{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:ML46YBB77EKNZIMP5W7PUYJ5EB","short_pith_number":"pith:ML46YBB7","canonical_record":{"source":{"id":"1509.01602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-04T20:48:23Z","cross_cats_sorted":[],"title_canon_sha256":"d591b20f894d222cc1bc1064885d5b74b3ac3f6c50018a89b4911f1296fc4c16","abstract_canon_sha256":"47520ec23f3ebea7781be075d25295c4faa6f5025c571f46b491baa1e5c791b0"},"schema_version":"1.0"},"canonical_sha256":"62f9ec043ff914dca18fedbefa613d20595b46031931ae76b3d450650679e352","source":{"kind":"arxiv","id":"1509.01602","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.01602","created_at":"2026-05-18T01:33:51Z"},{"alias_kind":"arxiv_version","alias_value":"1509.01602v1","created_at":"2026-05-18T01:33:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.01602","created_at":"2026-05-18T01:33:51Z"},{"alias_kind":"pith_short_12","alias_value":"ML46YBB77EKN","created_at":"2026-05-18T12:29:32Z"},{"alias_kind":"pith_short_16","alias_value":"ML46YBB77EKNZIMP","created_at":"2026-05-18T12:29:32Z"},{"alias_kind":"pith_short_8","alias_value":"ML46YBB7","created_at":"2026-05-18T12:29:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:ML46YBB77EKNZIMP5W7PUYJ5EB","target":"record","payload":{"canonical_record":{"source":{"id":"1509.01602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-04T20:48:23Z","cross_cats_sorted":[],"title_canon_sha256":"d591b20f894d222cc1bc1064885d5b74b3ac3f6c50018a89b4911f1296fc4c16","abstract_canon_sha256":"47520ec23f3ebea7781be075d25295c4faa6f5025c571f46b491baa1e5c791b0"},"schema_version":"1.0"},"canonical_sha256":"62f9ec043ff914dca18fedbefa613d20595b46031931ae76b3d450650679e352","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:33:51.093964Z","signature_b64":"wC4YlwgMYRaDSgK/Bv6wNBehtox/uy6Nl/9eOEnvm6l8fOFXhi9hAf96SfEU3wx62tyUJ1GsK8f63+NJnDmaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62f9ec043ff914dca18fedbefa613d20595b46031931ae76b3d450650679e352","last_reissued_at":"2026-05-18T01:33:51.093302Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:33:51.093302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1509.01602","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":"2026-05-18T01:33:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SYNzc7XZgEk0lQXE6atV5q1OqlPLlH6IzOjlxQPvo6TKgVEftuOxlDXm8KNCqDSF++doQF5MBg7SWbwIXB0OCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T05:03:49.311012Z"},"content_sha256":"597a03426d7e67ca5afb7a2488599cf29fe003d3c760dc1e2e105b46bc46a6e3","schema_version":"1.0","event_id":"sha256:597a03426d7e67ca5afb7a2488599cf29fe003d3c760dc1e2e105b46bc46a6e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:ML46YBB77EKNZIMP5W7PUYJ5EB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Object Recognition from Short Videos for Robotic Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anelia Angelova, Ivan Bogun, Navdeep Jaitly","submitted_at":"2015-09-04T20:48:23Z","abstract_excerpt":"Deep neural networks have become the primary learning technique for object recognition. Videos, unlike still images, are temporally coherent which makes the application of deep networks non-trivial. Here, we investigate how motion can aid object recognition in short videos. Our approach is based on Long Short-Term Memory (LSTM) deep networks. Unlike previous applications of LSTMs, we implement each gate as a convolution. We show that convolutional-based LSTM models are capable of learning motion dependencies and are able to improve the recognition accuracy when more frames in a sequence are av"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.01602","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":"2026-05-18T01:33:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zS2KBenRshbmLChvEsa2vNJPU1o0lavWPW9kzBVLoqaaJHd1j3BQ85ckMrXPTiwigEvPwViKIej25vODY3yXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T05:03:49.311846Z"},"content_sha256":"4d2a3c48fa6b036033a94b4314c2b4156af272f966345e27d124438b754f51ad","schema_version":"1.0","event_id":"sha256:4d2a3c48fa6b036033a94b4314c2b4156af272f966345e27d124438b754f51ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ML46YBB77EKNZIMP5W7PUYJ5EB/bundle.json","state_url":"https://pith.science/