{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4QS3DGMMZSCHJZIZ7CG5Z2JXD3","short_pith_number":"pith:4QS3DGMM","canonical_record":{"source":{"id":"1708.03958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-13T19:27:34Z","cross_cats_sorted":[],"title_canon_sha256":"af124e2dc4648ffd62b4b3db1b59d4fb80f998be86c85dff0f8acfb3168433a9","abstract_canon_sha256":"1cb0c7f6c65ef60be857e9ca098be17698df6f002430ee9d51cc4a3cb8cefefa"},"schema_version":"1.0"},"canonical_sha256":"e425b1998ccc8474e519f88ddce9371ef0af0b0ebb743aeab3de916f4c90dcb9","source":{"kind":"arxiv","id":"1708.03958","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.03958","created_at":"2026-05-18T00:38:07Z"},{"alias_kind":"arxiv_version","alias_value":"1708.03958v1","created_at":"2026-05-18T00:38:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.03958","created_at":"2026-05-18T00:38:07Z"},{"alias_kind":"pith_short_12","alias_value":"4QS3DGMMZSCH","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4QS3DGMMZSCHJZIZ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4QS3DGMM","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4QS3DGMMZSCHJZIZ7CG5Z2JXD3","target":"record","payload":{"canonical_record":{"source":{"id":"1708.03958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-13T19:27:34Z","cross_cats_sorted":[],"title_canon_sha256":"af124e2dc4648ffd62b4b3db1b59d4fb80f998be86c85dff0f8acfb3168433a9","abstract_canon_sha256":"1cb0c7f6c65ef60be857e9ca098be17698df6f002430ee9d51cc4a3cb8cefefa"},"schema_version":"1.0"},"canonical_sha256":"e425b1998ccc8474e519f88ddce9371ef0af0b0ebb743aeab3de916f4c90dcb9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:07.424142Z","signature_b64":"zqGztYMfkdkRDRy95lejjIQ3PEIKTfcxTFQRCoNjSR0y+SfmJVr+lDYZ4cLMtMWhzlC4qrhPaZmWQU3Eee6aDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e425b1998ccc8474e519f88ddce9371ef0af0b0ebb743aeab3de916f4c90dcb9","last_reissued_at":"2026-05-18T00:38:07.423684Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:07.423684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.03958","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":"2026-05-18T00:38:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jEYgtH8joNxstANe3ZT5CFoxrz4wvSpQ8B8+y84f9OquGLlvxCzoioKFzdK+Ona+2p9Q7dqqi6dKcQHUoz2IDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:36:54.442700Z"},"content_sha256":"6d4e685305886bffff60d6da540ce6221514d63e925c96e8c257d8e594cf7e1c","schema_version":"1.0","event_id":"sha256:6d4e685305886bffff60d6da540ce6221514d63e925c96e8c257d8e594cf7e1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4QS3DGMMZSCHJZIZ7CG5Z2JXD3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lattice Long Short-Term Memory for Human Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bertram E. Shi, Dit Yan Yeung, Kevin Chen, Kui Jia, Lin Sun, Silvio Savarese","submitted_at":"2017-08-13T19:27:34Z","abstract_excerpt":"Human actions captured in video sequences are three-dimensional signals characterizing visual appearance and motion dynamics. To learn action patterns, existing methods adopt Convolutional and/or Recurrent Neural Networks (CNNs and RNNs). CNN based methods are effective in learning spatial appearances, but are limited in modeling long-term motion dynamics. RNNs, especially Long Short-Term Memory (LSTM), are able to learn temporal motion dynamics. However, naively applying RNNs to video sequences in a convolutional manner implicitly assumes that motions in videos are stationary across different"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.03958","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":"2026-05-18T00:38:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VG5EBUojQTvlZHb95ZcNGhh8LE5j16BwE1osJ35NfkGVQRJwFELkN7KsMaNMiT0nVbQR7qPLKHYzennz+fLvAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T18:36:54.443336Z"},"content_sha256":"2b014216ff9d3f670c3233db8df5ec52163d1702ab60f9faf448e80431485e43","schema_version":"1.0","event_id":"sha256:2b014216ff9d3f670c3233db8df5ec52163d1702ab60f9faf448e80431485e43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4QS3DGMMZSCHJZIZ7CG5Z2JXD3/bundle.json","state_url