{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TWIA2DL6HLKR3TT6N75NFYXGLU","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":"f9909c34f2195f0b2015ac8603641f5cbe34eec72397d013dbc6315cc76aaddd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-11T22:31:39Z","title_canon_sha256":"b90878a8b5fb1b794dd68f59fa47049bf8b4b7f2adfb4a86039c6b4dbdd31c88"},"schema_version":"1.0","source":{"id":"2410.09286","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09286","created_at":"2026-07-05T09:19:37Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09286v1","created_at":"2026-07-05T09:19:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09286","created_at":"2026-07-05T09:19:37Z"},{"alias_kind":"pith_short_12","alias_value":"TWIA2DL6HLKR","created_at":"2026-07-05T09:19:37Z"},{"alias_kind":"pith_short_16","alias_value":"TWIA2DL6HLKR3TT6","created_at":"2026-07-05T09:19:37Z"},{"alias_kind":"pith_short_8","alias_value":"TWIA2DL6","created_at":"2026-07-05T09:19:37Z"}],"graph_snapshots":[{"event_id":"sha256:81b0932a242e920dcde259c073c7aa569518ad6b0e2254ef551f94868cd1d8e0","target":"graph","created_at":"2026-07-05T09:19:37Z","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/2410.09286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from Demonstrations, particularly from biological experts like humans and animals, often encounters significant data acquisition challenges. While recent approaches leverage internet videos for learning, they require complex, task-specific pipelines to extract and retarget motion data for the agent. In this work, we introduce a language-model-assisted bi-level programming framework that enables a reinforcement learning agent to directly learn its reward from internet videos, bypassing dedicated data preparation. The framework includes two levels: an upper level where a vision-language","authors_text":"Harsh Mahesheka, Wanxin Jin, Zhaoran Wang, Zhixian Xie","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-11T22:31:39Z","title":"Language-Model-Assisted Bi-Level Programming for Reward Learning from Internet Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09286","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:cb766ea3485c3be399332ba7b624ad4ddcec64c9e3a62b9472624af976c45b94","target":"record","created_at":"2026-07-05T09:19:37Z","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":"f9909c34f2195f0b2015ac8603641f5cbe34eec72397d013dbc6315cc76aaddd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-11T22:31:39Z","title_canon_sha256":"b90878a8b5fb1b794dd68f59fa47049bf8b4b7f2adfb4a86039c6b4dbdd31c88"},"schema_version":"1.0","source":{"id":"2410.09286","kind":"arxiv","version":1}},"canonical_sha256":"9d900d0d7e3ad51dce7e6ffad2e2e65d087c0d144f9213e0e091f1ccf019a193","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d900d0d7e3ad51dce7e6ffad2e2e65d087c0d144f9213e0e091f1ccf019a193","first_computed_at":"2026-07-05T09:19:37.304716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:37.304716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jR7haSS7Ssa8hdoKm04j5sHYFGoI1dAXrn6qewanNJ8PIFSz49mg7yKg8m45HcIiHA+go8p5N30jKgAxAYDECg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:37.305196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09286","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb766ea3485c3be399332ba7b624ad4ddcec64c9e3a62b9472624af976c45b94","sha256:81b0932a242e920dcde259c073c7aa569518ad6b0e2254ef551f94868cd1d8e0"],"state_sha256":"20e7fbd9de77cd8d7b00466a581f6e200a42e2d2454c5ba019d606d79694339f"}