{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HQKZJXXZKOXBLOLSH2MN5INFR2","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":"644a814a01538eb2b375f98c2a840c845742b55d44c7887de7ac0caaabb2ddff","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-11-13T06:56:21Z","title_canon_sha256":"63b0ac273f473740251da76d2d7184839eaa7e21027d055f2e1fade1c7134e49"},"schema_version":"1.0","source":{"id":"1911.05321","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.05321","created_at":"2026-07-05T00:43:05Z"},{"alias_kind":"arxiv_version","alias_value":"1911.05321v2","created_at":"2026-07-05T00:43:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.05321","created_at":"2026-07-05T00:43:05Z"},{"alias_kind":"pith_short_12","alias_value":"HQKZJXXZKOXB","created_at":"2026-07-05T00:43:05Z"},{"alias_kind":"pith_short_16","alias_value":"HQKZJXXZKOXBLOLS","created_at":"2026-07-05T00:43:05Z"},{"alias_kind":"pith_short_8","alias_value":"HQKZJXXZ","created_at":"2026-07-05T00:43:05Z"}],"graph_snapshots":[{"event_id":"sha256:e7a1db6e26ca2e71fb7f2bec39d57028dab3b07b87049c14de07acea32dcd1be","target":"graph","created_at":"2026-07-05T00:43:05Z","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/1911.05321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from offline task demonstrations is a problem of great interest in robotics. For simple short-horizon manipulation tasks with modest variation in task instances, offline learning from a small set of demonstrations can produce controllers that successfully solve the task. However, leveraging a fixed batch of data can be problematic for larger datasets and longer-horizon tasks with greater variations. The data can exhibit substantial diversity and consist of suboptimal solution approaches. In this paper, we propose Implicit Reinforcement without Interaction at Scale (IRIS), a novel fram","authors_text":"Ajay Mandlekar, Animesh Garg, Byron Boots, Dieter Fox, Fabio Ramos, Li Fei-Fei, Silvio Savarese","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-11-13T06:56:21Z","title":"IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.05321","kind":"arxiv","version":2},"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:b6e7021bb6c47e56fd1b3d969c197100ff142a7749c2b1e5e520567c189a91cd","target":"record","created_at":"2026-07-05T00:43:05Z","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":"644a814a01538eb2b375f98c2a840c845742b55d44c7887de7ac0caaabb2ddff","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-11-13T06:56:21Z","title_canon_sha256":"63b0ac273f473740251da76d2d7184839eaa7e21027d055f2e1fade1c7134e49"},"schema_version":"1.0","source":{"id":"1911.05321","kind":"arxiv","version":2}},"canonical_sha256":"3c1594def953ae15b9723e98dea1a58eae35fde73ba69547532aec7f7c8ce949","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c1594def953ae15b9723e98dea1a58eae35fde73ba69547532aec7f7c8ce949","first_computed_at":"2026-07-05T00:43:05.591733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:43:05.591733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c5swosBRHwM+X68FB8kSbuUbdxLs1+Q4iU71ljU5BrPOVJicyk11+cD3QXDkqRrkAk+yjHgQbF5Ez5T6l6vVDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:43:05.592283Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.05321","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6e7021bb6c47e56fd1b3d969c197100ff142a7749c2b1e5e520567c189a91cd","sha256:e7a1db6e26ca2e71fb7f2bec39d57028dab3b07b87049c14de07acea32dcd1be"],"state_sha256":"637ca0c188e5d0ca09157b45fe4063bac92cf231fcf5ac8702cd8d4fc9ea2213"}