{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2IHZOKVSS2FKP746A5NR7MEHYG","short_pith_number":"pith:2IHZOKVS","schema_version":"1.0","canonical_sha256":"d20f972ab2968aa7ff9e075b1fb087c182e680733649118b3bb6b9935dfa51c7","source":{"kind":"arxiv","id":"1705.09805","version":3},"attestation_state":"computed","paper":{"title":"PVEs: Position-Velocity Encoders for Unsupervised Learning of Structured State Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jonathan Scholz, Martin Riedmiller, Rico Jonschkowski, Roland Hafner","submitted_at":"2017-05-27T11:17:49Z","abstract_excerpt":"We propose position-velocity encoders (PVEs) which learn---without supervision---to encode images to positions and velocities of task-relevant objects. PVEs encode a single image into a low-dimensional position state and compute the velocity state from finite differences in position. In contrast to autoencoders, position-velocity encoders are not trained by image reconstruction, but by making the position-velocity representation consistent with priors about interacting with the physical world. We applied PVEs to several simulated control tasks from pixels and achieved promising preliminary res"},"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":"1705.09805","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-05-27T11:17:49Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"659138a97635fe1b700c58ab5544c226c46e6060cd0784474c757bd7743df8ed","abstract_canon_sha256":"e0ec420244413c78dab6ca29e39131f1ed9f81b8730899149ef8caca8b695018"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:46.064355Z","signature_b64":"iTL5SriGgabzm/IslLt4ngiqT2go1iWUOoxYZhaY7rH8Cbnsyc7PCosUP2kde4i2Fv+ijshXrawyqNMZRvKaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d20f972ab2968aa7ff9e075b1fb087c182e680733649118b3bb6b9935dfa51c7","last_reissued_at":"2026-05-18T00:39:46.063563Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:46.063563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PVEs: Position-Velocity Encoders for Unsupervised Learning of Structured State Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jonathan Scholz, Martin Riedmiller, Rico Jonschkowski, Roland Hafner","submitted_at":"2017-05-27T11:17:49Z","abstract_excerpt":"We propose position-velocity encoders (PVEs) which learn---without supervision---to encode images to positions and velocities of task-relevant objects. PVEs encode a single image into a low-dimensional position state and compute the velocity state from finite differences in position. In contrast to autoencoders, position-velocity encoders are not trained by image reconstruction, but by making the position-velocity representation consistent with priors about interacting with the physical world. We applied PVEs to several simulated control tasks from pixels and achieved promising preliminary res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09805","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1705.09805","created_at":"2026-05-18T00:39:46.063698+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.09805v3","created_at":"2026-05-18T00:39:46.063698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09805","created_at":"2026-05-18T00:39:46.063698+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IHZOKVSS2FK","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IHZOKVSS2FKP746","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IHZOKVS","created_at":"2026-05-18T12:30:55.937587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11951","citing_title":"Supervise Thyself: Examining Self-Supervised Representations in Interactive Environments","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2IHZOKVSS2FKP746A5NR7MEHYG","json":"https://pith.science/pith/2IHZOKVSS2FKP746A5NR7MEHYG.json","graph_json":"https://pith.science/api/pith-number/2IHZOKVSS2FKP746A5NR7MEHYG/graph.json","events_json":"https://pith.science/api/pith-number/2IHZOKVSS2FKP746A5NR7MEHYG/events.json","paper":"https://pith.science/paper/2IHZOKVS"},"agent_actions":{"view_html":"https://pith.science/pith/2IHZOKVSS2FKP746A5NR7MEHYG","download_json":"https://pith.science/pith/2IHZOKVSS2FKP746A5NR7MEHYG.json","view_paper":"https://pith.science/paper/2IHZOKVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.09805&json=true","fetch_graph":"https://pith.science/api/pith-number/2IHZOKVSS2FKP746A5NR7MEHYG/graph.json","fetch_events":"https://pith.science/api/pith-number/2IHZOKVSS2FKP746A5NR7MEHYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IHZOKVSS2FKP746A5NR7MEHYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IHZOKVSS2FKP746A5NR7MEHYG/action/storage_attestation","attest_author":"https://pith.science/pith/2IHZOKVSS2FKP746A5NR7MEHYG/action/author_attestation","sign_citation":"https://pith.science/pith/2IHZOKVSS2FKP746A5NR7MEHYG/action/citation_signature","submit_replication":"https://pith.science/pith/2IHZOKVSS2FKP746A5NR7MEHYG/action/replication_record"}},"created_at":"2026-05-18T00:39:46.063698+00:00","updated_at":"2026-05-18T00:39:46.063698+00:00"}