{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EIPAM3NBAAEQSKWEH7V2GQ5C5F","short_pith_number":"pith:EIPAM3NB","schema_version":"1.0","canonical_sha256":"221e066da10009092ac43feba343a2e946e17487be3d6fe3493fe4e213788715","source":{"kind":"arxiv","id":"2506.05543","version":1},"attestation_state":"computed","paper":{"title":"FRAME: Pre-Training Video Feature Representations via Anticipation and Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Derek Hoiem, Jiahui Huang, Joon-Young Lee, Savya Khosla, Seoung Wug Oh, Sethuraman TV, Simon Jenni, Vignesh Srinivasakumar","submitted_at":"2025-06-05T19:44:47Z","abstract_excerpt":"Dense video prediction tasks, such as object tracking and semantic segmentation, require video encoders that generate temporally consistent, spatially dense features for every frame. However, existing approaches fall short: image encoders like DINO or CLIP lack temporal awareness, while video models such as VideoMAE underperform compared to image encoders on dense prediction tasks. We address this gap with FRAME, a self-supervised video frame encoder tailored for dense video understanding. FRAME learns to predict current and future DINO patch features from past and present RGB frames, leading "},"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":"2506.05543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T19:44:47Z","cross_cats_sorted":[],"title_canon_sha256":"9d8444bcc7dfb5e42da55e856cd3e2789a26b82dbadf79064b9e2585dc29a904","abstract_canon_sha256":"9f15cb45104473811870fbda2bd11c274ef2df5ebcc64994f31929ea17fec561"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:05.485847Z","signature_b64":"cW+hhRLwuastckMZH1YkTZ30OZVKKKQVIX/hrXDGlBP4VMgpy57ecppgFStJfROr0Yb0HDQWN1MvG3991PmfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"221e066da10009092ac43feba343a2e946e17487be3d6fe3493fe4e213788715","last_reissued_at":"2026-07-05T11:17:05.485348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:05.485348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FRAME: Pre-Training Video Feature Representations via Anticipation and Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Derek Hoiem, Jiahui Huang, Joon-Young Lee, Savya Khosla, Seoung Wug Oh, Sethuraman TV, Simon Jenni, Vignesh Srinivasakumar","submitted_at":"2025-06-05T19:44:47Z","abstract_excerpt":"Dense video prediction tasks, such as object tracking and semantic segmentation, require video encoders that generate temporally consistent, spatially dense features for every frame. However, existing approaches fall short: image encoders like DINO or CLIP lack temporal awareness, while video models such as VideoMAE underperform compared to image encoders on dense prediction tasks. We address this gap with FRAME, a self-supervised video frame encoder tailored for dense video understanding. FRAME learns to predict current and future DINO patch features from past and present RGB frames, leading "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05543","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/2506.05543/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":"2506.05543","created_at":"2026-07-05T11:17:05.485412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05543v1","created_at":"2026-07-05T11:17:05.485412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05543","created_at":"2026-07-05T11:17:05.485412+00:00"},{"alias_kind":"pith_short_12","alias_value":"EIPAM3NBAAEQ","created_at":"2026-07-05T11:17:05.485412+00:00"},{"alias_kind":"pith_short_16","alias_value":"EIPAM3NBAAEQSKWE","created_at":"2026-07-05T11:17:05.485412+00:00"},{"alias_kind":"pith_short_8","alias_value":"EIPAM3NB","created_at":"2026-07-05T11:17:05.485412+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/EIPAM3NBAAEQSKWEH7V2GQ5C5F","json":"https://pith.science/pith/EIPAM3NBAAEQSKWEH7V2GQ5C5F.json","graph_json":"https://pith.science/api/pith-number/EIPAM3NBAAEQSKWEH7V2GQ5C5F/graph.json","events_json":"https://pith.science/api/pith-number/EIPAM3NBAAEQSKWEH7V2GQ5C5F/events.json","paper":"https://pith.science/paper/EIPAM3NB"},"agent_actions":{"view_html":"https://pith.science/pith/EIPAM3NBAAEQSKWEH7V2GQ5C5F","download_json":"https://pith.science/pith/EIPAM3NBAAEQSKWEH7V2GQ5C5F.json","view_paper":"https://pith.science/paper/EIPAM3NB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05543&json=true","fetch_graph":"https://pith.science/api/pith-number/EIPAM3NBAAEQSKWEH7V2GQ5C5F/graph.json","fetch_events":"https://pith.science/api/pith-number/EIPAM3NBAAEQSKWEH7V2GQ5C5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EIPAM3NBAAEQSKWEH7V2GQ5C5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EIPAM3NBAAEQSKWEH7V2GQ5C5F/action/storage_attestation","attest_author":"https://pith.science/pith/EIPAM3NBAAEQSKWEH7V2GQ5C5F/action/author_attestation","sign_citation":"https://pith.science/pith/EIPAM3NBAAEQSKWEH7V2GQ5C5F/action/citation_signature","submit_replication":"https://pith.science/pith/EIPAM3NBAAEQSKWEH7V2GQ5C5F/action/replication_record"}},"created_at":"2026-07-05T11:17:05.485412+00:00","updated_at":"2026-07-05T11:17:05.485412+00:00"}