{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:CJC5Y7CDJMEFXVCLEIKAKTA35N","short_pith_number":"pith:CJC5Y7CD","canonical_record":{"source":{"id":"1704.03615","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-12T04:20:35Z","cross_cats_sorted":[],"title_canon_sha256":"676a6c140ab7d2b82e94d1bfda31ebbd84a8f29c4d8f6644aac7d33bfc5f9915","abstract_canon_sha256":"d49169e6234677b6fe50481ef4e5733114b9cd51568bd8e98a19de1368661795"},"schema_version":"1.0"},"canonical_sha256":"1245dc7c434b085bd44b2214054c1beb539d94bab7249d907e2667c6ee06432f","source":{"kind":"arxiv","id":"1704.03615","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.03615","created_at":"2026-05-18T00:28:15Z"},{"alias_kind":"arxiv_version","alias_value":"1704.03615v2","created_at":"2026-05-18T00:28:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03615","created_at":"2026-05-18T00:28:15Z"},{"alias_kind":"pith_short_12","alias_value":"CJC5Y7CDJMEF","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CJC5Y7CDJMEFXVCL","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CJC5Y7CD","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:CJC5Y7CDJMEFXVCLEIKAKTA35N","target":"record","payload":{"canonical_record":{"source":{"id":"1704.03615","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-12T04:20:35Z","cross_cats_sorted":[],"title_canon_sha256":"676a6c140ab7d2b82e94d1bfda31ebbd84a8f29c4d8f6644aac7d33bfc5f9915","abstract_canon_sha256":"d49169e6234677b6fe50481ef4e5733114b9cd51568bd8e98a19de1368661795"},"schema_version":"1.0"},"canonical_sha256":"1245dc7c434b085bd44b2214054c1beb539d94bab7249d907e2667c6ee06432f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:15.986485Z","signature_b64":"CmFuWlwn3Jc8oqDfJWpWfbRQVVfl0L+OyMvfNTcbEuZWyXw5qPVrjQHxYuyQqt/gvtHfBh3YrJMIh0lGCVvyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1245dc7c434b085bd44b2214054c1beb539d94bab7249d907e2667c6ee06432f","last_reissued_at":"2026-05-18T00:28:15.985838Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:15.985838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.03615","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":"2026-05-18T00:28:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mbr4ZK/nCNOc+SI1rPjw5628bUGzbV6egRdE3VCELPHtVqoPsMr7he5oC52zSVEcNR2kHvoBZNRms14zJbh9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T20:56:40.103948Z"},"content_sha256":"cef97b549aa8737b0882ee186a855c6f51e5575fa21d02dc240d7cbb1e765215","schema_version":"1.0","event_id":"sha256:cef97b549aa8737b0882ee186a855c6f51e5575fa21d02dc240d7cbb1e765215"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:CJC5Y7CDJMEFXVCLEIKAKTA35N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predictive-Corrective Networks for Action Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achal Dave, Deva Ramanan, Olga Russakovsky","submitted_at":"2017-04-12T04:20:35Z","abstract_excerpt":"While deep feature learning has revolutionized techniques for static-image understanding, the same does not quite hold for video processing. Architectures and optimization techniques used for video are largely based off those for static images, potentially underutilizing rich video information. In this work, we rethink both the underlying network architecture and the stochastic learning paradigm for temporal data. To do so, we draw inspiration from classic theory on linear dynamic systems for modeling time series. By extending such models to include nonlinear mappings, we derive a series of no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03615","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":"2026-05-18T00:28:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4GEgSxhsxQg+CzHFSJ59HnfmdRXXWSemn79D44nhTnMBsWTacnqb7sem/55/+Dr/Qm72DB4uF+n6FkRYuGj3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T20:56:40.104284Z"},"content_sha256":"f353a02cecb471b8fffcf5309c9eaa65b972510f37fe7d4000305268267846b8","schema_version":"1.0","event_id":"sha256:f353a02cecb471b8fffcf5309c9eaa65b972510f37fe7d4000305268267846b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CJC5Y7CDJMEFXVCLEIKAKTA35N/bundle.json","state_url":"https://pith.science