{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JGG3PPVADSIVYUGCHUBYROJ2WC","short_pith_number":"pith:JGG3PPVA","canonical_record":{"source":{"id":"2103.13834","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-03-25T13:28:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"269ceef97c3a9b52be1957629651ab14da23ca1f2acfce4d4030f57c633618e8","abstract_canon_sha256":"2ac71a66a781706d1db3c8e292d6eb5a74583d9d5cfb96eb7b466af9545007f4"},"schema_version":"1.0"},"canonical_sha256":"498db7bea01c915c50c23d0388b93ab08d1df6546affe9c552e7a7c839171313","source":{"kind":"arxiv","id":"2103.13834","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.13834","created_at":"2026-07-05T02:26:57Z"},{"alias_kind":"arxiv_version","alias_value":"2103.13834v2","created_at":"2026-07-05T02:26:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13834","created_at":"2026-07-05T02:26:57Z"},{"alias_kind":"pith_short_12","alias_value":"JGG3PPVADSIV","created_at":"2026-07-05T02:26:57Z"},{"alias_kind":"pith_short_16","alias_value":"JGG3PPVADSIVYUGC","created_at":"2026-07-05T02:26:57Z"},{"alias_kind":"pith_short_8","alias_value":"JGG3PPVA","created_at":"2026-07-05T02:26:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JGG3PPVADSIVYUGCHUBYROJ2WC","target":"record","payload":{"canonical_record":{"source":{"id":"2103.13834","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-03-25T13:28:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"269ceef97c3a9b52be1957629651ab14da23ca1f2acfce4d4030f57c633618e8","abstract_canon_sha256":"2ac71a66a781706d1db3c8e292d6eb5a74583d9d5cfb96eb7b466af9545007f4"},"schema_version":"1.0"},"canonical_sha256":"498db7bea01c915c50c23d0388b93ab08d1df6546affe9c552e7a7c839171313","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:57.687338Z","signature_b64":"lKgyQQ8FEmtIZ0hkksU5ucHewnSGzGuSwat99eOFFta++bNNB5b9rxbJUoIQ/fLO/3XN+yK0F9KW8dXsCXOHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"498db7bea01c915c50c23d0388b93ab08d1df6546affe9c552e7a7c839171313","last_reissued_at":"2026-07-05T02:26:57.686885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:57.686885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.13834","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":"2026-07-05T02:26:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oXbWgT8H/vubCC/bEzji6wqF1AXOOvnN5avZOCQNNQF6ioj8xi3m3ac2MEwlmWs+kUGN/8LBKJMtYGlzlRLvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:47:55.399480Z"},"content_sha256":"7adf62173557d8c733b4fe29f09c7476acb95a2a7731f869bdaa6f549de34687","schema_version":"1.0","event_id":"sha256:7adf62173557d8c733b4fe29f09c7476acb95a2a7731f869bdaa6f549de34687"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JGG3PPVADSIVYUGCHUBYROJ2WC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Imitation Learning by Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Hamidreza Kasaei, Lambert Schomaker, Sha Luo","submitted_at":"2021-03-25T13:28:38Z","abstract_excerpt":"Imitation learning (IL) enables robots to acquire skills quickly by transferring expert knowledge, which is widely adopted in reinforcement learning (RL) to initialize exploration. However, in long-horizon motion planning tasks, a challenging problem in deploying IL and RL methods is how to generate and collect massive, broadly distributed data such that these methods can generalize effectively. In this work, we solve this problem using our proposed approach called {self-imitation learning by planning (SILP)}, where demonstration data are collected automatically by planning on the visited stat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13834","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.13834/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":"2026-07-05T02:26:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1oLSrUWhEb6n3T/U1ipqJjS7VuVlNhFB/awmaJmzvRoBBXz81+ROFEBBjrYAKAoT6Nhyhg5EROphl2d8lPWMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:47:55.399847Z"},"content_sha256":"f59cefeeedf56ac88c9f41afe55d821a62f548e2a4a075e781270c13eb5ad985","schema_version":"1.0","event_id":"sha256:f59cefeeedf56ac88c9f41afe55d821a62f548e2a4a075e781270c13eb5ad985"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JGG3PPVADSIVYUGCHUBYROJ2WC/bundle.json","state_url":"https://pith.science