{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZNHRAPXVJR645N6IWOQLW4VQ4R","short_pith_number":"pith:ZNHRAPXV","canonical_record":{"source":{"id":"1906.10165","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-06-24T18:37:33Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"e733bfce7d2d5e5112be5ab7681a046badbcd60a6605cad5c2cb87aca32498b0","abstract_canon_sha256":"3db6c6c9218f6e94b52f353709f5ca167d295130a613ed39172f072d1c3dd9aa"},"schema_version":"1.0"},"canonical_sha256":"cb4f103ef54c7dceb7c8b3a0bb72b0e46a4f17374417c55f01e507e0252c06fb","source":{"kind":"arxiv","id":"1906.10165","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10165","created_at":"2026-05-17T23:41:41Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10165v2","created_at":"2026-05-17T23:41:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10165","created_at":"2026-05-17T23:41:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZNHRAPXVJR64","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZNHRAPXVJR645N6I","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZNHRAPXV","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZNHRAPXVJR645N6IWOQLW4VQ4R","target":"record","payload":{"canonical_record":{"source":{"id":"1906.10165","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-06-24T18:37:33Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"e733bfce7d2d5e5112be5ab7681a046badbcd60a6605cad5c2cb87aca32498b0","abstract_canon_sha256":"3db6c6c9218f6e94b52f353709f5ca167d295130a613ed39172f072d1c3dd9aa"},"schema_version":"1.0"},"canonical_sha256":"cb4f103ef54c7dceb7c8b3a0bb72b0e46a4f17374417c55f01e507e0252c06fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:41.706104Z","signature_b64":"BpBn9sTRHv8i8uqgQP6d+kg5Euqs9FllHZoze/Tui/MdWoIJsUZAwYLnaf+q7w0gem/uFew+1FNCKzr4qLmdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb4f103ef54c7dceb7c8b3a0bb72b0e46a4f17374417c55f01e507e0252c06fb","last_reissued_at":"2026-05-17T23:41:41.705616Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:41.705616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.10165","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mXw9Lfb3R96tAkk8hDdo9vmZokHXtZ3RKosYQEJrFzf7KryCIxX2HLy6AgR3u3LHF4/Yf20VTqKZsM/Kfvz8AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T02:37:52.077582Z"},"content_sha256":"82a7112a8378c0a0f5003c08130425d2daabc34df94f029446816aac1ea3f6ac","schema_version":"1.0","event_id":"sha256:82a7112a8378c0a0f5003c08130425d2daabc34df94f029446816aac1ea3f6ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZNHRAPXVJR645N6IWOQLW4VQ4R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training an Interactive Helper","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Chelsea Finn, Karol Hausman, Mark Woodward","submitted_at":"2019-06-24T18:37:33Z","abstract_excerpt":"Developing agents that can quickly adapt their behavior to new tasks remains a challenge. Meta-learning has been applied to this problem, but previous methods require either specifying a reward function which can be tedious or providing demonstrations which can be inefficient. In this paper, we investigate if, and how, a \"helper\" agent can be trained to interactively adapt their behavior to maximize the reward of another agent, whom we call the \"prime\" agent, without observing their reward or receiving explicit demonstrations. To this end, we propose to meta-learn a helper agent along with a p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10165","kind":"arxiv","version":2},"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":"2026-05-17T23:41:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rfdumbipZyuU4p9t02XR/1hLu4YReePa8CYeYumRxFQgLC1xP7B97mlvQpzppwNRL4wYpQBqbJhAmu18OgbNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T02:37:52.078238Z"},"content_sha256":"6833e43aa2f978005cd111586accff67be75b4628fb3ef73dae75df185dde076","schema_version":"1.0","event_id":"sha256:6833e43aa2f978005cd111586accff67be75b4628fb3ef73dae75df185dde076"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZNHRAPXVJR645N6IWOQLW4VQ4R/bundle.json","state_url":"https://pith.science/pith/ZNHRAPXVJR645N