{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SVAXBUE2AK7D5RMWDPQWUEP6MV","short_pith_number":"pith:SVAXBUE2","canonical_record":{"source":{"id":"1904.13080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-30T07:19:50Z","cross_cats_sorted":[],"title_canon_sha256":"e22d6ae8183e5566e829e38f3557d2cc918647f3c11821b94a0d62412638de91","abstract_canon_sha256":"99b4f51296920a3d7d0318a031396e534b729bc5c6e4384733a9869a4c6705af"},"schema_version":"1.0"},"canonical_sha256":"954170d09a02be3ec5961be16a11fe6566d877c4b9f26c0f20bb7213808174f7","source":{"kind":"arxiv","id":"1904.13080","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.13080","created_at":"2026-05-17T23:47:23Z"},{"alias_kind":"arxiv_version","alias_value":"1904.13080v1","created_at":"2026-05-17T23:47:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.13080","created_at":"2026-05-17T23:47:23Z"},{"alias_kind":"pith_short_12","alias_value":"SVAXBUE2AK7D","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SVAXBUE2AK7D5RMW","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SVAXBUE2","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SVAXBUE2AK7D5RMWDPQWUEP6MV","target":"record","payload":{"canonical_record":{"source":{"id":"1904.13080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-30T07:19:50Z","cross_cats_sorted":[],"title_canon_sha256":"e22d6ae8183e5566e829e38f3557d2cc918647f3c11821b94a0d62412638de91","abstract_canon_sha256":"99b4f51296920a3d7d0318a031396e534b729bc5c6e4384733a9869a4c6705af"},"schema_version":"1.0"},"canonical_sha256":"954170d09a02be3ec5961be16a11fe6566d877c4b9f26c0f20bb7213808174f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:23.978177Z","signature_b64":"etFIQTUw12l40id5m1EumO5cgXvtWRFFKvaSjgvaI5nUYSoarBwA4sPVjior2vHfYbJbOVhmqJNGygnnUiykBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"954170d09a02be3ec5961be16a11fe6566d877c4b9f26c0f20bb7213808174f7","last_reissued_at":"2026-05-17T23:47:23.977656Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:23.977656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.13080","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":"2026-05-17T23:47:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e7S4VLIx0SUr8N2BZrK65WmvY3BxxKCsD0zGP9GHqW8ox6R8xe+GYPb6zm6YHzNEH+YT/S5J2V8ceirFbM4WCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T10:29:02.691914Z"},"content_sha256":"b487bd3996efb33cd5940ed007540b832add544b23a10cd63ceedd93389b5bae","schema_version":"1.0","event_id":"sha256:b487bd3996efb33cd5940ed007540b832add544b23a10cd63ceedd93389b5bae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SVAXBUE2AK7D5RMWDPQWUEP6MV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Memory-Augmented Temporal Dynamic Learning for Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Wang, Qi Wang, Yuan Yuan","submitted_at":"2019-04-30T07:19:50Z","abstract_excerpt":"Human actions captured in video sequences contain two crucial factors for action recognition, i.e., visual appearance and motion dynamics. To model these two aspects, Convolutional and Recurrent Neural Networks (CNNs and RNNs) are adopted in most existing successful methods for recognizing actions. However, CNN based methods are limited in modeling long-term motion dynamics. RNNs are able to learn temporal motion dynamics but lack effective ways to tackle unsteady dynamics in long-duration motion. In this work, we propose a memory-augmented temporal dynamic learning network, which learns to wr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.13080","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":""},"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":"2026-05-17T23:47:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rY4v4pfEeT79plK60gTBxchxXF5I5Y4XpNAEEbSi7JgQB6O3H5hEyQ8m84i62IwTX7t8iYj5HwsI2eaChrAcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T10:29:02.692581Z"},"content_sha256":"3b74e6e2447b5b9841eb8ec3ca06378e129ab1e69532bdb6c78231b86ed52b2e","schema_version":"1.0","event_id":"sha256:3b74e6e2447b5b9841eb8ec3ca06378e129ab1e69532bdb6c78231b86ed52b2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SVAXBUE2AK7D5RMWDPQWUEP6MV/bundle.json","state_url":