{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:EMGA3KYM7WI7HW4NBSCAXMJJ4H","short_pith_number":"pith:EMGA3KYM","canonical_record":{"source":{"id":"1903.11412","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T13:24:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cd6ad4d23d1d9c072be85afbb49f297b1e9b3a769a4b9e4bf34eeb0efcfe364e","abstract_canon_sha256":"fcba3728059f9dac32d3f3663dbeb5a73e0147817be955af2597cd3cb67ae3b0"},"schema_version":"1.0"},"canonical_sha256":"230c0dab0cfd91f3db8d0c840bb129e1d0759d519edd134c3fb7f98c38ac0921","source":{"kind":"arxiv","id":"1903.11412","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.11412","created_at":"2026-05-17T23:47:48Z"},{"alias_kind":"arxiv_version","alias_value":"1903.11412v3","created_at":"2026-05-17T23:47:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.11412","created_at":"2026-05-17T23:47:48Z"},{"alias_kind":"pith_short_12","alias_value":"EMGA3KYM7WI7","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"EMGA3KYM7WI7HW4N","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"EMGA3KYM","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:EMGA3KYM7WI7HW4NBSCAXMJJ4H","target":"record","payload":{"canonical_record":{"source":{"id":"1903.11412","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T13:24:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cd6ad4d23d1d9c072be85afbb49f297b1e9b3a769a4b9e4bf34eeb0efcfe364e","abstract_canon_sha256":"fcba3728059f9dac32d3f3663dbeb5a73e0147817be955af2597cd3cb67ae3b0"},"schema_version":"1.0"},"canonical_sha256":"230c0dab0cfd91f3db8d0c840bb129e1d0759d519edd134c3fb7f98c38ac0921","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:48.218397Z","signature_b64":"tnRQW3AYlQ++TWvXJaY4gwKGxJMqFsXE7Jiwn28ezpn4qIe5PMPDGDpXQ6Ab19MkiGvHo4klHeO9NQ3j9NJkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"230c0dab0cfd91f3db8d0c840bb129e1d0759d519edd134c3fb7f98c38ac0921","last_reissued_at":"2026-05-17T23:47:48.217793Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:48.217793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.11412","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BibfvgxBtNEei8i2u6KvBOL7jAcFc2Ia6tyw1KliRh/bdCozlQ3xgeGpkkPtt6EDey+tT1kIr3EJNMEO75fQCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:46:21.887830Z"},"content_sha256":"d9c1955f2f831303c057628484663c5a5090c0d7cd18a629f4a736baad301afb","schema_version":"1.0","event_id":"sha256:d9c1955f2f831303c057628484663c5a5090c0d7cd18a629f4a736baad301afb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:EMGA3KYM7WI7HW4NBSCAXMJJ4H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Supervised Learning via Conditional Motion Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Dahua Lin, Xiaohang Zhan, Xingang Pan, Ziwei Liu","submitted_at":"2019-03-27T13:24:46Z","abstract_excerpt":"Intelligent agent naturally learns from motion. Various self-supervised algorithms have leveraged motion cues to learn effective visual representations. The hurdle here is that motion is both ambiguous and complex, rendering previous works either suffer from degraded learning efficacy, or resort to strong assumptions on object motions. In this work, we design a new learning-from-motion paradigm to bridge these gaps. Instead of explicitly modeling the motion probabilities, we design the pretext task as a conditional motion propagation problem. Given an input image and several sparse flow guidan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.11412","kind":"arxiv","version":3},"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":"2026-05-17T23:47:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"90syOFaySkcVzImqpV3LogOZjl2/wJrNilPObN1OMw9z77jdcchWFd3BqxabBY2KqDAgH3ocga4WkW2rBfEjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:46:21.888491Z"},"content_sha256":"45c3c05743b7c30f6518dcebb6728e11528912a03828a47aa72aef939859e14a","schema_version":"1.0","event_id":"sha256:45c3c05743b7c30f6518dcebb6728e11528912a03828a47aa72aef939859e14a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EMGA3KYM7WI7HW4NBSCAXMJJ4H/bundle.json","state_url":"https://pith.science/pith/EMGA3KYM7WI7HW4NBSCAXMJJ4H