{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:AULWFMZT3S7MHH3Q7CMYQT6ZBT","short_pith_number":"pith:AULWFMZT","canonical_record":{"source":{"id":"2104.08665","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-17T23:51:05Z","cross_cats_sorted":[],"title_canon_sha256":"8330609fe05f3980fb0b6a209cf27627171094966f213c6e9fad158aca9cb8e8","abstract_canon_sha256":"b7ea136736832c74f069e650d688133b19440a803e5da05efe031d9170d7fac9"},"schema_version":"1.0"},"canonical_sha256":"051762b333dcbec39f70f899884fd90cfa3824d65be2141db6f97ae9223599df","source":{"kind":"arxiv","id":"2104.08665","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08665","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08665v3","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08665","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_12","alias_value":"AULWFMZT3S7M","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_16","alias_value":"AULWFMZT3S7MHH3Q","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_8","alias_value":"AULWFMZT","created_at":"2026-07-05T03:15:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:AULWFMZT3S7MHH3Q7CMYQT6ZBT","target":"record","payload":{"canonical_record":{"source":{"id":"2104.08665","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-17T23:51:05Z","cross_cats_sorted":[],"title_canon_sha256":"8330609fe05f3980fb0b6a209cf27627171094966f213c6e9fad158aca9cb8e8","abstract_canon_sha256":"b7ea136736832c74f069e650d688133b19440a803e5da05efe031d9170d7fac9"},"schema_version":"1.0"},"canonical_sha256":"051762b333dcbec39f70f899884fd90cfa3824d65be2141db6f97ae9223599df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:52.515679Z","signature_b64":"ryZH9AHxxUM1/4QEk7HW415HWy30UyaPlWVzded+nr2BF2Cc7X2986sYNlqEljbTm5iPPZMYAG7EVag8lsqNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"051762b333dcbec39f70f899884fd90cfa3824d65be2141db6f97ae9223599df","last_reissued_at":"2026-07-05T03:15:52.515173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:52.515173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.08665","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":"2026-07-05T03:15:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UJpeOF8R7NlSCnjOlVjBp42Ts3aLPEAkP/T8kBl0ng2Dx9WB+ver8F6SICRXQlP1PLy/s9ewKGy8Juxtz0cPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:20:41.815739Z"},"content_sha256":"6be0dfa55d59ea5ce821c44a99942a39008dc277ca8eeb81874810fdca601808","schema_version":"1.0","event_id":"sha256:6be0dfa55d59ea5ce821c44a99942a39008dc277ca8eeb81874810fdca601808"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:AULWFMZT3S7MHH3Q7CMYQT6ZBT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Higher Order Recurrent Space-Time Transformer for Video Action Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-Kuang Lee, Giuseppe Fiameni, Oswald Lanz, Tsung-Ming Tai","submitted_at":"2021-04-17T23:51:05Z","abstract_excerpt":"Endowing visual agents with predictive capability is a key step towards video intelligence at scale. The predominant modeling paradigm for this is sequence learning, mostly implemented through LSTMs. Feed-forward Transformer architectures have replaced recurrent model designs in ML applications of language processing and also partly in computer vision. In this paper we investigate on the competitiveness of Transformer-style architectures for video predictive tasks. To do so we propose HORST, a novel higher order recurrent layer design whose core element is a spatial-temporal decomposition of s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08665","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/2104.08665/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":"2026-07-05T03:15:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0p4mbHsfRB1XY1YI2keXH/kjCOnBGb6v2x2rJsfqgRabthMj0A+KYKaXqWyCaYhoBXJTh74NFqhXNltfDBf1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:20:41.816258Z"},"content_sha256":"a3e0c283908fac09b63b916dac04be8f8faeb27fd18bb7f1ab9417b936957de2","schema_version":"1.0","event_id":"sha256:a3e0c283908fac09b63b916dac04be8f8faeb27fd18bb7f1ab9417b936957de2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AULWFMZT3S7MHH3Q7CMYQT6ZBT/bundle.json","state_url":"https://pith.science