6IWOQLW4VQ4R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZNHRAPXVJR645N6IWOQLW4VQ4R/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":"2026-06-04T02:37:52Z","links":{"resolver":"https://pith.science/pith/ZNHRAPXVJR645N6IWOQLW4VQ4R","bundle":"https://pith.science/pith/ZNHRAPXVJR645N6IWOQLW4VQ4R/bundle.json","state":"https://pith.science/pith/ZNHRAPXVJR645N6IWOQLW4VQ4R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZNHRAPXVJR645N6IWOQLW4VQ4R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZNHRAPXVJR645N6IWOQLW4VQ4R","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":"3db6c6c9218f6e94b52f353709f5ca167d295130a613ed39172f072d1c3dd9aa","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-06-24T18:37:33Z","title_canon_sha256":"e733bfce7d2d5e5112be5ab7681a046badbcd60a6605cad5c2cb87aca32498b0"},"schema_version":"1.0","source":{"id":"1906.10165","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10165","created_at":"2026-05-17T23:41:41Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10165v2","created_at":"2026-05-17T23:41:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10165","created_at":"2026-05-17T23:41:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZNHRAPXVJR64","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZNHRAPXVJR645N6I","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZNHRAPXV","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:6833e43aa2f978005cd111586accff67be75b4628fb3ef73dae75df185dde076","target":"graph","created_at":"2026-05-17T23:41:41Z","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":"Developing agents that can quickly adapt their behavior to new tasks remains a challenge. Meta-learning has been applied to this problem, but previous methods require either specifying a reward function which can be tedious or providing demonstrations which can be inefficient. In this paper, we investigate if, and how, a \"helper\" agent can be trained to interactively adapt their behavior to maximize the reward of another agent, whom we call the \"prime\" agent, without observing their reward or receiving explicit demonstrations. To this end, we propose to meta-learn a helper agent along with a p","authors_text":"Chelsea Finn, Karol Hausman, Mark Woodward","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-06-24T18:37:33Z","title":"Training an Interactive Helper"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10165","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":"sha256:82a7112a8378c0a0f5003c08130425d2daabc34df94f029446816aac1ea3f6ac","target":"record","created_at":"2026-05-17T23:41:41Z","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":"3db6c6c9218f6e94b52f353709f5ca167d295130a613ed39172f072d1c3dd9aa","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-06-24T18:37:33Z","title_canon_sha256":"e733bfce7d2d5e5112be5ab7681a046badbcd60a6605cad5c2cb87aca32498b0"},"schema_version":"1.0","source":{"id":"1906.10165","kind":"arxiv","version":2}},"canonical_sha256":"cb4f103ef54c7dceb7c8b3a0bb72b0e46a4f17374417c55f01e507e0252c06fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb4f103ef54c7dceb7c8b3a0bb72b0e46a4f17374417c55f01e507e0252c06fb","first_computed_at":"2026-05-17T23:41:41.705616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:41.705616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BpBn9sTRHv8i8uqgQP6d+kg5Euqs9FllHZoze/Tui/MdWoIJsUZAwYLnaf+q7w0gem/uFew+1FNCKzr4qLmdCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:41.706104Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.10165","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82a7112a8378c0a0f5003c08130425d2daabc34df94f029446816aac1ea3f6ac","sha256:6833e43aa2f978005cd111586accff67be75b4628fb3ef73dae75df185dde076"],"state_sha256":"b0edd8af94ff8d7bddced189b3a9a61a4d6ec7838e86044d08b57c1cc4b8de0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/FNOlL4AQE9wtf1oEApByK9xzsDVh9AcJD7mudSpUCRKG9crK5+1hHafZ1ubmwzbCwv8Zp9wkHe2g7NopnG8Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T02:37:52.081911Z","bundle_sha256":"ccb5270c1f5c06e072fa97170d37e71ca9b240fa88222971589f1e79eacefe91"}}