{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ALQMR2ITEDJYMDDSEQ5QNKGRFY","short_pith_number":"pith:ALQMR2IT","canonical_record":{"source":{"id":"2405.03770","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-06T18:09:48Z","cross_cats_sorted":[],"title_canon_sha256":"bcf37a1f8656830b8ee64ede4952d3c910e5b61c131496342f4eb2c298b02a4e","abstract_canon_sha256":"9d1b0e61953b31b68e49bca9b630511f92a946cbd80eb4253f2c86189c479a4d"},"schema_version":"1.0"},"canonical_sha256":"02e0c8e91320d3860c72243b06a8d12e238b7bdf208ad4d1fe122e626df72bea","source":{"kind":"arxiv","id":"2405.03770","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03770","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03770v1","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03770","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"pith_short_12","alias_value":"ALQMR2ITEDJY","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"pith_short_16","alias_value":"ALQMR2ITEDJYMDDS","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"pith_short_8","alias_value":"ALQMR2IT","created_at":"2026-07-05T08:16:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ALQMR2ITEDJYMDDSEQ5QNKGRFY","target":"record","payload":{"canonical_record":{"source":{"id":"2405.03770","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-06T18:09:48Z","cross_cats_sorted":[],"title_canon_sha256":"bcf37a1f8656830b8ee64ede4952d3c910e5b61c131496342f4eb2c298b02a4e","abstract_canon_sha256":"9d1b0e61953b31b68e49bca9b630511f92a946cbd80eb4253f2c86189c479a4d"},"schema_version":"1.0"},"canonical_sha256":"02e0c8e91320d3860c72243b06a8d12e238b7bdf208ad4d1fe122e626df72bea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:10.590866Z","signature_b64":"CsSh6azTirdM6l6NUJDM4xX7hxGWTUu7E1OHVLbiQIzeaOA++P4SYC8ABT9RtXJOXbjpsw7ohFZyTbIFH/5TBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02e0c8e91320d3860c72243b06a8d12e238b7bdf208ad4d1fe122e626df72bea","last_reissued_at":"2026-07-05T08:16:10.590392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:10.590392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.03770","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:16:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i25IEfAAjMiSuZdgHd2ZVd1r77TvBzGN1dmTakm629PjBKs3ruQbNIVLiyWUoo49mUJi2sjHOnZ3TWMLpby4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:05:43.809006Z"},"content_sha256":"c261608c20f2c8ceb3b03fa047be19a01da91e4f9f6c2d55b42306326b07dadc","schema_version":"1.0","event_id":"sha256:c261608c20f2c8ceb3b03fa047be19a01da91e4f9f6c2d55b42306326b07dadc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ALQMR2ITEDJYMDDSEQ5QNKGRFY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Foundation Models for Video Understanding: A Survey","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Moegelmose, Neelu Madan, Rajat Modi, Thomas B. Moeslund, Yogesh S. Rawat","submitted_at":"2024-05-06T18:09:48Z","abstract_excerpt":"Video Foundation Models (ViFMs) aim to learn a general-purpose representation for various video understanding tasks. Leveraging large-scale datasets and powerful models, ViFMs achieve this by capturing robust and generic features from video data. This survey analyzes over 200 video foundational models, offering a comprehensive overview of benchmarks and evaluation metrics across 14 distinct video tasks categorized into 3 main categories. Additionally, we offer an in-depth performance analysis of these models for the 6 most common video tasks. We categorize ViFMs into three categories: 1) Image"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03770","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/2405.03770/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:16:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mByInjShGXGB3Ctg/eQ++XuA7Muk8DcW4ny+WOZtApTCFWYz840DPMj3pjE2SkC0Cv6Q22d9Z3SZWXQFS03wCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:05:43.809389Z"},"content_sha256":"be72850c7afb09abcce9d9c763bee5ee176f9dca5271653234b00e39061a016e","schema_version":"1.0","event_id":"sha256:be72850c7afb09abcce9d9c763bee5ee176f9dca5271653234b00e39061a016e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ALQMR2ITEDJYMDDSEQ5QNKGRFY/bundle.json","state_url