{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:MIKPHBH5SLI5U36EXFKKFJLI7H","short_pith_number":"pith:MIKPHBH5","canonical_record":{"source":{"id":"1412.0767","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-02T03:05:54Z","cross_cats_sorted":[],"title_canon_sha256":"10b1eaadb46cd971a63a6349fdfbee518c66dffe32135cecf91b42bf0ca7e5d3","abstract_canon_sha256":"f5869575a34ba0b1e1a124ebffbb33053e607a94d598dc8b537d28ddc87c8815"},"schema_version":"1.0"},"canonical_sha256":"6214f384fd92d1da6fc4b954a2a568f9ecdbc9cd59c923b472865588b65b0cf0","source":{"kind":"arxiv","id":"1412.0767","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.0767","created_at":"2026-05-18T01:30:51Z"},{"alias_kind":"arxiv_version","alias_value":"1412.0767v4","created_at":"2026-05-18T01:30:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.0767","created_at":"2026-05-18T01:30:51Z"},{"alias_kind":"pith_short_12","alias_value":"MIKPHBH5SLI5","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"MIKPHBH5SLI5U36E","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"MIKPHBH5","created_at":"2026-05-18T12:28:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:MIKPHBH5SLI5U36EXFKKFJLI7H","target":"record","payload":{"canonical_record":{"source":{"id":"1412.0767","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-02T03:05:54Z","cross_cats_sorted":[],"title_canon_sha256":"10b1eaadb46cd971a63a6349fdfbee518c66dffe32135cecf91b42bf0ca7e5d3","abstract_canon_sha256":"f5869575a34ba0b1e1a124ebffbb33053e607a94d598dc8b537d28ddc87c8815"},"schema_version":"1.0"},"canonical_sha256":"6214f384fd92d1da6fc4b954a2a568f9ecdbc9cd59c923b472865588b65b0cf0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:30:51.155300Z","signature_b64":"my+bX7xNathZ1oa6Lgl9Hth6xq3w20e6zTo0KqMmUZkN+c/OFwqLnShAE+B8674Ded9xF7G7DPr5lCjZlKqLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6214f384fd92d1da6fc4b954a2a568f9ecdbc9cd59c923b472865588b65b0cf0","last_reissued_at":"2026-05-18T01:30:51.154846Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:30:51.154846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.0767","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:30:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n2jzAtsW54uXbOmq5Dqt06ICbTXbdBk+5z7NH6slkJf6jL6+sMgW17qNZMsbkxSVhG9VjJ+KdpfrNW9RiPbzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:06:08.131459Z"},"content_sha256":"adbbe12c12626e498ff769909510c97bdd58ef6e5087cdd137be20690c05b274","schema_version":"1.0","event_id":"sha256:adbbe12c12626e498ff769909510c97bdd58ef6e5087cdd137be20690c05b274"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:MIKPHBH5SLI5U36EXFKKFJLI7H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Spatiotemporal Features with 3D Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Du Tran, Lorenzo Torresani, Lubomir Bourdev, Manohar Paluri, Rob Fergus","submitted_at":"2014-12-02T03:05:54Z","abstract_excerpt":"We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets; 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets; and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.0767","kind":"arxiv","version":4},"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":"2026-05-18T01:30:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AeIUz9vGEbFhRBjLU4Sr+PYiIOjHrLsZaSGI+A68y1Hitx6l81P5KsSHJS9nLmdXkmv9WtKuZ2+EhagCfy+ZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:06:08.132000Z"},"content_sha256":"6f9c38bb29f43b3b544b2100b99ba05f281e4241da2bb247d1c8ee89242685a5","schema_version":"1.0","event_id":"sha256:6f9c38bb29f43b3b544b2100b99ba05f281e4241da2bb247d1c8ee89242685a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MIKPHBH5SLI5U36EXFKKFJLI7H/bundle.json","state_url":"https://pith.science/pith/MIKPHBH5SLI5U36EXFKKFJLI7H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MIKPHBH5SLI5U36EXFKKFJLI7H/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":"2026-06-02T21:06:08Z","links":{"resolver":"https://pith.science/pith/MIKPHBH5SLI5U36EXFKKFJLI7H","bundle":"https://pith.science/pith/MIKPHBH5SLI5U36EXFKKFJLI7H/bundle.json","state":"https://pith.science/pith/MIKPHBH5SLI5U36EXFKKFJLI7H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MIKPHBH5SLI5U36EXFKKFJLI7H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:MIKPHBH5SLI5U36EXFKKFJLI7H","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":"f5869575a34ba0b1e1a124ebffbb33053e607a94d598dc8b537d28ddc87c8815","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-02T03:05:54Z","title_canon_sha256":"10b1eaadb46cd971a63a6349fdfbee518c66dffe32135cecf91b42bf0ca7e5d3"},"schema_version":"1.0","source":{"id":"1412.0767","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.0767","created_at":"2026-05-18T01:30:51Z"},{"alias_kind":"arxiv_version","alias_value":"1412.0767v4","created_at":"2026-05-18T01:30:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.0767","created_at":"2026-05-18T01:30:51Z"},{"alias_kind":"pith_short_12","alias_value":"MIKPHBH5SLI5","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"MIKPHBH5SLI5U36E","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"MIKPHBH5","created_at":"2026-05-18T12:28:38Z"}],"graph_snapshots":[{"event_id":"sha256:6f9c38bb29f43b3b544b2100b99ba05f281e4241da2bb247d1c8ee89242685a5","target":"graph","created_at":"2026-05-18T01:30:51Z","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 propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets; 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets; and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different ","authors_text":"Du Tran, Lorenzo Torresani, Lubomir Bourdev, Manohar Paluri, Rob Fergus","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-02T03:05:54Z","title":"Learning Spatiotemporal Features with 3D Convolutional Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.0767","kind":"arxiv","version":4},"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:adbbe12c12626e498ff769909510c97bdd58ef6e5087cdd137be20690c05b274","target":"record","created_at":"2026-05-18T01:30:51Z","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":"f5869575a34ba0b1e1a124ebffbb33053e607a94d598dc8b537d28ddc87c8815","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-02T03:05:54Z","title_canon_sha256":"10b1eaadb46cd971a63a6349fdfbee518c66dffe32135cecf91b42bf0ca7e5d3"},"schema_version":"1.0","source":{"id":"1412.0767","kind":"arxiv","version":4}},"canonical_sha256":"6214f384fd92d1da6fc4b954a2a568f9ecdbc9cd59c923b472865588b65b0cf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6214f384fd92d1da6fc4b954a2a568f9ecdbc9cd59c923b472865588b65b0cf0","first_computed_at":"2026-05-18T01:30:51.154846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:30:51.154846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"my+bX7xNathZ1oa6Lgl9Hth6xq3w20e6zTo0KqMmUZkN+c/OFwqLnShAE+B8674Ded9xF7G7DPr5lCjZlKqLCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:30:51.155300Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.0767","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adbbe12c12626e498ff769909510c97bdd58ef6e5087cdd137be20690c05b274","sha256:6f9c38bb29f43b3b544b2100b99ba05f281e4241da2bb247d1c8ee89242685a5"],"state_sha256":"a94639021cddf25ed5673a30711236ed19d49a5e1a571338808af37b6c1afb64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BnxQ/IeOd7JBlh6N2jTn12Q37kWADtbFY/TSGV8Pfc4m0JJNTLi2nqpvgjQnJ6fhQ/jd4tivqP/odmWmRKY8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T21:06:08.134566Z","bundle_sha256":"af9a9240da220b8634b3b6cf03e292abc179b1146b18da2c9bc8a72caba82124"}}