"https://pith.science/pith/SVAXBUE2AK7D5RMWDPQWUEP6MV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SVAXBUE2AK7D5RMWDPQWUEP6MV/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":"2026-06-10T10:29:02Z","links":{"resolver":"https://pith.science/pith/SVAXBUE2AK7D5RMWDPQWUEP6MV","bundle":"https://pith.science/pith/SVAXBUE2AK7D5RMWDPQWUEP6MV/bundle.json","state":"https://pith.science/pith/SVAXBUE2AK7D5RMWDPQWUEP6MV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SVAXBUE2AK7D5RMWDPQWUEP6MV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SVAXBUE2AK7D5RMWDPQWUEP6MV","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":"99b4f51296920a3d7d0318a031396e534b729bc5c6e4384733a9869a4c6705af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-30T07:19:50Z","title_canon_sha256":"e22d6ae8183e5566e829e38f3557d2cc918647f3c11821b94a0d62412638de91"},"schema_version":"1.0","source":{"id":"1904.13080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.13080","created_at":"2026-05-17T23:47:23Z"},{"alias_kind":"arxiv_version","alias_value":"1904.13080v1","created_at":"2026-05-17T23:47:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.13080","created_at":"2026-05-17T23:47:23Z"},{"alias_kind":"pith_short_12","alias_value":"SVAXBUE2AK7D","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SVAXBUE2AK7D5RMW","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SVAXBUE2","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:3b74e6e2447b5b9841eb8ec3ca06378e129ab1e69532bdb6c78231b86ed52b2e","target":"graph","created_at":"2026-05-17T23:47:23Z","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"},"paper":{"abstract_excerpt":"Human actions captured in video sequences contain two crucial factors for action recognition, i.e., visual appearance and motion dynamics. To model these two aspects, Convolutional and Recurrent Neural Networks (CNNs and RNNs) are adopted in most existing successful methods for recognizing actions. However, CNN based methods are limited in modeling long-term motion dynamics. RNNs are able to learn temporal motion dynamics but lack effective ways to tackle unsteady dynamics in long-duration motion. In this work, we propose a memory-augmented temporal dynamic learning network, which learns to wr","authors_text":"Dong Wang, Qi Wang, Yuan Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-30T07:19:50Z","title":"Memory-Augmented Temporal Dynamic Learning for Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.13080","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:b487bd3996efb33cd5940ed007540b832add544b23a10cd63ceedd93389b5bae","target":"record","created_at":"2026-05-17T23:47:23Z","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":"99b4f51296920a3d7d0318a031396e534b729bc5c6e4384733a9869a4c6705af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-30T07:19:50Z","title_canon_sha256":"e22d6ae8183e5566e829e38f3557d2cc918647f3c11821b94a0d62412638de91"},"schema_version":"1.0","source":{"id":"1904.13080","kind":"arxiv","version":1}},"canonical_sha256":"954170d09a02be3ec5961be16a11fe6566d877c4b9f26c0f20bb7213808174f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"954170d09a02be3ec5961be16a11fe6566d877c4b9f26c0f20bb7213808174f7","first_computed_at":"2026-05-17T23:47:23.977656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:23.977656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"etFIQTUw12l40id5m1EumO5cgXvtWRFFKvaSjgvaI5nUYSoarBwA4sPVjior2vHfYbJbOVhmqJNGygnnUiykBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:23.978177Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.13080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b487bd3996efb33cd5940ed007540b832add544b23a10cd63ceedd93389b5bae","sha256:3b74e6e2447b5b9841eb8ec3ca06378e129ab1e69532bdb6c78231b86ed52b2e"],"state_sha256":"d203909b6a8221d4b5a73edf487b64efea92998a088688c252616131250c275a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ru5WtyDzy08dRoZmAo5D6tUCFFJ7++bbXVCM5bW7oAkm6ffIJnfjU2TYLW0uN2t7VIcPlekBophvOc87FbAVDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T10:29:02.696646Z","bundle_sha256":"4fcc54240b97cb0b7389d8c624edfc527eb4e8ef90fb18375f6cf71ed437a029"}}