but typically require large-scale pre-training on massive video datasets, resulting in substantial data and compute costs. In contrast, modern image foundation models already provide powerful spatial representations. This raises an important question: can competitive video models be built by reusing these spatial representations and pre-training only for temporal reasoning? We take initial steps toward exploring a lightweight training paradigm that freezes a pre-trained image foundation model and trains o"},"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":"2605.19137","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T21:35:09Z","cross_cats_sorted":[],"title_canon_sha256":"1065902edb5fd0ca843378e8bc634917e38322d4795a04a97aa226a8acae6314","abstract_canon_sha256":"8e3e73238e486377fdd0e28fc36b92726482bf7c9b85b73d0cac8d4c3ad4479f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:29.060368Z","signature_b64":"QPH2x1xMqe3kr1uI3yzKafxgDUqBLa1qPrPP52CcWnbIhfe5mVWU1tlOxFzBQPddNXPzXetHLYpw2OZcHFz2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0965cf780f72287dce76d2d4b26801cd36ea72acb83cf87a7f3d8d34d020b224","last_reissued_at":"2026-05-20T01:05:29.059625Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:29.059625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Data-Efficient Video Pre-training with Frozen Image Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gijs Dubbelman, Niccol\\`o Cavagnero, Svetlana Orlova","submitted_at":"2026-05-18T21:35:09Z","abstract_excerpt":"Video foundation models achieve strong performance across many video understanding tasks, but typically require large-scale pre-training on massive video datasets, resulting in substantial data and compute costs. In contrast, modern image foundation models already provide powerful spatial representations. This raises an important question: can competitive video models be built by reusing these spatial representations and pre-training only for temporal reasoning? We take initial steps toward exploring a lightweight training paradigm that freezes a pre-trained image foundation model and trains o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19137","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/2605.19137/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":"2605.19137","created_at":"2026-05-20T01:05:29.059774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19137v1","created_at":"2026-05-20T01:05:29.059774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19137","created_at":"2026-05-20T01:05:29.059774+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFS466APOIUH","created_at":"2026-05-20T01:05:29.059774+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFS466APOIUH3TTW","created_at":"2026-05-20T01:05:29.059774+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFS466AP","created_at":"2026-05-20T01:05:29.059774+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/BFS466APOIUH3TTW2LKLE2ABZU","json":"https://pith.science/pith/BFS466APOIUH3TTW2LKLE2ABZU.json","graph_json":"https://pith.science/api/pith-number/BFS466APOIUH3TTW2LKLE2ABZU/graph.json","events_json":"https://pith.science/api/pith-number/BFS466APOIUH3TTW2LKLE2ABZU/events.json","paper":"https://pith.science/paper/BFS466AP"},"agent_actions":{"view_html":"https://pith.science/pith/BFS466APOIUH3TTW2LKLE2ABZU","download_json":"https://pith.science/pith/BFS466APOIUH3TTW2LKLE2ABZU.json","view_paper":"https://pith.science/paper/BFS466AP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19137&json=true","fetch_graph":"https://pith.science/api/pith-number/BFS466APOIUH3TTW2LKLE2ABZU/graph.json","fetch_events":"https://pith.science/api/pith-number/BFS466APOIUH3TTW2LKLE2ABZU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFS466APOIUH3TTW2LKLE2ABZU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFS466APOIUH3TTW2LKLE2ABZU/action/storage_attestation","attest_author":"https://pith.science/pith/BFS466APOIUH3TTW2LKLE2ABZU/action/author_attestation","sign_citation":"https://pith.science/pith/BFS466APOIUH3TTW2LKLE2ABZU/action/citation_signature","submit_replication":"https://pith.science/pith/BFS466APOIUH3TTW2LKLE2ABZU/action/replication_record"}},"created_at":"2026-05-20T01:05:29.059774+00:00","updated_at":"2026-05-20T01:05:29.059774+00:00"}