{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:WGXXCQVE7NTFNS5JR3WHVZ5IFY","short_pith_number":"pith:WGXXCQVE","canonical_record":{"source":{"id":"1605.07157","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-23T19:45:55Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"d06f9a5db47fc974348ebaba4306cd139f57aec08e8cafd930b88c925d7876d6","abstract_canon_sha256":"066547be1fef29b05e1d512ba02a388da349991c7d5c26712e7acaf73c901d71"},"schema_version":"1.0"},"canonical_sha256":"b1af7142a4fb6656cba98eec7ae7a82e1fb4c90b90bb98b47402a2ece13db640","source":{"kind":"arxiv","id":"1605.07157","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.07157","created_at":"2026-05-18T01:02:04Z"},{"alias_kind":"arxiv_version","alias_value":"1605.07157v4","created_at":"2026-05-18T01:02:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07157","created_at":"2026-05-18T01:02:04Z"},{"alias_kind":"pith_short_12","alias_value":"WGXXCQVE7NTF","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WGXXCQVE7NTFNS5J","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WGXXCQVE","created_at":"2026-05-18T12:30:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:WGXXCQVE7NTFNS5JR3WHVZ5IFY","target":"record","payload":{"canonical_record":{"source":{"id":"1605.07157","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-23T19:45:55Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"d06f9a5db47fc974348ebaba4306cd139f57aec08e8cafd930b88c925d7876d6","abstract_canon_sha256":"066547be1fef29b05e1d512ba02a388da349991c7d5c26712e7acaf73c901d71"},"schema_version":"1.0"},"canonical_sha256":"b1af7142a4fb6656cba98eec7ae7a82e1fb4c90b90bb98b47402a2ece13db640","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:02:04.223990Z","signature_b64":"YjnXicmo65JQCotZaRsKuUDuU4qDg4jXQUUi3yOok6PcNqoGP1LFfDzkG6MAtukPuJc7GvKP/KuORQclCyt7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1af7142a4fb6656cba98eec7ae7a82e1fb4c90b90bb98b47402a2ece13db640","last_reissued_at":"2026-05-18T01:02:04.223371Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:02:04.223371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.07157","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:02:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h+XGHz50L/6pRNLs5f4D2e7IY/UvC+xtRSGKjzMRzjwkr6BuaOPT8y6bv8SDaRJ+Fvl1k5TTgvcY91W8AyKrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:15:36.038245Z"},"content_sha256":"e7888becadcae820b6aef558d390a6e91ead22fafef53630b6a1a8179fea0b13","schema_version":"1.0","event_id":"sha256:e7888becadcae820b6aef558d390a6e91ead22fafef53630b6a1a8179fea0b13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:WGXXCQVE7NTFNS5JR3WHVZ5IFY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Learning for Physical Interaction through Video Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Ian Goodfellow, Sergey Levine","submitted_at":"2016-05-23T19:45:55Z","abstract_excerpt":"A core challenge for an agent learning to interact with the world is to predict how its actions affect objects in its environment. Many existing methods for learning the dynamics of physical interactions require labeled object information. However, to scale real-world interaction learning to a variety of scenes and objects, acquiring labeled data becomes increasingly impractical. To learn about physical object motion without labels, we develop an action-conditioned video prediction model that explicitly models pixel motion, by predicting a distribution over pixel motion from previous frames. B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07157","kind":"arxiv","version":4},"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":"2026-05-18T01:02:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wkma57Ar8xJh8np3q7DrRpCvQidYiO9zBdrZc9TeCTgGvglqDybCa2yChZuj3317udEG19w8zuU7pYqNGxzyAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:15:36.038932Z"},"content_sha256":"53ebbd29bcb40783385bf9df0fc32923c608ff904bb65d2ee5c600a12f105e11","schema_version":"1.0","event_id":"sha256:53ebbd29bcb40783385bf9df0fc32923c608ff904bb65d2ee5c600a12f105e11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WGXXCQVE7NTFNS5JR3WHVZ5IFY/bundle.json","state_url":"https://pith.science/pith/WGXXCQVE7NTFNS5JR3WHVZ5IFY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WGXXCQVE7NTFNS5JR3WHVZ5IFY/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":"2026-05-28T00:15:36Z","links":{"resolver":"https://pith.science/pith/WGXXCQVE7NTFNS5JR3WHVZ5IFY","bundle":"https://pith.science/pith/WGXXCQVE7NTFNS5JR3WHVZ5IFY/bundle.json","state":"https://pith.science/pith/WGXXCQVE7NTFNS5JR3WHVZ5IFY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WGXXCQVE7NTFNS5JR3WHVZ5IFY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:WGXXCQVE7NTFNS5JR3WHVZ5IFY","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":"066547be1fef29b05e1d512ba02a388da349991c7d5c26712e7acaf73c901d71","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-23T19:45:55Z","title_canon_sha256":"d06f9a5db47fc974348ebaba4306cd139f57aec08e8cafd930b88c925d7876d6"},"schema_version":"1.0","source":{"id":"1605.07157","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.07157","created_at":"2026-05-18T01:02:04Z"},{"alias_kind":"arxiv_version","alias_value":"1605.07157v4","created_at":"2026-05-18T01:02:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07157","created_at":"2026-05-18T01:02:04Z"},{"alias_kind":"pith_short_12","alias_value":"WGXXCQVE7NTF","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WGXXCQVE7NTFNS5J","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WGXXCQVE","created_at":"2026-05-18T12:30:48Z"}],"graph_snapshots":[{"event_id":"sha256:53ebbd29bcb40783385bf9df0fc32923c608ff904bb65d2ee5c600a12f105e11","target":"graph","created_at":"2026-05-18T01:02:04Z","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":"A core challenge for an agent learning to interact with the world is to predict how its actions affect objects in its environment. Many existing methods for learning the dynamics of physical interactions require labeled object information. However, to scale real-world interaction learning to a variety of scenes and objects, acquiring labeled data becomes increasingly impractical. To learn about physical object motion without labels, we develop an action-conditioned video prediction model that explicitly models pixel motion, by predicting a distribution over pixel motion from previous frames. B","authors_text":"Chelsea Finn, Ian Goodfellow, Sergey Levine","cross_cats":["cs.AI","cs.CV","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-23T19:45:55Z","title":"Unsupervised Learning for Physical Interaction through Video Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07157","kind":"arxiv","version":4},"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:e7888becadcae820b6aef558d390a6e91ead22fafef53630b6a1a8179fea0b13","target":"record","created_at":"2026-05-18T01:02:04Z","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":"066547be1fef29b05e1d512ba02a388da349991c7d5c26712e7acaf73c901d71","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-23T19:45:55Z","title_canon_sha256":"d06f9a5db47fc974348ebaba4306cd139f57aec08e8cafd930b88c925d7876d6"},"schema_version":"1.0","source":{"id":"1605.07157","kind":"arxiv","version":4}},"canonical_sha256":"b1af7142a4fb6656cba98eec7ae7a82e1fb4c90b90bb98b47402a2ece13db640","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1af7142a4fb6656cba98eec7ae7a82e1fb4c90b90bb98b47402a2ece13db640","first_computed_at":"2026-05-18T01:02:04.223371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:02:04.223371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YjnXicmo65JQCotZaRsKuUDuU4qDg4jXQUUi3yOok6PcNqoGP1LFfDzkG6MAtukPuJc7GvKP/KuORQclCyt7BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:02:04.223990Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.07157","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7888becadcae820b6aef558d390a6e91ead22fafef53630b6a1a8179fea0b13","sha256:53ebbd29bcb40783385bf9df0fc32923c608ff904bb65d2ee5c600a12f105e11"],"state_sha256":"69f0f11d41d9051c6f21c9db6c7508eb29956484aa827d42940190313d8d1867"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PZOP0PE2aR+UjBw2UXxC3sToo58cZN/AuLjyHqJfBAnaUd6IGnUsSe/W98EtbgqCKJHGEUet0x6lCAiDFEPrDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T00:15:36.041599Z","bundle_sha256":"98db7b848c074abb4824f419ec73d52647f08ba2f4df7a36b5487b5ffa8cd1de"}}