{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:AOAZSDKLYTCTSVOURIJ33WTC2K","short_pith_number":"pith:AOAZSDKL","canonical_record":{"source":{"id":"2001.00503","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-02T16:04:21Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"8aff62f8117c8d01404d67924207b71b88aae7256d9d7d61e4be5dbb931724a6","abstract_canon_sha256":"bb2c4f91bef268ed8cd236f5a6438388ecf9b12b84d8478a8c6634d4e8d302bd"},"schema_version":"1.0"},"canonical_sha256":"0381990d4bc4c53955d48a13bdda62d2852f8aac07498edd453ec0e2de0c98d2","source":{"kind":"arxiv","id":"2001.00503","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.00503","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"arxiv_version","alias_value":"2001.00503v3","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00503","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"pith_short_12","alias_value":"AOAZSDKLYTCT","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"pith_short_16","alias_value":"AOAZSDKLYTCTSVOU","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"pith_short_8","alias_value":"AOAZSDKL","created_at":"2026-07-05T01:53:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:AOAZSDKLYTCTSVOURIJ33WTC2K","target":"record","payload":{"canonical_record":{"source":{"id":"2001.00503","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-02T16:04:21Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"8aff62f8117c8d01404d67924207b71b88aae7256d9d7d61e4be5dbb931724a6","abstract_canon_sha256":"bb2c4f91bef268ed8cd236f5a6438388ecf9b12b84d8478a8c6634d4e8d302bd"},"schema_version":"1.0"},"canonical_sha256":"0381990d4bc4c53955d48a13bdda62d2852f8aac07498edd453ec0e2de0c98d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:36.805593Z","signature_b64":"21G20C1AqJ1Tg2np7Ew7Zno8WjM/asdnjT6nPqW8mKiIfBHRGQTBJHnA9Yua6P9BECl8YUK2+XolocoBzthnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0381990d4bc4c53955d48a13bdda62d2852f8aac07498edd453ec0e2de0c98d2","last_reissued_at":"2026-07-05T01:53:36.805132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:36.805132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.00503","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:53:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F+DTB7F6FoX2uB16yhcGuFX9kM8h1ewrcs0oFvSCtkZ5u4cZGj/pYDeqsjYOIy6sp/0da3bfheR/RIoanYs5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:35:56.088886Z"},"content_sha256":"120cfd55fff3a58959a131dfbb1e6fe22b2e0b9984be45a1983a46bf6261180a","schema_version":"1.0","event_id":"sha256:120cfd55fff3a58959a131dfbb1e6fe22b2e0b9984be45a1983a46bf6261180a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:AOAZSDKLYTCTSVOURIJ33WTC2K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Letian Chen, Matthew Gombolay, Muyleng Ghuy, Rohan Paleja","submitted_at":"2020-01-02T16:04:21Z","abstract_excerpt":"Reinforcement learning (RL) has achieved tremendous success as a general framework for learning how to make decisions. However, this success relies on the interactive hand-tuning of a reward function by RL experts. On the other hand, inverse reinforcement learning (IRL) seeks to learn a reward function from readily-obtained human demonstrations. Yet, IRL suffers from two major limitations: 1) reward ambiguity - there are an infinite number of possible reward functions that could explain an expert's demonstration and 2) heterogeneity - human experts adopt varying strategies and preferences, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00503","kind":"arxiv","version":3},"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/2001.00503/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":"2026-07-05T01:53:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XnJt+0ZapaPp6PUabAql76+Hez8a3t6E7luYlycirup+euAHaUvFWWlTaldyr7LggmpjWU6z7hN27lK5NRWoDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:35:56.089395Z"},"content_sha256":"e9ac9b317016448bd6948e82d15379e974dd31044fb605fefcd9a502814f2c8a","schema_version":"1.0","event_id":"sha256:e9ac9b317016448bd6948e82d15379e974dd31044fb605fefcd9a502814f2c8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AOAZSDKLYTCTSVOURIJ33WTC2K/bundle.json","state_url":"https://pith.science/pith/AOAZSDKLYTCTSVOURIJ33WTC2K