{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2NZMNZKZHSOEEP6A2WD7YGVFCR","short_pith_number":"pith:2NZMNZKZ","canonical_record":{"source":{"id":"2204.01692","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-04T17:58:02Z","cross_cats_sorted":[],"title_canon_sha256":"a1426fabe8def96f45abc63983d43e14036c3cee5c361beefa6fb7eab97f99da","abstract_canon_sha256":"4da5e9d83c08e18f2d304cb64072b7b62a4827e97cce48247404379e07a93e84"},"schema_version":"1.0"},"canonical_sha256":"d372c6e5593c9c423fc0d587fc1aa51465d042483362c61f08f66c510b694c27","source":{"kind":"arxiv","id":"2204.01692","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.01692","created_at":"2026-07-05T05:30:28Z"},{"alias_kind":"arxiv_version","alias_value":"2204.01692v3","created_at":"2026-07-05T05:30:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.01692","created_at":"2026-07-05T05:30:28Z"},{"alias_kind":"pith_short_12","alias_value":"2NZMNZKZHSOE","created_at":"2026-07-05T05:30:28Z"},{"alias_kind":"pith_short_16","alias_value":"2NZMNZKZHSOEEP6A","created_at":"2026-07-05T05:30:28Z"},{"alias_kind":"pith_short_8","alias_value":"2NZMNZKZ","created_at":"2026-07-05T05:30:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2NZMNZKZHSOEEP6A2WD7YGVFCR","target":"record","payload":{"canonical_record":{"source":{"id":"2204.01692","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-04T17:58:02Z","cross_cats_sorted":[],"title_canon_sha256":"a1426fabe8def96f45abc63983d43e14036c3cee5c361beefa6fb7eab97f99da","abstract_canon_sha256":"4da5e9d83c08e18f2d304cb64072b7b62a4827e97cce48247404379e07a93e84"},"schema_version":"1.0"},"canonical_sha256":"d372c6e5593c9c423fc0d587fc1aa51465d042483362c61f08f66c510b694c27","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:28.891216Z","signature_b64":"eUQfsgX0PNlN2xVMo0BEqXdApXVBtMhb41iKxBnt7O5gIhz5y7yOdU62CFCRTuZflQzQ5+p1hjRzemaaQ4S4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d372c6e5593c9c423fc0d587fc1aa51465d042483362c61f08f66c510b694c27","last_reissued_at":"2026-07-05T05:30:28.890853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:28.890853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.01692","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:30:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4GvLYYmTXopY+UClizGNdNI5l+nJ6wdhSM/qjV0xZj9ccMFkljL2Mz77kz0vsXn+Gem6WHHQqPstNfCZXfg0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:28:43.876046Z"},"content_sha256":"6b61ef269d68405d4a06248119f2869ec3b0a41f21ede124cdd8c7112a5a7274","schema_version":"1.0","event_id":"sha256:6b61ef269d68405d4a06248119f2869ec3b0a41f21ede124cdd8c7112a5a7274"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2NZMNZKZHSOEEP6A2WD7YGVFCR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Long Movie Clip Classification with State-Space Video Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gedas Bertasius, Md Mohaiminul Islam","submitted_at":"2022-04-04T17:58:02Z","abstract_excerpt":"Most modern video recognition models are designed to operate on short video clips (e.g., 5-10s in length). Thus, it is challenging to apply such models to long movie understanding tasks, which typically require sophisticated long-range temporal reasoning. The recently introduced video transformers partially address this issue by using long-range temporal self-attention. However, due to the quadratic cost of self-attention, such models are often costly and impractical to use. Instead, we propose ViS4mer, an efficient long-range video model that combines the strengths of self-attention and the r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.01692","kind":"arxiv","version":3},"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/2204.01692/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":"2026-07-05T05:30:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hzluGoCs7q6IP+51UReqcI6eYXkKK36fB+ITzE0dWMBEDMYo2jW7089RXBSfrOeCN1iVoEqau7YylsLCOvlrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:28:43.876548Z"},"content_sha256":"de4662d22b309e5bcc9ae8ba20c9ba161dc3de39e822e4ad494cd88c3e6ff586","schema_version":"1.0","event_id":"sha256:de4662d22b309e5bcc9ae8ba20c9ba161dc3de39e822e4ad494cd88c3e6ff586"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2NZMNZKZHSOEEP6A2WD7YGVFCR/bundle.json","state_url":"https://pith.science/pith/2NZMNZKZHSOEEP6A2WD7YGVFCR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2NZMNZKZHSOEEP6A2WD7YGVFCR/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":"2026-08-15T11:28:43Z","links":{"resolver":"https://pith.science/pith/2NZMNZKZHSOEEP6A2WD7YGVFCR","bundle":"https://pith.science/pith/2NZMNZKZHSOEEP6A2WD7YGVFCR/bundle.json","state":"https://pith.science/pith/2NZMNZKZHSOEEP6A2WD7YGVFCR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2NZMNZKZHSOEEP6A2WD7YGVFCR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2NZMNZKZHSOEEP6A2WD7YGVFCR","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":"4da5e9d83c08e18f2d304cb64072b7b62a4827e97cce48247404379e07a93e84","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-04T17:58:02Z","title_canon_sha256":"a1426fabe8def96f45abc63983d43e14036c3cee5c361beefa6fb7eab97f99da"},"schema_version":"1.0","source":{"id":"2204.01692","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.01692","created_at":"2026-07-05T05:30:28Z"},{"alias_kind":"arxiv_version","alias_value":"2204.01692v3","created_at":"2026-07-05T05:30:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.01692","created_at":"2026-07-05T05:30:28Z"},{"alias_kind":"pith_short_12","alias_value":"2NZMNZKZHSOE","created_at":"2026-07-05T05:30:28Z"},{"alias_kind":"pith_short_16","alias_value":"2NZMNZKZHSOEEP6A","created_at":"2026-07-05T05:30:28Z"},{"alias_kind":"pith_short_8","alias_value":"2NZMNZKZ","created_at":"2026-07-05T05:30:28Z"}],"graph_snapshots":[{"event_id":"sha256:de4662d22b309e5bcc9ae8ba20c9ba161dc3de39e822e4ad494cd88c3e6ff586","target":"graph","created_at":"2026-07-05T05:30:28Z","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/2204.01692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most modern video recognition models are designed to operate on short video clips (e.g., 5-10s in length). Thus, it is challenging to apply such models to long movie understanding tasks, which typically require sophisticated long-range temporal reasoning. The recently introduced video transformers partially address this issue by using long-range temporal self-attention. However, due to the quadratic cost of self-attention, such models are often costly and impractical to use. Instead, we propose ViS4mer, an efficient long-range video model that combines the strengths of self-attention and the r","authors_text":"Gedas Bertasius, Md Mohaiminul Islam","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-04T17:58:02Z","title":"Long Movie Clip Classification with State-Space Video Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.01692","kind":"arxiv","version":3},"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":"sha256:6b61ef269d68405d4a06248119f2869ec3b0a41f21ede124cdd8c7112a5a7274","target":"record","created_at":"2026-07-05T05:30:28Z","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":"4da5e9d83c08e18f2d304cb64072b7b62a4827e97cce48247404379e07a93e84","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-04T17:58:02Z","title_canon_sha256":"a1426fabe8def96f45abc63983d43e14036c3cee5c361beefa6fb7eab97f99da"},"schema_version":"1.0","source":{"id":"2204.01692","kind":"arxiv","version":3}},"canonical_sha256":"d372c6e5593c9c423fc0d587fc1aa51465d042483362c61f08f66c510b694c27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d372c6e5593c9c423fc0d587fc1aa51465d042483362c61f08f66c510b694c27","first_computed_at":"2026-07-05T05:30:28.890853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:30:28.890853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eUQfsgX0PNlN2xVMo0BEqXdApXVBtMhb41iKxBnt7O5gIhz5y7yOdU62CFCRTuZflQzQ5+p1hjRzemaaQ4S4Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T05:30:28.891216Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.01692","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b61ef269d68405d4a06248119f2869ec3b0a41f21ede124cdd8c7112a5a7274","sha256:de4662d22b309e5bcc9ae8ba20c9ba161dc3de39e822e4ad494cd88c3e6ff586"],"state_sha256":"09a8dfce93b13eb02b981283e7e6605dd61ee4c8158e27f45a0f1d475be80ddf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TBC4/IstYhJw1LXz1K7yDpydYSVhBan+1Q6UKmKk9uTzFuL/bRQXeoAlxovAAWR2I682GcF+Oh+w9VsN2vxyBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T11:28:43.880682Z","bundle_sha256":"01976017e6cff399ce4a0cf34eb59e938be83b494c09f6e8f50701435905b68f"}}