{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:3GNARAWO4Z3ACSUPPDFIHNU3V3","short_pith_number":"pith:3GNARAWO","canonical_record":{"source":{"id":"2012.02419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T06:07:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b51827fb776d970549e4e2e853d3ea10e3fbdae78056ad6f45ca1f1f35f56dc","abstract_canon_sha256":"e3c99f6bdfdf2253fc227c10f332b70e96f7f3f3d6c029ce460ad7ad0638bb5b"},"schema_version":"1.0"},"canonical_sha256":"d99a0882cee676014a8f78ca83b69baef14b93b0107ecfa3cf9ebcb68ccfc6a0","source":{"kind":"arxiv","id":"2012.02419","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02419","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02419v1","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02419","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"pith_short_12","alias_value":"3GNARAWO4Z3A","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"pith_short_16","alias_value":"3GNARAWO4Z3ACSUP","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"pith_short_8","alias_value":"3GNARAWO","created_at":"2026-07-05T01:56:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:3GNARAWO4Z3ACSUPPDFIHNU3V3","target":"record","payload":{"canonical_record":{"source":{"id":"2012.02419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T06:07:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b51827fb776d970549e4e2e853d3ea10e3fbdae78056ad6f45ca1f1f35f56dc","abstract_canon_sha256":"e3c99f6bdfdf2253fc227c10f332b70e96f7f3f3d6c029ce460ad7ad0638bb5b"},"schema_version":"1.0"},"canonical_sha256":"d99a0882cee676014a8f78ca83b69baef14b93b0107ecfa3cf9ebcb68ccfc6a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:59.412246Z","signature_b64":"SwVNXbPgbmerMc+Dic5EmZHyHQpAIKGDObcln6WBX+GjnDDdcpcP52qdG7TejpU74gC9zZ57X3UnC0Fl6gWUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d99a0882cee676014a8f78ca83b69baef14b93b0107ecfa3cf9ebcb68ccfc6a0","last_reissued_at":"2026-07-05T01:56:59.411755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:59.411755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.02419","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:56:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2DKdNshJ5d2veb97A6OJ0Pc5PJ/ls/VdOZiYzVsodI77DgYeN+53jnRqwpF1CzJ1xMiIlhcnXl9VZhUD+roDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T10:15:21.453502Z"},"content_sha256":"dbb10eb40580ab68d3244f702be21c481d6f6d4cccde70c6439d1f832632e7a9","schema_version":"1.0","event_id":"sha256:dbb10eb40580ab68d3244f702be21c481d6f6d4cccde70c6439d1f832632e7a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:3GNARAWO4Z3ACSUPPDFIHNU3V3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Planning from Pixels using Inverse Dynamics Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jimmy Ba, Keiran Paster, Sheila A. McIlraith","submitted_at":"2020-12-04T06:07:36Z","abstract_excerpt":"Learning task-agnostic dynamics models in high-dimensional observation spaces can be challenging for model-based RL agents. We propose a novel way to learn latent world models by learning to predict sequences of future actions conditioned on task completion. These task-conditioned models adaptively focus modeling capacity on task-relevant dynamics, while simultaneously serving as an effective heuristic for planning with sparse rewards. We evaluate our method on challenging visual goal completion tasks and show a substantial increase in performance compared to prior model-free approaches."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02419","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.02419/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:56:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y17oIJDhSKqhEfCUOca07y8whj4DWFriDUVcuYiAZ0/9wZwxf2KJsjYQ0TXDZZKfQN95T4B12HwKb3v8nua4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T10:15:21.453883Z"},"content_sha256":"17933ba9973e704e4626a414ec9bdeb316e5ab0e48e2cb9fc12f31d73fb78d02","schema_version":"1.0","event_id":"sha256:17933ba9973e704e4626a414ec9bdeb316e5ab0e48e2cb9fc12f31d73fb78d02"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GNARAWO4Z3ACSUPPDFIHNU3V3/bundle.json","state_url":"https://pith.science/pith/3GNARAWO4Z3ACSUPPDFIHNU3V3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GNARAWO4Z3ACSUPPDFIHNU3V3/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":"2026-07-24T10:15:21Z","links":{"resolver":"https://pith.science/pith/3GNARAWO4Z3ACSUPPDFIHNU3V3","bundle":"https://pith.science/pith/3GNARAWO4Z3ACSUPPDFIHNU3V3/bundle.json","state":"https://pith.science/pith/3GNARAWO4Z3ACSUPPDFIHNU3V3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GNARAWO4Z3ACSUPPDFIHNU3V3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3GNARAWO4Z3ACSUPPDFIHNU3V3","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":"e3c99f6bdfdf2253fc227c10f332b70e96f7f3f3d6c029ce460ad7ad0638bb5b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T06:07:36Z","title_canon_sha256":"8b51827fb776d970549e4e2e853d3ea10e3fbdae78056ad6f45ca1f1f35f56dc"},"schema_version":"1.0","source":{"id":"2012.02419","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02419","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02419v1","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02419","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"pith_short_12","alias_value":"3GNARAWO4Z3A","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"pith_short_16","alias_value":"3GNARAWO4Z3ACSUP","created_at":"2026-07-05T01:56:59Z"},{"alias_kind":"pith_short_8","alias_value":"3GNARAWO","created_at":"2026-07-05T01:56:59Z"}],"graph_snapshots":[{"event_id":"sha256:17933ba9973e704e4626a414ec9bdeb316e5ab0e48e2cb9fc12f31d73fb78d02","target":"graph","created_at":"2026-07-05T01:56:59Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2012.02419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning task-agnostic dynamics models in high-dimensional observation spaces can be challenging for model-based RL agents. We propose a novel way to learn latent world models by learning to predict sequences of future actions conditioned on task completion. These task-conditioned models adaptively focus modeling capacity on task-relevant dynamics, while simultaneously serving as an effective heuristic for planning with sparse rewards. We evaluate our method on challenging visual goal completion tasks and show a substantial increase in performance compared to prior model-free approaches.","authors_text":"Jimmy Ba, Keiran Paster, Sheila A. McIlraith","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T06:07:36Z","title":"Planning from Pixels using Inverse Dynamics Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02419","kind":"arxiv","version":1},"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:dbb10eb40580ab68d3244f702be21c481d6f6d4cccde70c6439d1f832632e7a9","target":"record","created_at":"2026-07-05T01:56:59Z","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":"e3c99f6bdfdf2253fc227c10f332b70e96f7f3f3d6c029ce460ad7ad0638bb5b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T06:07:36Z","title_canon_sha256":"8b51827fb776d970549e4e2e853d3ea10e3fbdae78056ad6f45ca1f1f35f56dc"},"schema_version":"1.0","source":{"id":"2012.02419","kind":"arxiv","version":1}},"canonical_sha256":"d99a0882cee676014a8f78ca83b69baef14b93b0107ecfa3cf9ebcb68ccfc6a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d99a0882cee676014a8f78ca83b69baef14b93b0107ecfa3cf9ebcb68ccfc6a0","first_computed_at":"2026-07-05T01:56:59.411755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:59.411755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SwVNXbPgbmerMc+Dic5EmZHyHQpAIKGDObcln6WBX+GjnDDdcpcP52qdG7TejpU74gC9zZ57X3UnC0Fl6gWUAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:59.412246Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.02419","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbb10eb40580ab68d3244f702be21c481d6f6d4cccde70c6439d1f832632e7a9","sha256:17933ba9973e704e4626a414ec9bdeb316e5ab0e48e2cb9fc12f31d73fb78d02"],"state_sha256":"cbbbd0a3f9977a77eb40ddc208bebf35b687ced5c00d35b1fe515f40b702fcf2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"deTBnw2k4ilks4c2uYt+GxOYVrWWvPL0uQVGMZrrJ8pLL19ZM36oe43lcfdZwGzqYRgQAGJwVLFKz3LWOSOJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T10:15:21.456464Z","bundle_sha256":"5cb0f54f1c8f3be815a93bd1abc38120a6543488a94b447b6cecbbf18b8da160"}}