{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:M3ZEIEXKKQS6VOSESGKGYWEIN4","short_pith_number":"pith:M3ZEIEXK","canonical_record":{"source":{"id":"1406.2199","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-06-09T14:44:14Z","cross_cats_sorted":[],"title_canon_sha256":"2d0ca9c9242bbd5797320a538090fcb86aeeb22876119404448652b7022fc7ab","abstract_canon_sha256":"dcf0b36b50d7ad95db13c6674ab2ec83e22af8bdea1d79deaece30c06bb259e3"},"schema_version":"1.0"},"canonical_sha256":"66f24412ea5425eaba4491946c58886f39d058d1a029743f2c43bc0d52e805c7","source":{"kind":"arxiv","id":"1406.2199","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.2199","created_at":"2026-05-18T02:37:51Z"},{"alias_kind":"arxiv_version","alias_value":"1406.2199v2","created_at":"2026-05-18T02:37:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.2199","created_at":"2026-05-18T02:37:51Z"},{"alias_kind":"pith_short_12","alias_value":"M3ZEIEXKKQS6","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"M3ZEIEXKKQS6VOSE","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"M3ZEIEXK","created_at":"2026-05-18T12:28:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:M3ZEIEXKKQS6VOSESGKGYWEIN4","target":"record","payload":{"canonical_record":{"source":{"id":"1406.2199","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-06-09T14:44:14Z","cross_cats_sorted":[],"title_canon_sha256":"2d0ca9c9242bbd5797320a538090fcb86aeeb22876119404448652b7022fc7ab","abstract_canon_sha256":"dcf0b36b50d7ad95db13c6674ab2ec83e22af8bdea1d79deaece30c06bb259e3"},"schema_version":"1.0"},"canonical_sha256":"66f24412ea5425eaba4491946c58886f39d058d1a029743f2c43bc0d52e805c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:37:51.702258Z","signature_b64":"u13MyQfHBJy+f368Ra90QKiPQ5H5VhPl1GYT5sgcqPlfPRDA1HkO+2gAbNFRdGj9Ol8M4PIho/xoSj2oEHGfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66f24412ea5425eaba4491946c58886f39d058d1a029743f2c43bc0d52e805c7","last_reissued_at":"2026-05-18T02:37:51.701725Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:37:51.701725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1406.2199","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:37:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H2rXmwzKxLfbPw71FibSb8CnZppoqBgJFzkN887XFktJjLjHMcYBecpRrYPLKGLTfzUxoXumixUI/mj8eZatCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:23:42.748984Z"},"content_sha256":"88e3e2ad11329e20a273b520638bd7cdf622187b6ca8c79b2809eabf4d3384bf","schema_version":"1.0","event_id":"sha256:88e3e2ad11329e20a273b520638bd7cdf622187b6ca8c79b2809eabf4d3384bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:M3ZEIEXKKQS6VOSESGKGYWEIN4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Two-Stream Convolutional Networks for Action Recognition in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Karen Simonyan","submitted_at":"2014-06-09T14:44:14Z","abstract_excerpt":"We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between frames. We also aim to generalise the best performing hand-crafted features within a data-driven learning framework.\n  Our contribution is three-fold. First, we propose a two-stream ConvNet architecture which incorporates spatial and temporal networks. Second, we demonstrate that a ConvNet trained on multi-frame dense optical flow is able to achieve very good "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.2199","kind":"arxiv","version":2},"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":"2026-05-18T02:37:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XmuqtDI3gbF73gKz0e8TCm6a3UMX2MiViZPc8HxxbuzjnPU5aOBb4wijBIqXCNe22fDeUWV1YHqf3vfqFiQ1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:23:42.749611Z"},"content_sha256":"67458fcdd6490f65080a75ddd4742736cec175bd27c1a78e843fc4ef090f512c","schema_version":"1.0","event_id":"sha256:67458fcdd6490f65080a75ddd4742736cec175bd27c1a78e843fc4ef090f512c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M3ZEIEXKKQS6VOSESGKGYWEIN4/bundle.json","state_url":"https://pith.science/pith/M3ZEIEXKKQS6