":"https://pith.science/pith/ALQMR2ITEDJYMDDSEQ5QNKGRFY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ALQMR2ITEDJYMDDSEQ5QNKGRFY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T10:05:43Z","links":{"resolver":"https://pith.science/pith/ALQMR2ITEDJYMDDSEQ5QNKGRFY","bundle":"https://pith.science/pith/ALQMR2ITEDJYMDDSEQ5QNKGRFY/bundle.json","state":"https://pith.science/pith/ALQMR2ITEDJYMDDSEQ5QNKGRFY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ALQMR2ITEDJYMDDSEQ5QNKGRFY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ALQMR2ITEDJYMDDSEQ5QNKGRFY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9d1b0e61953b31b68e49bca9b630511f92a946cbd80eb4253f2c86189c479a4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-06T18:09:48Z","title_canon_sha256":"bcf37a1f8656830b8ee64ede4952d3c910e5b61c131496342f4eb2c298b02a4e"},"schema_version":"1.0","source":{"id":"2405.03770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03770","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03770v1","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03770","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"pith_short_12","alias_value":"ALQMR2ITEDJY","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"pith_short_16","alias_value":"ALQMR2ITEDJYMDDS","created_at":"2026-07-05T08:16:10Z"},{"alias_kind":"pith_short_8","alias_value":"ALQMR2IT","created_at":"2026-07-05T08:16:10Z"}],"graph_snapshots":[{"event_id":"sha256:be72850c7afb09abcce9d9c763bee5ee176f9dca5271653234b00e39061a016e","target":"graph","created_at":"2026-07-05T08:16:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.03770/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Foundation Models (ViFMs) aim to learn a general-purpose representation for various video understanding tasks. Leveraging large-scale datasets and powerful models, ViFMs achieve this by capturing robust and generic features from video data. This survey analyzes over 200 video foundational models, offering a comprehensive overview of benchmarks and evaluation metrics across 14 distinct video tasks categorized into 3 main categories. Additionally, we offer an in-depth performance analysis of these models for the 6 most common video tasks. We categorize ViFMs into three categories: 1) Image","authors_text":"Andreas Moegelmose, Neelu Madan, Rajat Modi, Thomas B. Moeslund, Yogesh S. Rawat","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-06T18:09:48Z","title":"Foundation Models for Video Understanding: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03770","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c261608c20f2c8ceb3b03fa047be19a01da91e4f9f6c2d55b42306326b07dadc","target":"record","created_at":"2026-07-05T08:16:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9d1b0e61953b31b68e49bca9b630511f92a946cbd80eb4253f2c86189c479a4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-06T18:09:48Z","title_canon_sha256":"bcf37a1f8656830b8ee64ede4952d3c910e5b61c131496342f4eb2c298b02a4e"},"schema_version":"1.0","source":{"id":"2405.03770","kind":"arxiv","version":1}},"canonical_sha256":"02e0c8e91320d3860c72243b06a8d12e238b7bdf208ad4d1fe122e626df72bea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02e0c8e91320d3860c72243b06a8d12e238b7bdf208ad4d1fe122e626df72bea","first_computed_at":"2026-07-05T08:16:10.590392Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:10.590392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CsSh6azTirdM6l6NUJDM4xX7hxGWTUu7E1OHVLbiQIzeaOA++P4SYC8ABT9RtXJOXbjpsw7ohFZyTbIFH/5TBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:10.590866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.03770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c261608c20f2c8ceb3b03fa047be19a01da91e4f9f6c2d55b42306326b07dadc","sha256:be72850c7afb09abcce9d9c763bee5ee176f9dca5271653234b00e39061a016e"],"state_sha256":"df1dd94e35fc34849ff6e0ca6d532b00b5120933f7bfbf6e27e6a24c21bcbb72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RNtQJhvpZrwnYOifGmBfpwSyQTbUYGCEh7epbJzIxldiHbsj9e6f2YZiscMBtliQKI5LcRrFnq6vSHCN/mVwAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:05:43.811420Z","bundle_sha256":"174767d16d8c82fb0ae20ba6226792914dab7120df869237b9bb4d9d21130cbc"}}