{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LGLMQ5SCI7WVW6XHT62U5VZU5C","short_pith_number":"pith:LGLMQ5SC","schema_version":"1.0","canonical_sha256":"5996c8764247ed5b7ae79fb54ed734e885f384a52966c4441360368bc55530e1","source":{"kind":"arxiv","id":"1708.05827","version":1},"attestation_state":"computed","paper":{"title":"Visual Forecasting by Imitating Dynamics in Natural Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"De-An Huang, Juan Carlos Niebles, Kuo-Hao Zeng, Min Sun, William B. Shen","submitted_at":"2017-08-19T09:45:52Z","abstract_excerpt":"We introduce a general framework for visual forecasting, which directly imitates visual sequences without additional supervision. As a result, our model can be applied at several semantic levels and does not require any domain knowledge or handcrafted features. We achieve this by formulating visual forecasting as an inverse reinforcement learning (IRL) problem, and directly imitate the dynamics in natural sequences from their raw pixel values. The key challenge is the high-dimensional and continuous state-action space that prohibits the application of previous IRL algorithms. We address this c"},"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":"1708.05827","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-19T09:45:52Z","cross_cats_sorted":[],"title_canon_sha256":"a0d8d8a71b950066a6944cd76c2e3b6685f9e245fe61bb3f241d5ddc9f084be5","abstract_canon_sha256":"232cb3807eba94e5e8d3a268e8917ae1387c411817f0e59268629791331f774b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:44.124474Z","signature_b64":"c7jWa69kx3Muo5COo/ro9SgWD+VgnKtSr80pRbMZSBruHnkaJkR94n50V8HltJ+6gSHGwXgApT4/KL7ysp1iCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5996c8764247ed5b7ae79fb54ed734e885f384a52966c4441360368bc55530e1","last_reissued_at":"2026-05-18T00:37:44.123634Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:44.123634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Forecasting by Imitating Dynamics in Natural Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"De-An Huang, Juan Carlos Niebles, Kuo-Hao Zeng, Min Sun, William B. Shen","submitted_at":"2017-08-19T09:45:52Z","abstract_excerpt":"We introduce a general framework for visual forecasting, which directly imitates visual sequences without additional supervision. As a result, our model can be applied at several semantic levels and does not require any domain knowledge or handcrafted features. We achieve this by formulating visual forecasting as an inverse reinforcement learning (IRL) problem, and directly imitate the dynamics in natural sequences from their raw pixel values. The key challenge is the high-dimensional and continuous state-action space that prohibits the application of previous IRL algorithms. We address this c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05827","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":"1708.05827","created_at":"2026-05-18T00:37:44.123761+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.05827v1","created_at":"2026-05-18T00:37:44.123761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05827","created_at":"2026-05-18T00:37:44.123761+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGLMQ5SCI7WV","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGLMQ5SCI7WVW6XH","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGLMQ5SC","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGLMQ5SCI7WVW6XHT62U5VZU5C","json":"https://pith.science/pith/LGLMQ5SCI7WVW6XHT62U5VZU5C.json","graph_json":"https://pith.science/api/pith-number/LGLMQ5SCI7WVW6XHT62U5VZU5C/graph.json","events_json":"https://pith.science/api/pith-number/LGLMQ5SCI7WVW6XHT62U5VZU5C/events.json","paper":"https://pith.science/paper/LGLMQ5SC"},"agent_actions":{"view_html":"https://pith.science/pith/LGLMQ5SCI7WVW6XHT62U5VZU5C","download_json":"https://pith.science/pith/LGLMQ5SCI7WVW6XHT62U5VZU5C.json","view_paper":"https://pith.science/paper/LGLMQ5SC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.05827&json=true","fetch_graph":"https://pith.science/api/pith-number/LGLMQ5SCI7WVW6XHT62U5VZU5C/graph.json","fetch_events":"https://pith.science/api/pith-number/LGLMQ5SCI7WVW6XHT62U5VZU5C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGLMQ5SCI7WVW6XHT62U5VZU5C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGLMQ5SCI7WVW6XHT62U5VZU5C/action/storage_attestation","attest_author":"https://pith.science/pith/LGLMQ5SCI7WVW6XHT62U5VZU5C/action/author_attestation","sign_citation":"https://pith.science/pith/LGLMQ5SCI7WVW6XHT62U5VZU5C/action/citation_signature","submit_replication":"https://pith.science/pith/LGLMQ5SCI7WVW6XHT62U5VZU5C/action/replication_record"}},"created_at":"2026-05-18T00:37:44.123761+00:00","updated_at":"2026-05-18T00:37:44.123761+00:00"}