pith/ML46YBB77EKNZIMP5W7PUYJ5EB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ML46YBB77EKNZIMP5W7PUYJ5EB/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":"2026-05-20T05:03:49Z","links":{"resolver":"https://pith.science/pith/ML46YBB77EKNZIMP5W7PUYJ5EB","bundle":"https://pith.science/pith/ML46YBB77EKNZIMP5W7PUYJ5EB/bundle.json","state":"https://pith.science/pith/ML46YBB77EKNZIMP5W7PUYJ5EB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ML46YBB77EKNZIMP5W7PUYJ5EB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:ML46YBB77EKNZIMP5W7PUYJ5EB","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":"47520ec23f3ebea7781be075d25295c4faa6f5025c571f46b491baa1e5c791b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-04T20:48:23Z","title_canon_sha256":"d591b20f894d222cc1bc1064885d5b74b3ac3f6c50018a89b4911f1296fc4c16"},"schema_version":"1.0","source":{"id":"1509.01602","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.01602","created_at":"2026-05-18T01:33:51Z"},{"alias_kind":"arxiv_version","alias_value":"1509.01602v1","created_at":"2026-05-18T01:33:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.01602","created_at":"2026-05-18T01:33:51Z"},{"alias_kind":"pith_short_12","alias_value":"ML46YBB77EKN","created_at":"2026-05-18T12:29:32Z"},{"alias_kind":"pith_short_16","alias_value":"ML46YBB77EKNZIMP","created_at":"2026-05-18T12:29:32Z"},{"alias_kind":"pith_short_8","alias_value":"ML46YBB7","created_at":"2026-05-18T12:29:32Z"}],"graph_snapshots":[{"event_id":"sha256:4d2a3c48fa6b036033a94b4314c2b4156af272f966345e27d124438b754f51ad","target":"graph","created_at":"2026-05-18T01:33:51Z","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":"Deep neural networks have become the primary learning technique for object recognition. Videos, unlike still images, are temporally coherent which makes the application of deep networks non-trivial. Here, we investigate how motion can aid object recognition in short videos. Our approach is based on Long Short-Term Memory (LSTM) deep networks. Unlike previous applications of LSTMs, we implement each gate as a convolution. We show that convolutional-based LSTM models are capable of learning motion dependencies and are able to improve the recognition accuracy when more frames in a sequence are av","authors_text":"Anelia Angelova, Ivan Bogun, Navdeep Jaitly","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-04T20:48:23Z","title":"Object Recognition from Short Videos for Robotic Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.01602","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":"sha256:597a03426d7e67ca5afb7a2488599cf29fe003d3c760dc1e2e105b46bc46a6e3","target":"record","created_at":"2026-05-18T01:33:51Z","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":"47520ec23f3ebea7781be075d25295c4faa6f5025c571f46b491baa1e5c791b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-04T20:48:23Z","title_canon_sha256":"d591b20f894d222cc1bc1064885d5b74b3ac3f6c50018a89b4911f1296fc4c16"},"schema_version":"1.0","source":{"id":"1509.01602","kind":"arxiv","version":1}},"canonical_sha256":"62f9ec043ff914dca18fedbefa613d20595b46031931ae76b3d450650679e352","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62f9ec043ff914dca18fedbefa613d20595b46031931ae76b3d450650679e352","first_computed_at":"2026-05-18T01:33:51.093302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:33:51.093302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wC4YlwgMYRaDSgK/Bv6wNBehtox/uy6Nl/9eOEnvm6l8fOFXhi9hAf96SfEU3wx62tyUJ1GsK8f63+NJnDmaDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:33:51.093964Z","signed_message":"canonical_sha256_bytes"},"source_id":"1509.01602","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:597a03426d7e67ca5afb7a2488599cf29fe003d3c760dc1e2e105b46bc46a6e3","sha256:4d2a3c48fa6b036033a94b4314c2b4156af272f966345e27d124438b754f51ad"],"state_sha256":"d9680b24c9db4471187264f2c5cc554a246987e01420e772c3b75346b8bd141f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3N8uEakgLgk69Cwzu4gV2gcbT4o7JRqotG2qeGTZ7l0tEvyju3yoUiOIRRh/cDrXMITxBnOLFcMpROS4vBEqBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T05:03:49.316659Z","bundle_sha256":"7b3e7e12da4f8403a92a83f30299a19059e10d21c4946d3aff1c414f6ccd280d"}}