{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PYGOXYOJJ3AYOGWHLR2DILWCV4","short_pith_number":"pith:PYGOXYOJ","canonical_record":{"source":{"id":"2307.06947","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-13T17:59:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"17d2c7990256f02b4ef24029ae41d306d5fc5408a7ef97c2b2fdabb817a184a0","abstract_canon_sha256":"8bcb04bdd682ce39f2c1d3dc1366299c1dbc1c2ae6cbb117b8ee2999a4f24b46"},"schema_version":"1.0"},"canonical_sha256":"7e0cebe1c94ec1871ac75c74342ec2af16ebf9e6a2dfc76a3af1d17ed45535cb","source":{"kind":"arxiv","id":"2307.06947","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06947","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06947v4","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06947","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"PYGOXYOJJ3AY","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"PYGOXYOJJ3AYOGWH","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"PYGOXYOJ","created_at":"2026-07-05T07:05:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PYGOXYOJJ3AYOGWHLR2DILWCV4","target":"record","payload":{"canonical_record":{"source":{"id":"2307.06947","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-13T17:59:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"17d2c7990256f02b4ef24029ae41d306d5fc5408a7ef97c2b2fdabb817a184a0","abstract_canon_sha256":"8bcb04bdd682ce39f2c1d3dc1366299c1dbc1c2ae6cbb117b8ee2999a4f24b46"},"schema_version":"1.0"},"canonical_sha256":"7e0cebe1c94ec1871ac75c74342ec2af16ebf9e6a2dfc76a3af1d17ed45535cb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:46.099511Z","signature_b64":"otcJZn4cOEsRKVLgC9jwV0caBtTHMiN8Q4ka5kiymuQnMDWUUDjNmifSAqVfiMQcObFZFtXNC3lIKeBvtWxqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e0cebe1c94ec1871ac75c74342ec2af16ebf9e6a2dfc76a3af1d17ed45535cb","last_reissued_at":"2026-07-05T07:05:46.099076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:46.099076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.06947","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AVWLXqHJsBSbHAziJlp/zpIYEig2SZMW95Nr2+m/ZDmPArkWwAEJTNRuZaqNDc3p3/CTX4veBt5xevRXyY7sAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:11:13.058643Z"},"content_sha256":"817af351259cb3b9d0adf917a56fd0834dfbc1d3c90f88e49ca27e040e1acc19","schema_version":"1.0","event_id":"sha256:817af351259cb3b9d0adf917a56fd0834dfbc1d3c90f88e49ca27e040e1acc19"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PYGOXYOJJ3AYOGWHLR2DILWCV4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Mubarak Shah, Muhammad Uzair Khattak, Muzammal Naseer, Salman Khan, Syed Talal Wasim","submitted_at":"2023-07-13T17:59:33Z","abstract_excerpt":"Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison, convolutional designs for videos offer an efficient alternative but lack long-range dependency modeling. Towards achieving the best of both designs, this work proposes Video-FocalNet, an effective and efficient architecture for video recognition that models both local and global contexts. Video-FocalNet is based on a spatio-temporal focal modulation architectur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06947","kind":"arxiv","version":4},"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/2307.06947/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":"2026-07-05T07:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OMy0bpENw1rqePr9Jhuxxz8iyopXxB1711hCuSbvwHfaTPpQVKk/LbMhTYtu98Q0ZGVcX6XVmI4l1UKzk7WoDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:11:13.059031Z"},"content_sha256":"ce172c34da2bc29393691c898a9a4b95958f56a210e5d8687a6dd53e2c30bef8","schema_version":"1.0","event_id":"sha256:ce172c34da2bc29393691c898a9a4b95958f56a210e5d8687a6dd53e2c30bef8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYGOXYOJJ3AYOGWHLR2DILWCV4/bundle.json","state_url":"https://pith.science/pith/PYGOXYOJJ3AYOGWHLR2DILWCV4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYGOXYOJJ3AYOGWHLR2DILWCV4/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":"2026-07-07T07:11:13Z","links":{"resolver":"https://pith.science/pith/PYGOXYOJJ3AYOGWHLR2DILWCV4","bundle":"https://pith.science/pith/PYGOXYOJJ3AYOGWHLR2DILWCV4/bundle.json","state":"https://pith.science/pith/PYGOXYOJJ3AYOGWHLR2DILWCV4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYGOXYOJJ3AYOGWHLR2DILWCV4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PYGOXYOJJ3AYOGWHLR2DILWCV4","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":"8bcb04bdd682ce39f2c1d3dc1366299c1dbc1c2ae6cbb117b8ee2999a4f24b46","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-13T17:59:33Z","title_canon_sha256":"17d2c7990256f02b4ef24029ae41d306d5fc5408a7ef97c2b2fdabb817a184a0"},"schema_version":"1.0","source":{"id":"2307.06947","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06947","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06947v4","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06947","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"PYGOXYOJJ3AY","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"PYGOXYOJJ3AYOGWH","created_at":"2026-07-05T07:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"PYGOXYOJ","created_at":"2026-07-05T07:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:ce172c34da2bc29393691c898a9a4b95958f56a210e5d8687a6dd53e2c30bef8","target":"graph","created_at":"2026-07-05T07:05:46Z","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/2307.06947/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison, convolutional designs for videos offer an efficient alternative but lack long-range dependency modeling. Towards achieving the best of both designs, this work proposes Video-FocalNet, an effective and efficient architecture for video recognition that models both local and global contexts. Video-FocalNet is based on a spatio-temporal focal modulation architectur","authors_text":"Fahad Shahbaz Khan, Mubarak Shah, Muhammad Uzair Khattak, Muzammal Naseer, Salman Khan, Syed Talal Wasim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-13T17:59:33Z","title":"Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06947","kind":"arxiv","version":4},"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":"sha256:817af351259cb3b9d0adf917a56fd0834dfbc1d3c90f88e49ca27e040e1acc19","target":"record","created_at":"2026-07-05T07:05:46Z","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":"8bcb04bdd682ce39f2c1d3dc1366299c1dbc1c2ae6cbb117b8ee2999a4f24b46","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-13T17:59:33Z","title_canon_sha256":"17d2c7990256f02b4ef24029ae41d306d5fc5408a7ef97c2b2fdabb817a184a0"},"schema_version":"1.0","source":{"id":"2307.06947","kind":"arxiv","version":4}},"canonical_sha256":"7e0cebe1c94ec1871ac75c74342ec2af16ebf9e6a2dfc76a3af1d17ed45535cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e0cebe1c94ec1871ac75c74342ec2af16ebf9e6a2dfc76a3af1d17ed45535cb","first_computed_at":"2026-07-05T07:05:46.099076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:46.099076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"otcJZn4cOEsRKVLgC9jwV0caBtTHMiN8Q4ka5kiymuQnMDWUUDjNmifSAqVfiMQcObFZFtXNC3lIKeBvtWxqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:46.099511Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.06947","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:817af351259cb3b9d0adf917a56fd0834dfbc1d3c90f88e49ca27e040e1acc19","sha256:ce172c34da2bc29393691c898a9a4b95958f56a210e5d8687a6dd53e2c30bef8"],"state_sha256":"a61af3f10c1686f7316612c1a0a1a460345239b848d91723c4fbf2b1d1b1683c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n1kKZQQwIefwvGcJOnQqLyg9H3iJMlMRZSC4wFYAhq3FAs+wVaXvoh4pVBcxfWEy0m15p72DExhkDu4YHmJ/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:11:13.061231Z","bundle_sha256":"159ad3fe15cea14065f68c3dd2bc39a55df3023ffda649947361e6e249113542"}}