/pith/AULWFMZT3S7MHH3Q7CMYQT6ZBT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AULWFMZT3S7MHH3Q7CMYQT6ZBT/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":"2026-08-14T07:20:41Z","links":{"resolver":"https://pith.science/pith/AULWFMZT3S7MHH3Q7CMYQT6ZBT","bundle":"https://pith.science/pith/AULWFMZT3S7MHH3Q7CMYQT6ZBT/bundle.json","state":"https://pith.science/pith/AULWFMZT3S7MHH3Q7CMYQT6ZBT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AULWFMZT3S7MHH3Q7CMYQT6ZBT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AULWFMZT3S7MHH3Q7CMYQT6ZBT","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":"b7ea136736832c74f069e650d688133b19440a803e5da05efe031d9170d7fac9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-17T23:51:05Z","title_canon_sha256":"8330609fe05f3980fb0b6a209cf27627171094966f213c6e9fad158aca9cb8e8"},"schema_version":"1.0","source":{"id":"2104.08665","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08665","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08665v3","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08665","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_12","alias_value":"AULWFMZT3S7M","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_16","alias_value":"AULWFMZT3S7MHH3Q","created_at":"2026-07-05T03:15:52Z"},{"alias_kind":"pith_short_8","alias_value":"AULWFMZT","created_at":"2026-07-05T03:15:52Z"}],"graph_snapshots":[{"event_id":"sha256:a3e0c283908fac09b63b916dac04be8f8faeb27fd18bb7f1ab9417b936957de2","target":"graph","created_at":"2026-07-05T03:15:52Z","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/2104.08665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Endowing visual agents with predictive capability is a key step towards video intelligence at scale. The predominant modeling paradigm for this is sequence learning, mostly implemented through LSTMs. Feed-forward Transformer architectures have replaced recurrent model designs in ML applications of language processing and also partly in computer vision. In this paper we investigate on the competitiveness of Transformer-style architectures for video predictive tasks. To do so we propose HORST, a novel higher order recurrent layer design whose core element is a spatial-temporal decomposition of s","authors_text":"Cheng-Kuang Lee, Giuseppe Fiameni, Oswald Lanz, Tsung-Ming Tai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-17T23:51:05Z","title":"Higher Order Recurrent Space-Time Transformer for Video Action Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08665","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":"sha256:6be0dfa55d59ea5ce821c44a99942a39008dc277ca8eeb81874810fdca601808","target":"record","created_at":"2026-07-05T03:15:52Z","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":"b7ea136736832c74f069e650d688133b19440a803e5da05efe031d9170d7fac9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-17T23:51:05Z","title_canon_sha256":"8330609fe05f3980fb0b6a209cf27627171094966f213c6e9fad158aca9cb8e8"},"schema_version":"1.0","source":{"id":"2104.08665","kind":"arxiv","version":3}},"canonical_sha256":"051762b333dcbec39f70f899884fd90cfa3824d65be2141db6f97ae9223599df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"051762b333dcbec39f70f899884fd90cfa3824d65be2141db6f97ae9223599df","first_computed_at":"2026-07-05T03:15:52.515173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:52.515173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ryZH9AHxxUM1/4QEk7HW415HWy30UyaPlWVzded+nr2BF2Cc7X2986sYNlqEljbTm5iPPZMYAG7EVag8lsqNAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:52.515679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.08665","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6be0dfa55d59ea5ce821c44a99942a39008dc277ca8eeb81874810fdca601808","sha256:a3e0c283908fac09b63b916dac04be8f8faeb27fd18bb7f1ab9417b936957de2"],"state_sha256":"15d4b4191c60e611fbe6e00be20f94a26904338d584a0fb17c2b89d19a995e27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sPVVinRtv8JHmGjVptxluj6ng+Hr1zEfbNOvI6aSmORvhCGHTk1vOotFgp8qENQqskzLZWxQ880qZXrKhdi5BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T07:20:41.823092Z","bundle_sha256":"71bc478f673dcfe33121a34cfc83dac4e677c9e62f89081fd996cdbeab3f6eb1"}}