":"https://pith.science/pith/4QS3DGMMZSCHJZIZ7CG5Z2JXD3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4QS3DGMMZSCHJZIZ7CG5Z2JXD3/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":"2026-06-06T18:36:54Z","links":{"resolver":"https://pith.science/pith/4QS3DGMMZSCHJZIZ7CG5Z2JXD3","bundle":"https://pith.science/pith/4QS3DGMMZSCHJZIZ7CG5Z2JXD3/bundle.json","state":"https://pith.science/pith/4QS3DGMMZSCHJZIZ7CG5Z2JXD3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4QS3DGMMZSCHJZIZ7CG5Z2JXD3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4QS3DGMMZSCHJZIZ7CG5Z2JXD3","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":"1cb0c7f6c65ef60be857e9ca098be17698df6f002430ee9d51cc4a3cb8cefefa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-13T19:27:34Z","title_canon_sha256":"af124e2dc4648ffd62b4b3db1b59d4fb80f998be86c85dff0f8acfb3168433a9"},"schema_version":"1.0","source":{"id":"1708.03958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.03958","created_at":"2026-05-18T00:38:07Z"},{"alias_kind":"arxiv_version","alias_value":"1708.03958v1","created_at":"2026-05-18T00:38:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.03958","created_at":"2026-05-18T00:38:07Z"},{"alias_kind":"pith_short_12","alias_value":"4QS3DGMMZSCH","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4QS3DGMMZSCHJZIZ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4QS3DGMM","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:2b014216ff9d3f670c3233db8df5ec52163d1702ab60f9faf448e80431485e43","target":"graph","created_at":"2026-05-18T00:38:07Z","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 are three-dimensional signals characterizing visual appearance and motion dynamics. To learn action patterns, existing methods adopt Convolutional and/or Recurrent Neural Networks (CNNs and RNNs). CNN based methods are effective in learning spatial appearances, but are limited in modeling long-term motion dynamics. RNNs, especially Long Short-Term Memory (LSTM), are able to learn temporal motion dynamics. However, naively applying RNNs to video sequences in a convolutional manner implicitly assumes that motions in videos are stationary across different","authors_text":"Bertram E. Shi, Dit Yan Yeung, Kevin Chen, Kui Jia, Lin Sun, Silvio Savarese","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-13T19:27:34Z","title":"Lattice Long Short-Term Memory for Human Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.03958","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":"sha256:6d4e685305886bffff60d6da540ce6221514d63e925c96e8c257d8e594cf7e1c","target":"record","created_at":"2026-05-18T00:38:07Z","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":"1cb0c7f6c65ef60be857e9ca098be17698df6f002430ee9d51cc4a3cb8cefefa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-13T19:27:34Z","title_canon_sha256":"af124e2dc4648ffd62b4b3db1b59d4fb80f998be86c85dff0f8acfb3168433a9"},"schema_version":"1.0","source":{"id":"1708.03958","kind":"arxiv","version":1}},"canonical_sha256":"e425b1998ccc8474e519f88ddce9371ef0af0b0ebb743aeab3de916f4c90dcb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e425b1998ccc8474e519f88ddce9371ef0af0b0ebb743aeab3de916f4c90dcb9","first_computed_at":"2026-05-18T00:38:07.423684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:07.423684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zqGztYMfkdkRDRy95lejjIQ3PEIKTfcxTFQRCoNjSR0y+SfmJVr+lDYZ4cLMtMWhzlC4qrhPaZmWQU3Eee6aDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:07.424142Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.03958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d4e685305886bffff60d6da540ce6221514d63e925c96e8c257d8e594cf7e1c","sha256:2b014216ff9d3f670c3233db8df5ec52163d1702ab60f9faf448e80431485e43"],"state_sha256":"c5d42617faa6a31a52eb3409f4b44fbe620fa63002c8489282dc459629b2efa5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i6I2/KLqdLwFWw/oSDQUPryFF7Dc1s4i6l5qQogXKITTEK3OpT6+OmqDTteqnRGMGZbBVM/r2i7ziAvDM0kUDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T18:36:54.446177Z","bundle_sha256":"0c45f7f9a1d23efa15b4d6136d7d93a7841168484521077cb4c383895a1ccf92"}}