{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CMKSV5ZHJ4X4IXG2WH5HXGCG4Y","short_pith_number":"pith:CMKSV5ZH","canonical_record":{"source":{"id":"2110.13992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-26T19:58:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"610f3fa9164ec0264abfe1278d48775300cf0ba5e6152ffe43037457b8074297","abstract_canon_sha256":"f5b8731b685f7a3ac12ef7ee4a5ed504626a803d52b019d7a21567d3470e3b0d"},"schema_version":"1.0"},"canonical_sha256":"13152af7274f2fc45cdab1fa7b9846e606f49ff370c6baa4a882c52acef1f3ff","source":{"kind":"arxiv","id":"2110.13992","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.13992","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"arxiv_version","alias_value":"2110.13992v1","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13992","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"pith_short_12","alias_value":"CMKSV5ZHJ4X4","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"pith_short_16","alias_value":"CMKSV5ZHJ4X4IXG2","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"pith_short_8","alias_value":"CMKSV5ZH","created_at":"2026-07-05T03:26:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CMKSV5ZHJ4X4IXG2WH5HXGCG4Y","target":"record","payload":{"canonical_record":{"source":{"id":"2110.13992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-26T19:58:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"610f3fa9164ec0264abfe1278d48775300cf0ba5e6152ffe43037457b8074297","abstract_canon_sha256":"f5b8731b685f7a3ac12ef7ee4a5ed504626a803d52b019d7a21567d3470e3b0d"},"schema_version":"1.0"},"canonical_sha256":"13152af7274f2fc45cdab1fa7b9846e606f49ff370c6baa4a882c52acef1f3ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:22.566606Z","signature_b64":"KdEbSXQcxar10LijP/ojjf+r1wShwhiYWE7xVFxHuOlEfwDkFq2Xe/+RO2PePUFqGIqHk5YFekEJjFKlAYoZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13152af7274f2fc45cdab1fa7b9846e606f49ff370c6baa4a882c52acef1f3ff","last_reissued_at":"2026-07-05T03:26:22.566119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:22.566119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.13992","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":"2026-07-05T03:26:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aWkSlroP+WKV88ROXv/EI5LijzWSlEtE9kohwOQOyCCchsRrHNIvPQtd6fha7362+RnJImmP2lDtLTpYguOPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:01:14.059090Z"},"content_sha256":"59861885ff759fcfb846aac8167ea2de7f7fb15938fbe28d99f1f81ff4b8f953","schema_version":"1.0","event_id":"sha256:59861885ff759fcfb846aac8167ea2de7f7fb15938fbe28d99f1f81ff4b8f953"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CMKSV5ZHJ4X4IXG2WH5HXGCG4Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Local Temporal Information for Multimodal Scene Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Palash Goyal, Saurabh Sahu","submitted_at":"2021-10-26T19:58:32Z","abstract_excerpt":"Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized representations for individual tokens given a sequence of tokens, are becoming increasingly popular in many computer vision tasks. However, the use of Transformer based models for video understanding is still relatively unexplored. Moreover, these models fail to exploit the strong temporal relationships between the neighboring video frames to get potent frame-level repre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13992","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/2110.13992/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":"2026-07-05T03:26:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UoE2Zda8tYkSxazW+5J2LsIhb2lhOVliiqBn92YBlUd6hsbJM9martpYYTpNvIC7UhvZ1SxdSOIOVXPqzVerAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:01:14.059470Z"},"content_sha256":"a9e3cf29cf6b056266fec9d717444ebd8b6e61ac7e90efe40f8e9df779adb48c","schema_version":"1.0","event_id":"sha256:a9e3cf29cf6b056266fec9d717444ebd8b6e61ac7e90efe40f8e9df779adb48c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CMKSV5ZHJ4X4IXG2WH5HXGCG4Y/bundle.json","state