{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:YQ3SGSIZ2DNXU2W7BKEPDSBJO5","short_pith_number":"pith:YQ3SGSIZ","schema_version":"1.0","canonical_sha256":"c437234919d0db7a6adf0a88f1c829777d5442aff34fb3814c422868356a67a2","source":{"kind":"arxiv","id":"1705.02082","version":1},"attestation_state":"computed","paper":{"title":"Motion Prediction Under Multimodality with Conditional Stochastic Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Alemi, Jonathan Huang, Katerina Fragkiadaki, Rahul Sukthankar, Sudheendra Vijayanarasimhan, Susanna Ricco","submitted_at":"2017-05-05T04:19:40Z","abstract_excerpt":"Given a visual history, multiple future outcomes for a video scene are equally probable, in other words, the distribution of future outcomes has multiple modes. Multimodality is notoriously hard to handle by standard regressors or classifiers: the former regress to the mean and the latter discretize a continuous high dimensional output space. In this work, we present stochastic neural network architectures that handle such multimodality through stochasticity: future trajectories of objects, body joints or frames are represented as deep, non-linear transformations of random (as opposed to deter"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1705.02082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-05T04:19:40Z","cross_cats_sorted":[],"title_canon_sha256":"0642275244de0511ef9055da60a933ac35df9765a50a85f7d7886d4ca2107737","abstract_canon_sha256":"af0b87262176d924162dd43053a4e4620d17cbb54bc60dc6de43920f457dfaca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:00.675693Z","signature_b64":"dOmnrIbsJ/pGzyJlsRd9RKiOJ+38l+bm2bNX3IPZs0mL0pFSO33bS/v9jKrpCR/5I2w+h304TvwKxpdadTV6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c437234919d0db7a6adf0a88f1c829777d5442aff34fb3814c422868356a67a2","last_reissued_at":"2026-05-18T00:45:00.675241Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:00.675241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Motion Prediction Under Multimodality with Conditional Stochastic Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Alemi, Jonathan Huang, Katerina Fragkiadaki, Rahul Sukthankar, Sudheendra Vijayanarasimhan, Susanna Ricco","submitted_at":"2017-05-05T04:19:40Z","abstract_excerpt":"Given a visual history, multiple future outcomes for a video scene are equally probable, in other words, the distribution of future outcomes has multiple modes. Multimodality is notoriously hard to handle by standard regressors or classifiers: the former regress to the mean and the latter discretize a continuous high dimensional output space. In this work, we present stochastic neural network architectures that handle such multimodality through stochasticity: future trajectories of objects, body joints or frames are represented as deep, non-linear transformations of random (as opposed to deter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.02082","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1705.02082","created_at":"2026-05-18T00:45:00.675307+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.02082v1","created_at":"2026-05-18T00:45:00.675307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.02082","created_at":"2026-05-18T00:45:00.675307+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQ3SGSIZ2DNX","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQ3SGSIZ2DNXU2W7","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQ3SGSIZ","created_at":"2026-05-18T12:31:56.362134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.08522","citing_title":"Compositional Video Prediction","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQ3SGSIZ2DNXU2W7BKEPDSBJO5","json":"https://pith.science/pith/YQ3SGSIZ2DNXU2W7BKEPDSBJO5.json","graph_json":"https://pith.science/api/pith-number/YQ3SGSIZ2DNXU2W7BKEPDSBJO5/graph.json","events_json":"https://pith.science/api/pith-number/YQ3SGSIZ2DNXU2W7BKEPDSBJO5/events.json","paper":"https://pith.science/paper/YQ3SGSIZ"},"agent_actions":{"view_html":"https://pith.science/pith/YQ3SGSIZ2DNXU2W7BKEPDSBJO5","download_json":"https://pith.science/pith/YQ3SGSIZ2DNXU2W7BKEPDSBJO5.json","view_paper":"https://pith.science/paper/YQ3SGSIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.02082&json=true","fetch_graph":"https://pith.science/api/pith-number/YQ3SGSIZ2DNXU2W7BKEPDSBJO5/graph.json","fetch_events":"https://pith.science/api/pith-number/YQ3SGSIZ2DNXU2W7BKEPDSBJO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQ3SGSIZ2DNXU2W7BKEPDSBJO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQ3SGSIZ2DNXU2W7BKEPDSBJO5/action/storage_attestation","attest_author":"https://pith.science/pith/YQ3SGSIZ2DNXU2W7BKEPDSBJO5/action/author_attestation","sign_citation":"https://pith.science/pith/YQ3SGSIZ2DNXU2W7BKEPDSBJO5/action/citation_signature","submit_replication":"https://pith.science/pith/YQ3SGSIZ2DNXU2W7BKEPDSBJO5/action/replication_record"}},"created_at":"2026-05-18T00:45:00.675307+00:00","updated_at":"2026-05-18T00:45:00.675307+00:00"}