{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DDKUGPHAVFNYUSTSJOBV4S6TYA","short_pith_number":"pith:DDKUGPHA","canonical_record":{"source":{"id":"1904.03597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-07T07:27:37Z","cross_cats_sorted":[],"title_canon_sha256":"2cc4ec3c0c5f52778838cbb4eaa0131fa7d2a98232003ef9b84999a94c99fed0","abstract_canon_sha256":"d051abaceccc9de2271c63332f0e97d2134d5d7a1e2d59bffcc96ebf96b95acd"},"schema_version":"1.0"},"canonical_sha256":"18d5433ce0a95b8a4a724b835e4bd3c016874a6d7c454fdf3ee8377b6e9efdf8","source":{"kind":"arxiv","id":"1904.03597","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03597","created_at":"2026-05-17T23:49:12Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03597v1","created_at":"2026-05-17T23:49:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03597","created_at":"2026-05-17T23:49:12Z"},{"alias_kind":"pith_short_12","alias_value":"DDKUGPHAVFNY","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DDKUGPHAVFNYUSTS","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DDKUGPHA","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DDKUGPHAVFNYUSTSJOBV4S6TYA","target":"record","payload":{"canonical_record":{"source":{"id":"1904.03597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-07T07:27:37Z","cross_cats_sorted":[],"title_canon_sha256":"2cc4ec3c0c5f52778838cbb4eaa0131fa7d2a98232003ef9b84999a94c99fed0","abstract_canon_sha256":"d051abaceccc9de2271c63332f0e97d2134d5d7a1e2d59bffcc96ebf96b95acd"},"schema_version":"1.0"},"canonical_sha256":"18d5433ce0a95b8a4a724b835e4bd3c016874a6d7c454fdf3ee8377b6e9efdf8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:12.860585Z","signature_b64":"smUadI57Oz3bfQXrduDMGPOfOMdLHBooAcDBW6U+1POXHJ0n/F3/tg+kB9LLGksPKq3lrazyAn7j44/zbbRGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18d5433ce0a95b8a4a724b835e4bd3c016874a6d7c454fdf3ee8377b6e9efdf8","last_reissued_at":"2026-05-17T23:49:12.859944Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:12.859944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.03597","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":"2026-05-17T23:49:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"roCzKrIOk87iwIhBgl+5DWE3jt+8JZooRjJX5iqlpFiVTsasmMW2Q/zGj/UUIwARMVjqp/DxB1K7BpCLEzgcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T00:18:50.868428Z"},"content_sha256":"a586d6ce1de2082622a9fc86215a5001f1e8ebbc38a7b3a1754581fe4572826b","schema_version":"1.0","event_id":"sha256:a586d6ce1de2082622a9fc86215a5001f1e8ebbc38a7b3a1754581fe4572826b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DDKUGPHAVFNYUSTSJOBV4S6TYA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbo Jiao, Jiangliu Wang, Linchao Bao, Shengfeng He, Wei Liu, Yunhui Liu","submitted_at":"2019-04-07T07:27:37Z","abstract_excerpt":"We address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a frame-by-frame basis, which are not applicable to many video analytic tasks where spatio-temporal features are prevailing. In this paper we propose a novel self-supervised approach to learn spatio-temporal features for video representation. Inspired by the success of two-stream approaches in video classification, we propose to learn visual features by regressing both mot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03597","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":"2026-05-17T23:49:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OmwMb7d20VsFxRJdmECBchAmH5mj75fyOVomng1csdwJt6Q4vjIomR9LCm54tl+zXrZeU4cVoDZTJyTlYcS3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T00:18:50.869115Z"},"content_sha256":"ac91a484ca0e28f50f9f6462231414a14558defa85c71d568ad1746afd34cbe6","schema_version":"1.0","event_id":"sha256:ac91a484ca0e28f50f9f6462231414a14558defa85c71d568ad1746afd34cbe6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA/bundle.json","state_url":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA/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":"2026-05-25T00:18:50Z","links":{"resolver":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA","bundle":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA/bundle.json","state":"https://pith.science/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DDKUGPHAVFNYUSTSJOBV4S6TYA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DDKUGPHAVFNYUSTSJOBV4S6TYA","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":"d051abaceccc9de2271c63332f0e97d2134d5d7a1e2d59bffcc96ebf96b95acd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-07T07:27:37Z","title_canon_sha256":"2cc4ec3c0c5f52778838cbb4eaa0131fa7d2a98232003ef9b84999a94c99fed0"},"schema_version":"1.0","source":{"id":"1904.03597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03597","created_at":"2026-05-17T23:49:12Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03597v1","created_at":"2026-05-17T23:49:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03597","created_at":"2026-05-17T23:49:12Z"},{"alias_kind":"pith_short_12","alias_value":"DDKUGPHAVFNY","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DDKUGPHAVFNYUSTS","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DDKUGPHA","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:ac91a484ca0e28f50f9f6462231414a14558defa85c71d568ad1746afd34cbe6","target":"graph","created_at":"2026-05-17T23:49:12Z","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 address the problem of video representation learning without human-annotated labels. While previous efforts address the problem by designing novel self-supervised tasks using video data, the learned features are merely on a frame-by-frame basis, which are not applicable to many video analytic tasks where spatio-temporal features are prevailing. In this paper we propose a novel self-supervised approach to learn spatio-temporal features for video representation. Inspired by the success of two-stream approaches in video classification, we propose to learn visual features by regressing both mot","authors_text":"Jianbo Jiao, Jiangliu Wang, Linchao Bao, Shengfeng He, Wei Liu, Yunhui Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-07T07:27:37Z","title":"Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03597","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:a586d6ce1de2082622a9fc86215a5001f1e8ebbc38a7b3a1754581fe4572826b","target":"record","created_at":"2026-05-17T23:49:12Z","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":"d051abaceccc9de2271c63332f0e97d2134d5d7a1e2d59bffcc96ebf96b95acd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-07T07:27:37Z","title_canon_sha256":"2cc4ec3c0c5f52778838cbb4eaa0131fa7d2a98232003ef9b84999a94c99fed0"},"schema_version":"1.0","source":{"id":"1904.03597","kind":"arxiv","version":1}},"canonical_sha256":"18d5433ce0a95b8a4a724b835e4bd3c016874a6d7c454fdf3ee8377b6e9efdf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18d5433ce0a95b8a4a724b835e4bd3c016874a6d7c454fdf3ee8377b6e9efdf8","first_computed_at":"2026-05-17T23:49:12.859944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:12.859944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"smUadI57Oz3bfQXrduDMGPOfOMdLHBooAcDBW6U+1POXHJ0n/F3/tg+kB9LLGksPKq3lrazyAn7j44/zbbRGDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:12.860585Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.03597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a586d6ce1de2082622a9fc86215a5001f1e8ebbc38a7b3a1754581fe4572826b","sha256:ac91a484ca0e28f50f9f6462231414a14558defa85c71d568ad1746afd34cbe6"],"state_sha256":"e059945a12b5437314a1a819260f6dd70f7eab1efaaa1e67171ef4be9caf5715"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GwhfWlI1QWhz9QD4jjjDNFMKD8TE0dzS50qWNzOIhQG2GSVmWM95MNkI9tSydG4V9n4MxthQVzLdboLyZ8AwCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T00:18:50.872301Z","bundle_sha256":"01069ad449d7f302d02d87348ecff516737ba89537c2f8beeaa0a26124296437"}}