_url":"https://pith.science/pith/CMKSV5ZHJ4X4IXG2WH5HXGCG4Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CMKSV5ZHJ4X4IXG2WH5HXGCG4Y/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":"2026-07-07T06:01:14Z","links":{"resolver":"https://pith.science/pith/CMKSV5ZHJ4X4IXG2WH5HXGCG4Y","bundle":"https://pith.science/pith/CMKSV5ZHJ4X4IXG2WH5HXGCG4Y/bundle.json","state":"https://pith.science/pith/CMKSV5ZHJ4X4IXG2WH5HXGCG4Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CMKSV5ZHJ4X4IXG2WH5HXGCG4Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CMKSV5ZHJ4X4IXG2WH5HXGCG4Y","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":"f5b8731b685f7a3ac12ef7ee4a5ed504626a803d52b019d7a21567d3470e3b0d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-26T19:58:32Z","title_canon_sha256":"610f3fa9164ec0264abfe1278d48775300cf0ba5e6152ffe43037457b8074297"},"schema_version":"1.0","source":{"id":"2110.13992","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.13992","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"arxiv_version","alias_value":"2110.13992v1","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13992","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"pith_short_12","alias_value":"CMKSV5ZHJ4X4","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"pith_short_16","alias_value":"CMKSV5ZHJ4X4IXG2","created_at":"2026-07-05T03:26:22Z"},{"alias_kind":"pith_short_8","alias_value":"CMKSV5ZH","created_at":"2026-07-05T03:26:22Z"}],"graph_snapshots":[{"event_id":"sha256:a9e3cf29cf6b056266fec9d717444ebd8b6e61ac7e90efe40f8e9df779adb48c","target":"graph","created_at":"2026-07-05T03:26:22Z","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/2110.13992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized representations for individual tokens given a sequence of tokens, are becoming increasingly popular in many computer vision tasks. However, the use of Transformer based models for video understanding is still relatively unexplored. Moreover, these models fail to exploit the strong temporal relationships between the neighboring video frames to get potent frame-level repre","authors_text":"Palash Goyal, Saurabh Sahu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-26T19:58:32Z","title":"Leveraging Local Temporal Information for Multimodal Scene Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13992","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":"sha256:59861885ff759fcfb846aac8167ea2de7f7fb15938fbe28d99f1f81ff4b8f953","target":"record","created_at":"2026-07-05T03:26:22Z","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":"f5b8731b685f7a3ac12ef7ee4a5ed504626a803d52b019d7a21567d3470e3b0d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-26T19:58:32Z","title_canon_sha256":"610f3fa9164ec0264abfe1278d48775300cf0ba5e6152ffe43037457b8074297"},"schema_version":"1.0","source":{"id":"2110.13992","kind":"arxiv","version":1}},"canonical_sha256":"13152af7274f2fc45cdab1fa7b9846e606f49ff370c6baa4a882c52acef1f3ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13152af7274f2fc45cdab1fa7b9846e606f49ff370c6baa4a882c52acef1f3ff","first_computed_at":"2026-07-05T03:26:22.566119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:22.566119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KdEbSXQcxar10LijP/ojjf+r1wShwhiYWE7xVFxHuOlEfwDkFq2Xe/+RO2PePUFqGIqHk5YFekEJjFKlAYoZDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:22.566606Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.13992","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59861885ff759fcfb846aac8167ea2de7f7fb15938fbe28d99f1f81ff4b8f953","sha256:a9e3cf29cf6b056266fec9d717444ebd8b6e61ac7e90efe40f8e9df779adb48c"],"state_sha256":"5f7c4098f4cac67fbb64bb3079015c9e86a2e61eea3712ee298564dfd4303c7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T8eG0T16/wN7btxWAL8HngvjMjVroztRAWh6tv3ZD0pjgvoEYv59YQW/3MVVhNisfJlvSt17F8hZED1cmpMhCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:01:14.061458Z","bundle_sha256":"0aa1d0e19dccc6fc459031c8677a69e6f1e0f4fd00cfefcfc7a4c1440fa7d114"}}