VOSESGKGYWEIN4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M3ZEIEXKKQS6VOSESGKGYWEIN4/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":"2026-05-26T14:23:42Z","links":{"resolver":"https://pith.science/pith/M3ZEIEXKKQS6VOSESGKGYWEIN4","bundle":"https://pith.science/pith/M3ZEIEXKKQS6VOSESGKGYWEIN4/bundle.json","state":"https://pith.science/pith/M3ZEIEXKKQS6VOSESGKGYWEIN4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M3ZEIEXKKQS6VOSESGKGYWEIN4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:M3ZEIEXKKQS6VOSESGKGYWEIN4","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":"dcf0b36b50d7ad95db13c6674ab2ec83e22af8bdea1d79deaece30c06bb259e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-06-09T14:44:14Z","title_canon_sha256":"2d0ca9c9242bbd5797320a538090fcb86aeeb22876119404448652b7022fc7ab"},"schema_version":"1.0","source":{"id":"1406.2199","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.2199","created_at":"2026-05-18T02:37:51Z"},{"alias_kind":"arxiv_version","alias_value":"1406.2199v2","created_at":"2026-05-18T02:37:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.2199","created_at":"2026-05-18T02:37:51Z"},{"alias_kind":"pith_short_12","alias_value":"M3ZEIEXKKQS6","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"M3ZEIEXKKQS6VOSE","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"M3ZEIEXK","created_at":"2026-05-18T12:28:38Z"}],"graph_snapshots":[{"event_id":"sha256:67458fcdd6490f65080a75ddd4742736cec175bd27c1a78e843fc4ef090f512c","target":"graph","created_at":"2026-05-18T02:37:51Z","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":"We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between frames. We also aim to generalise the best performing hand-crafted features within a data-driven learning framework.\n  Our contribution is three-fold. First, we propose a two-stream ConvNet architecture which incorporates spatial and temporal networks. Second, we demonstrate that a ConvNet trained on multi-frame dense optical flow is able to achieve very good ","authors_text":"Andrew Zisserman, Karen Simonyan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-06-09T14:44:14Z","title":"Two-Stream Convolutional Networks for Action Recognition in Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.2199","kind":"arxiv","version":2},"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":"sha256:88e3e2ad11329e20a273b520638bd7cdf622187b6ca8c79b2809eabf4d3384bf","target":"record","created_at":"2026-05-18T02:37:51Z","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":"dcf0b36b50d7ad95db13c6674ab2ec83e22af8bdea1d79deaece30c06bb259e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-06-09T14:44:14Z","title_canon_sha256":"2d0ca9c9242bbd5797320a538090fcb86aeeb22876119404448652b7022fc7ab"},"schema_version":"1.0","source":{"id":"1406.2199","kind":"arxiv","version":2}},"canonical_sha256":"66f24412ea5425eaba4491946c58886f39d058d1a029743f2c43bc0d52e805c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66f24412ea5425eaba4491946c58886f39d058d1a029743f2c43bc0d52e805c7","first_computed_at":"2026-05-18T02:37:51.701725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:37:51.701725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u13MyQfHBJy+f368Ra90QKiPQ5H5VhPl1GYT5sgcqPlfPRDA1HkO+2gAbNFRdGj9Ol8M4PIho/xoSj2oEHGfAA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:37:51.702258Z","signed_message":"canonical_sha256_bytes"},"source_id":"1406.2199","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88e3e2ad11329e20a273b520638bd7cdf622187b6ca8c79b2809eabf4d3384bf","sha256:67458fcdd6490f65080a75ddd4742736cec175bd27c1a78e843fc4ef090f512c"],"state_sha256":"8e201785df16802aeb16909437b429bae30ba4d3c159e6bb9a5e738c7e7dbeef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NbGWp8t2a5VaH7dVSm0Ad5xOeUMmOI3WYkmAadIYTZk9nG78eQB3k6SWRfmbEnNNDe6BekwuqJGk4U3crR6IAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T14:23:42.753064Z","bundle_sha256":"5d712ad84ee9dc1f83a5ba6db2cdab2c12fa6eb97558b3747a92e0197819699f"}}