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EMGA3KYM7WI7HW4NBSCAXMJJ4H/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":"2026-05-25T18:46:21Z","links":{"resolver":"https://pith.science/pith/EMGA3KYM7WI7HW4NBSCAXMJJ4H","bundle":"https://pith.science/pith/EMGA3KYM7WI7HW4NBSCAXMJJ4H/bundle.json","state":"https://pith.science/pith/EMGA3KYM7WI7HW4NBSCAXMJJ4H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EMGA3KYM7WI7HW4NBSCAXMJJ4H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EMGA3KYM7WI7HW4NBSCAXMJJ4H","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":"fcba3728059f9dac32d3f3663dbeb5a73e0147817be955af2597cd3cb67ae3b0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T13:24:46Z","title_canon_sha256":"cd6ad4d23d1d9c072be85afbb49f297b1e9b3a769a4b9e4bf34eeb0efcfe364e"},"schema_version":"1.0","source":{"id":"1903.11412","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.11412","created_at":"2026-05-17T23:47:48Z"},{"alias_kind":"arxiv_version","alias_value":"1903.11412v3","created_at":"2026-05-17T23:47:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.11412","created_at":"2026-05-17T23:47:48Z"},{"alias_kind":"pith_short_12","alias_value":"EMGA3KYM7WI7","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"EMGA3KYM7WI7HW4N","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"EMGA3KYM","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:45c3c05743b7c30f6518dcebb6728e11528912a03828a47aa72aef939859e14a","target":"graph","created_at":"2026-05-17T23:47:48Z","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":"Intelligent agent naturally learns from motion. Various self-supervised algorithms have leveraged motion cues to learn effective visual representations. The hurdle here is that motion is both ambiguous and complex, rendering previous works either suffer from degraded learning efficacy, or resort to strong assumptions on object motions. In this work, we design a new learning-from-motion paradigm to bridge these gaps. Instead of explicitly modeling the motion probabilities, we design the pretext task as a conditional motion propagation problem. Given an input image and several sparse flow guidan","authors_text":"Chen Change Loy, Dahua Lin, Xiaohang Zhan, Xingang Pan, Ziwei Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T13:24:46Z","title":"Self-Supervised Learning via Conditional Motion Propagation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.11412","kind":"arxiv","version":3},"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:d9c1955f2f831303c057628484663c5a5090c0d7cd18a629f4a736baad301afb","target":"record","created_at":"2026-05-17T23:47:48Z","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":"fcba3728059f9dac32d3f3663dbeb5a73e0147817be955af2597cd3cb67ae3b0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T13:24:46Z","title_canon_sha256":"cd6ad4d23d1d9c072be85afbb49f297b1e9b3a769a4b9e4bf34eeb0efcfe364e"},"schema_version":"1.0","source":{"id":"1903.11412","kind":"arxiv","version":3}},"canonical_sha256":"230c0dab0cfd91f3db8d0c840bb129e1d0759d519edd134c3fb7f98c38ac0921","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"230c0dab0cfd91f3db8d0c840bb129e1d0759d519edd134c3fb7f98c38ac0921","first_computed_at":"2026-05-17T23:47:48.217793Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:48.217793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tnRQW3AYlQ++TWvXJaY4gwKGxJMqFsXE7Jiwn28ezpn4qIe5PMPDGDpXQ6Ab19MkiGvHo4klHeO9NQ3j9NJkCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:48.218397Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.11412","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9c1955f2f831303c057628484663c5a5090c0d7cd18a629f4a736baad301afb","sha256:45c3c05743b7c30f6518dcebb6728e11528912a03828a47aa72aef939859e14a"],"state_sha256":"903642e85495fa20684ac7a8d0e45b5c159b2f38bb3e57819d48a7c4369894e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n5D8O+tjAHIma2F4Gn0kSo1PYEFTPLwWu9FRDhdDifYDjt/ySa1eg3xKVTXA7Kj+Uv71x1mz3EuXLYAQra5cDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:46:21.891913Z","bundle_sha256":"1215418e87fa1e1785fa3f2f7e36d102665a369230f29984926d5bf5a7c6903d"}}