{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:Y4PWFZ3IT5MKFUZ7QN45457QJJ","short_pith_number":"pith:Y4PWFZ3I","canonical_record":{"source":{"id":"2111.01024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-01T15:27:35Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"0e954f6203ef570eb6b59fc1abeab30c1b2f83f1f8688e7e94b3e18ed0fa9922","abstract_canon_sha256":"0bafd0ce230aa298a96f539fe1d91fad6e77f575e5883fa2d74567051a0d5a2a"},"schema_version":"1.0"},"canonical_sha256":"c71f62e7689f58a2d33f8379de77f04a768e299a3f85e504c0ec0864b5171ba7","source":{"kind":"arxiv","id":"2111.01024","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.01024","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"arxiv_version","alias_value":"2111.01024v1","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01024","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"pith_short_12","alias_value":"Y4PWFZ3IT5MK","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"Y4PWFZ3IT5MKFUZ7","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"Y4PWFZ3I","created_at":"2026-07-05T03:27:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:Y4PWFZ3IT5MKFUZ7QN45457QJJ","target":"record","payload":{"canonical_record":{"source":{"id":"2111.01024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-01T15:27:35Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"0e954f6203ef570eb6b59fc1abeab30c1b2f83f1f8688e7e94b3e18ed0fa9922","abstract_canon_sha256":"0bafd0ce230aa298a96f539fe1d91fad6e77f575e5883fa2d74567051a0d5a2a"},"schema_version":"1.0"},"canonical_sha256":"c71f62e7689f58a2d33f8379de77f04a768e299a3f85e504c0ec0864b5171ba7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:52.751190Z","signature_b64":"0bTwTGpiBBmiclNCEU8lO6yzaUxbTJnKwm6lgG7Dy+uXinThP95RIq54IPCGuanaCLDCJjnQkSyYE2OrLuFjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c71f62e7689f58a2d33f8379de77f04a768e299a3f85e504c0ec0864b5171ba7","last_reissued_at":"2026-07-05T03:27:52.750664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:52.750664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.01024","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":"2026-07-05T03:27:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QNAe+GLjTjJjH/YcxCGpElaNMPD53O5YgLztQ42UkAhwCgYrWmaagZ998b2BF9kt1TOh9Ffac0+IF66PoedsCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:05:27.159926Z"},"content_sha256":"d4c8e528d093f26eb327e29799bb4ece2f964e048bf608d09b4aa903027c6212","schema_version":"1.0","event_id":"sha256:d4c8e528d093f26eb327e29799bb4ece2f964e048bf608d09b4aa903027c6212"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:Y4PWFZ3IT5MKFUZ7QN45457QJJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Arsha Nagrani, Dima Damen, Evangelos Kazakos, Jaesung Huh","submitted_at":"2021-11-01T15:27:35Z","abstract_excerpt":"In egocentric videos, actions occur in quick succession. We capitalise on the action's temporal context and propose a method that learns to attend to surrounding actions in order to improve recognition performance. To incorporate the temporal context, we propose a transformer-based multimodal model that ingests video and audio as input modalities, with an explicit language model providing action sequence context to enhance the predictions. We test our approach on EPIC-KITCHENS and EGTEA datasets reporting state-of-the-art performance. Our ablations showcase the advantage of utilising temporal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01024","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/2111.01024/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":"2026-07-05T03:27:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RmeWFwy1KYzC2tni8js256MdY1mcNqr0ah9o1I3dLKqw9Rb97Q/bMVgmrvn3EtTeihJLaZnDXbdKckMzS6X1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:05:27.160544Z"},"content_sha256":"62b996f44d843d3c86a6cfae5469b9a53558cd0a735da07f61e3d35045aa6008","schema_version":"1.0","event_id":"sha256:62b996f44d843d3c86a6cfae5469b9a53558cd0a735da07f61e3d35045aa6008"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ/bundle.json","state_url":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ/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":"2026-08-09T18:05:27Z","links":{"resolver":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ","bundle":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ/bundle.json","state":"https://pith.science/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y4PWFZ3IT5MKFUZ7QN45457QJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:Y4PWFZ3IT5MKFUZ7QN45457QJJ","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":"0bafd0ce230aa298a96f539fe1d91fad6e77f575e5883fa2d74567051a0d5a2a","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-01T15:27:35Z","title_canon_sha256":"0e954f6203ef570eb6b59fc1abeab30c1b2f83f1f8688e7e94b3e18ed0fa9922"},"schema_version":"1.0","source":{"id":"2111.01024","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.01024","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"arxiv_version","alias_value":"2111.01024v1","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01024","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"pith_short_12","alias_value":"Y4PWFZ3IT5MK","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"Y4PWFZ3IT5MKFUZ7","created_at":"2026-07-05T03:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"Y4PWFZ3I","created_at":"2026-07-05T03:27:52Z"}],"graph_snapshots":[{"event_id":"sha256:62b996f44d843d3c86a6cfae5469b9a53558cd0a735da07f61e3d35045aa6008","target":"graph","created_at":"2026-07-05T03:27:52Z","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/2111.01024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In egocentric videos, actions occur in quick succession. We capitalise on the action's temporal context and propose a method that learns to attend to surrounding actions in order to improve recognition performance. To incorporate the temporal context, we propose a transformer-based multimodal model that ingests video and audio as input modalities, with an explicit language model providing action sequence context to enhance the predictions. We test our approach on EPIC-KITCHENS and EGTEA datasets reporting state-of-the-art performance. Our ablations showcase the advantage of utilising temporal ","authors_text":"Andrew Zisserman, Arsha Nagrani, Dima Damen, Evangelos Kazakos, Jaesung Huh","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-01T15:27:35Z","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01024","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:d4c8e528d093f26eb327e29799bb4ece2f964e048bf608d09b4aa903027c6212","target":"record","created_at":"2026-07-05T03:27:52Z","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":"0bafd0ce230aa298a96f539fe1d91fad6e77f575e5883fa2d74567051a0d5a2a","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-01T15:27:35Z","title_canon_sha256":"0e954f6203ef570eb6b59fc1abeab30c1b2f83f1f8688e7e94b3e18ed0fa9922"},"schema_version":"1.0","source":{"id":"2111.01024","kind":"arxiv","version":1}},"canonical_sha256":"c71f62e7689f58a2d33f8379de77f04a768e299a3f85e504c0ec0864b5171ba7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c71f62e7689f58a2d33f8379de77f04a768e299a3f85e504c0ec0864b5171ba7","first_computed_at":"2026-07-05T03:27:52.750664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:52.750664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0bTwTGpiBBmiclNCEU8lO6yzaUxbTJnKwm6lgG7Dy+uXinThP95RIq54IPCGuanaCLDCJjnQkSyYE2OrLuFjBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:52.751190Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.01024","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4c8e528d093f26eb327e29799bb4ece2f964e048bf608d09b4aa903027c6212","sha256:62b996f44d843d3c86a6cfae5469b9a53558cd0a735da07f61e3d35045aa6008"],"state_sha256":"36bafaa17cfbb1c5581aa73f2ad82adf6623ae4f3e76736b18cbbc828c72f6d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kzW7kG34YjUy6CBkusMKq4/ux1jv7fxvKhhzhxdTv9xv6Q5QmM/4CsWfrY+72MdfTnyT7QlxDsrk/qYK7AWTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:05:27.166107Z","bundle_sha256":"4e53c20ed8e270af75cff6fd2c3e3313f425643249282d2409c9bcbe0189cbda"}}