{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:AWQI5QYTUI7ZGOQJ3VYQDOB7ON","short_pith_number":"pith:AWQI5QYT","schema_version":"1.0","canonical_sha256":"05a08ec313a23f933a09dd7101b83f736d34e75a3fadbbebd67333804e05b7ed","source":{"kind":"arxiv","id":"1603.01312","version":1},"attestation_state":"computed","paper":{"title":"Learning Physical Intuition of Block Towers by Example","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam Lerer, Rob Fergus, Sam Gross","submitted_at":"2016-03-03T22:59:35Z","abstract_excerpt":"Wooden blocks are a common toy for infants, allowing them to develop motor skills and gain intuition about the physical behavior of the world. In this paper, we explore the ability of deep feed-forward models to learn such intuitive physics. Using a 3D game engine, we create small towers of wooden blocks whose stability is randomized and render them collapsing (or remaining upright). This data allows us to train large convolutional network models which can accurately predict the outcome, as well as estimating the block trajectories. The models are also able to generalize in two important ways:"},"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":"1603.01312","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-03-03T22:59:35Z","cross_cats_sorted":[],"title_canon_sha256":"b21b6f17a5102601dba11b5a4c342c9e7f354febd0916b2fe14a251a47d33bbd","abstract_canon_sha256":"183580c59548dbb1ae2de089b61822928a1ff086ea6269b60dccb712bd07ff3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:37.992176Z","signature_b64":"x/5pJITAqBaUhMVw4igghwINWB9zWvGCTQjjWvGy+E9GL7e9p0ADccKAS0JpmmCTK1t4dsmHGnmneprxBwAJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05a08ec313a23f933a09dd7101b83f736d34e75a3fadbbebd67333804e05b7ed","last_reissued_at":"2026-05-18T01:19:37.991607Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:37.991607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Physical Intuition of Block Towers by Example","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam Lerer, Rob Fergus, Sam Gross","submitted_at":"2016-03-03T22:59:35Z","abstract_excerpt":"Wooden blocks are a common toy for infants, allowing them to develop motor skills and gain intuition about the physical behavior of the world. In this paper, we explore the ability of deep feed-forward models to learn such intuitive physics. Using a 3D game engine, we create small towers of wooden blocks whose stability is randomized and render them collapsing (or remaining upright). This data allows us to train large convolutional network models which can accurately predict the outcome, as well as estimating the block trajectories. The models are also able to generalize in two important ways:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.01312","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":"1603.01312","created_at":"2026-05-18T01:19:37.991708+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.01312v1","created_at":"2026-05-18T01:19:37.991708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.01312","created_at":"2026-05-18T01:19:37.991708+00:00"},{"alias_kind":"pith_short_12","alias_value":"AWQI5QYTUI7Z","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_16","alias_value":"AWQI5QYTUI7ZGOQJ","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_8","alias_value":"AWQI5QYT","created_at":"2026-05-18T12:30:07.202191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2005.01643","citing_title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AWQI5QYTUI7ZGOQJ3VYQDOB7ON","json":"https://pith.science/pith/AWQI5QYTUI7ZGOQJ3VYQDOB7ON.json","graph_json":"https://pith.science/api/pith-number/AWQI5QYTUI7ZGOQJ3VYQDOB7ON/graph.json","events_json":"https://pith.science/api/pith-number/AWQI5QYTUI7ZGOQJ3VYQDOB7ON/events.json","paper":"https://pith.science/paper/AWQI5QYT"},"agent_actions":{"view_html":"https://pith.science/pith/AWQI5QYTUI7ZGOQJ3VYQDOB7ON","download_json":"https://pith.science/pith/AWQI5QYTUI7ZGOQJ3VYQDOB7ON.json","view_paper":"https://pith.science/paper/AWQI5QYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.01312&json=true","fetch_graph":"https://pith.science/api/pith-number/AWQI5QYTUI7ZGOQJ3VYQDOB7ON/graph.json","fetch_events":"https://pith.science/api/pith-number/AWQI5QYTUI7ZGOQJ3VYQDOB7ON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AWQI5QYTUI7ZGOQJ3VYQDOB7ON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AWQI5QYTUI7ZGOQJ3VYQDOB7ON/action/storage_attestation","attest_author":"https://pith.science/pith/AWQI5QYTUI7ZGOQJ3VYQDOB7ON/action/author_attestation","sign_citation":"https://pith.science/pith/AWQI5QYTUI7ZGOQJ3VYQDOB7ON/action/citation_signature","submit_replication":"https://pith.science/pith/AWQI5QYTUI7ZGOQJ3VYQDOB7ON/action/replication_record"}},"created_at":"2026-05-18T01:19:37.991708+00:00","updated_at":"2026-05-18T01:19:37.991708+00:00"}