/pith/JGG3PPVADSIVYUGCHUBYROJ2WC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JGG3PPVADSIVYUGCHUBYROJ2WC/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":"2026-07-06T15:47:55Z","links":{"resolver":"https://pith.science/pith/JGG3PPVADSIVYUGCHUBYROJ2WC","bundle":"https://pith.science/pith/JGG3PPVADSIVYUGCHUBYROJ2WC/bundle.json","state":"https://pith.science/pith/JGG3PPVADSIVYUGCHUBYROJ2WC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JGG3PPVADSIVYUGCHUBYROJ2WC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JGG3PPVADSIVYUGCHUBYROJ2WC","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":"2ac71a66a781706d1db3c8e292d6eb5a74583d9d5cfb96eb7b466af9545007f4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-03-25T13:28:38Z","title_canon_sha256":"269ceef97c3a9b52be1957629651ab14da23ca1f2acfce4d4030f57c633618e8"},"schema_version":"1.0","source":{"id":"2103.13834","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.13834","created_at":"2026-07-05T02:26:57Z"},{"alias_kind":"arxiv_version","alias_value":"2103.13834v2","created_at":"2026-07-05T02:26:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13834","created_at":"2026-07-05T02:26:57Z"},{"alias_kind":"pith_short_12","alias_value":"JGG3PPVADSIV","created_at":"2026-07-05T02:26:57Z"},{"alias_kind":"pith_short_16","alias_value":"JGG3PPVADSIVYUGC","created_at":"2026-07-05T02:26:57Z"},{"alias_kind":"pith_short_8","alias_value":"JGG3PPVA","created_at":"2026-07-05T02:26:57Z"}],"graph_snapshots":[{"event_id":"sha256:f59cefeeedf56ac88c9f41afe55d821a62f548e2a4a075e781270c13eb5ad985","target":"graph","created_at":"2026-07-05T02:26:57Z","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/2103.13834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation learning (IL) enables robots to acquire skills quickly by transferring expert knowledge, which is widely adopted in reinforcement learning (RL) to initialize exploration. However, in long-horizon motion planning tasks, a challenging problem in deploying IL and RL methods is how to generate and collect massive, broadly distributed data such that these methods can generalize effectively. In this work, we solve this problem using our proposed approach called {self-imitation learning by planning (SILP)}, where demonstration data are collected automatically by planning on the visited stat","authors_text":"Hamidreza Kasaei, Lambert Schomaker, Sha Luo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-03-25T13:28:38Z","title":"Self-Imitation Learning by Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13834","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":"sha256:7adf62173557d8c733b4fe29f09c7476acb95a2a7731f869bdaa6f549de34687","target":"record","created_at":"2026-07-05T02:26:57Z","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":"2ac71a66a781706d1db3c8e292d6eb5a74583d9d5cfb96eb7b466af9545007f4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-03-25T13:28:38Z","title_canon_sha256":"269ceef97c3a9b52be1957629651ab14da23ca1f2acfce4d4030f57c633618e8"},"schema_version":"1.0","source":{"id":"2103.13834","kind":"arxiv","version":2}},"canonical_sha256":"498db7bea01c915c50c23d0388b93ab08d1df6546affe9c552e7a7c839171313","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"498db7bea01c915c50c23d0388b93ab08d1df6546affe9c552e7a7c839171313","first_computed_at":"2026-07-05T02:26:57.686885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:57.686885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lKgyQQ8FEmtIZ0hkksU5ucHewnSGzGuSwat99eOFFta++bNNB5b9rxbJUoIQ/fLO/3XN+yK0F9KW8dXsCXOHDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:57.687338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.13834","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7adf62173557d8c733b4fe29f09c7476acb95a2a7731f869bdaa6f549de34687","sha256:f59cefeeedf56ac88c9f41afe55d821a62f548e2a4a075e781270c13eb5ad985"],"state_sha256":"7ab87c61a8a93f07a79c29cff05bcb247e520dd6a5a665b30f74cd803dad02cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WYZZ9eXoZC1Z1VjNEKZgqnjG2rIUTxOIG/rgO/GmtRxtzy32L05pjumHkHEwIB2Ew13wwpYXzTYNDhozPPFSDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:47:55.401735Z","bundle_sha256":"53d4cce5d88cb4f7eb73f8382d994e0cc20afbc0fe9cb635c64ed2b435fcf5bb"}}