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AOAZSDKLYTCTSVOURIJ33WTC2K/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":"2026-08-01T07:35:56Z","links":{"resolver":"https://pith.science/pith/AOAZSDKLYTCTSVOURIJ33WTC2K","bundle":"https://pith.science/pith/AOAZSDKLYTCTSVOURIJ33WTC2K/bundle.json","state":"https://pith.science/pith/AOAZSDKLYTCTSVOURIJ33WTC2K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AOAZSDKLYTCTSVOURIJ33WTC2K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AOAZSDKLYTCTSVOURIJ33WTC2K","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":"bb2c4f91bef268ed8cd236f5a6438388ecf9b12b84d8478a8c6634d4e8d302bd","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-02T16:04:21Z","title_canon_sha256":"8aff62f8117c8d01404d67924207b71b88aae7256d9d7d61e4be5dbb931724a6"},"schema_version":"1.0","source":{"id":"2001.00503","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.00503","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"arxiv_version","alias_value":"2001.00503v3","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00503","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"pith_short_12","alias_value":"AOAZSDKLYTCT","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"pith_short_16","alias_value":"AOAZSDKLYTCTSVOU","created_at":"2026-07-05T01:53:36Z"},{"alias_kind":"pith_short_8","alias_value":"AOAZSDKL","created_at":"2026-07-05T01:53:36Z"}],"graph_snapshots":[{"event_id":"sha256:e9ac9b317016448bd6948e82d15379e974dd31044fb605fefcd9a502814f2c8a","target":"graph","created_at":"2026-07-05T01:53:36Z","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/2001.00503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has achieved tremendous success as a general framework for learning how to make decisions. However, this success relies on the interactive hand-tuning of a reward function by RL experts. On the other hand, inverse reinforcement learning (IRL) seeks to learn a reward function from readily-obtained human demonstrations. Yet, IRL suffers from two major limitations: 1) reward ambiguity - there are an infinite number of possible reward functions that could explain an expert's demonstration and 2) heterogeneity - human experts adopt varying strategies and preferences, whi","authors_text":"Letian Chen, Matthew Gombolay, Muyleng Ghuy, Rohan Paleja","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-02T16:04:21Z","title":"Joint Goal and Strategy Inference across Heterogeneous Demonstrators via Reward Network Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00503","kind":"arxiv","version":3},"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":"sha256:120cfd55fff3a58959a131dfbb1e6fe22b2e0b9984be45a1983a46bf6261180a","target":"record","created_at":"2026-07-05T01:53:36Z","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":"bb2c4f91bef268ed8cd236f5a6438388ecf9b12b84d8478a8c6634d4e8d302bd","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-02T16:04:21Z","title_canon_sha256":"8aff62f8117c8d01404d67924207b71b88aae7256d9d7d61e4be5dbb931724a6"},"schema_version":"1.0","source":{"id":"2001.00503","kind":"arxiv","version":3}},"canonical_sha256":"0381990d4bc4c53955d48a13bdda62d2852f8aac07498edd453ec0e2de0c98d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0381990d4bc4c53955d48a13bdda62d2852f8aac07498edd453ec0e2de0c98d2","first_computed_at":"2026-07-05T01:53:36.805132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:36.805132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"21G20C1AqJ1Tg2np7Ew7Zno8WjM/asdnjT6nPqW8mKiIfBHRGQTBJHnA9Yua6P9BECl8YUK2+XolocoBzthnAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:36.805593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.00503","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:120cfd55fff3a58959a131dfbb1e6fe22b2e0b9984be45a1983a46bf6261180a","sha256:e9ac9b317016448bd6948e82d15379e974dd31044fb605fefcd9a502814f2c8a"],"state_sha256":"e54d3d614a5c23615d98e4bea4bf255777994c839cf1fa576856df838ce251ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AzQnz9lNg85CJpXzkxhWjwxay/S++ECZTUFQdi+Wdqquyy0jDVbl+69JmlFZlYmAnobSBB4B4LjIKmAEGKiMDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T07:35:56.094130Z","bundle_sha256":"1c01e7f20749ea2562d51cedcd3066111877bba2a27a3de09c572c200d52fb0a"}}