/pith/CJC5Y7CDJMEFXVCLEIKAKTA35N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CJC5Y7CDJMEFXVCLEIKAKTA35N/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":"2026-07-21T20:56:40Z","links":{"resolver":"https://pith.science/pith/CJC5Y7CDJMEFXVCLEIKAKTA35N","bundle":"https://pith.science/pith/CJC5Y7CDJMEFXVCLEIKAKTA35N/bundle.json","state":"https://pith.science/pith/CJC5Y7CDJMEFXVCLEIKAKTA35N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CJC5Y7CDJMEFXVCLEIKAKTA35N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:CJC5Y7CDJMEFXVCLEIKAKTA35N","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":"d49169e6234677b6fe50481ef4e5733114b9cd51568bd8e98a19de1368661795","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-12T04:20:35Z","title_canon_sha256":"676a6c140ab7d2b82e94d1bfda31ebbd84a8f29c4d8f6644aac7d33bfc5f9915"},"schema_version":"1.0","source":{"id":"1704.03615","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.03615","created_at":"2026-05-18T00:28:15Z"},{"alias_kind":"arxiv_version","alias_value":"1704.03615v2","created_at":"2026-05-18T00:28:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03615","created_at":"2026-05-18T00:28:15Z"},{"alias_kind":"pith_short_12","alias_value":"CJC5Y7CDJMEF","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CJC5Y7CDJMEFXVCL","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CJC5Y7CD","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:f353a02cecb471b8fffcf5309c9eaa65b972510f37fe7d4000305268267846b8","target":"graph","created_at":"2026-05-18T00:28:15Z","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":"While deep feature learning has revolutionized techniques for static-image understanding, the same does not quite hold for video processing. Architectures and optimization techniques used for video are largely based off those for static images, potentially underutilizing rich video information. In this work, we rethink both the underlying network architecture and the stochastic learning paradigm for temporal data. To do so, we draw inspiration from classic theory on linear dynamic systems for modeling time series. By extending such models to include nonlinear mappings, we derive a series of no","authors_text":"Achal Dave, Deva Ramanan, Olga Russakovsky","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-12T04:20:35Z","title":"Predictive-Corrective Networks for Action Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03615","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:cef97b549aa8737b0882ee186a855c6f51e5575fa21d02dc240d7cbb1e765215","target":"record","created_at":"2026-05-18T00:28:15Z","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":"d49169e6234677b6fe50481ef4e5733114b9cd51568bd8e98a19de1368661795","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-12T04:20:35Z","title_canon_sha256":"676a6c140ab7d2b82e94d1bfda31ebbd84a8f29c4d8f6644aac7d33bfc5f9915"},"schema_version":"1.0","source":{"id":"1704.03615","kind":"arxiv","version":2}},"canonical_sha256":"1245dc7c434b085bd44b2214054c1beb539d94bab7249d907e2667c6ee06432f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1245dc7c434b085bd44b2214054c1beb539d94bab7249d907e2667c6ee06432f","first_computed_at":"2026-05-18T00:28:15.985838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:15.985838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CmFuWlwn3Jc8oqDfJWpWfbRQVVfl0L+OyMvfNTcbEuZWyXw5qPVrjQHxYuyQqt/gvtHfBh3YrJMIh0lGCVvyCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:15.986485Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.03615","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cef97b549aa8737b0882ee186a855c6f51e5575fa21d02dc240d7cbb1e765215","sha256:f353a02cecb471b8fffcf5309c9eaa65b972510f37fe7d4000305268267846b8"],"state_sha256":"0f4cf3b1fdc3f7f63232888e4c8bea8dc9228068eb7b2199c81e893e5997c176"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7jLby+Uzhb8u5OdOOaQYD1h6+ef2FC80eMvLb6YeAeP5gYYtYvOQTMctLs7aAn4dsZbCBnK9yt38ZqdXOq0zCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T20:56:40.107054Z","bundle_sha256":"2c9631eb6daa380e6da991d2ea16f8f9e29aa9c3ddbc9f812d32efe7724e8f00"}}