{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PRMXXWVBJHK5DWPNE7BUQ2MHWM","short_pith_number":"pith:PRMXXWVB","schema_version":"1.0","canonical_sha256":"7c597bdaa149d5d1d9ed27c3486987b3042911d31f76ef6434dd153638d5bc6a","source":{"kind":"arxiv","id":"2012.13037","version":1},"attestation_state":"computed","paper":{"title":"SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daniel Kasenberg, Jivko Sinapov, Matthias Scheutz, Shivam Goel, Vasanth Sarathy","submitted_at":"2020-12-24T00:31:02Z","abstract_excerpt":"Symbolic planning models allow decision-making agents to sequence actions in arbitrary ways to achieve a variety of goals in dynamic domains. However, they are typically handcrafted and tend to require precise formulations that are not robust to human error. Reinforcement learning (RL) approaches do not require such models, and instead learn domain dynamics by exploring the environment and collecting rewards. However, RL approaches tend to require millions of episodes of experience and often learn policies that are not easily transferable to other tasks. In this paper, we address one aspect of"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2012.13037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-12-24T00:31:02Z","cross_cats_sorted":[],"title_canon_sha256":"5ccf33f99dab33de045b4b5a106c52ba97feb6435dd3d849a6192f6bff728b46","abstract_canon_sha256":"6f4f763cd0252c0a925f059641db9f7920dbc3bc8cd86f3c7ec5251a598765a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:01:47.076623Z","signature_b64":"L6x47G/6bfKXYuriJ2lXSQcIeD1C/t08v7nO/gzejB7DmU3cmSSEviiyKpUPAh46lCxij+RyFxDJunaE9/06AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c597bdaa149d5d1d9ed27c3486987b3042911d31f76ef6434dd153638d5bc6a","last_reissued_at":"2026-07-05T02:01:47.076056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:01:47.076056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daniel Kasenberg, Jivko Sinapov, Matthias Scheutz, Shivam Goel, Vasanth Sarathy","submitted_at":"2020-12-24T00:31:02Z","abstract_excerpt":"Symbolic planning models allow decision-making agents to sequence actions in arbitrary ways to achieve a variety of goals in dynamic domains. However, they are typically handcrafted and tend to require precise formulations that are not robust to human error. Reinforcement learning (RL) approaches do not require such models, and instead learn domain dynamics by exploring the environment and collecting rewards. However, RL approaches tend to require millions of episodes of experience and often learn policies that are not easily transferable to other tasks. In this paper, we address one aspect of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.13037","kind":"arxiv","version":1},"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/2012.13037/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2012.13037","created_at":"2026-07-05T02:01:47.076126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.13037v1","created_at":"2026-07-05T02:01:47.076126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.13037","created_at":"2026-07-05T02:01:47.076126+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRMXXWVBJHK5","created_at":"2026-07-05T02:01:47.076126+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRMXXWVBJHK5DWPN","created_at":"2026-07-05T02:01:47.076126+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRMXXWVB","created_at":"2026-07-05T02:01:47.076126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18328","citing_title":"Recover, Discover, Plan: Learning Skills and Concepts from Robot Failures","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRMXXWVBJHK5DWPNE7BUQ2MHWM","json":"https://pith.science/pith/PRMXXWVBJHK5DWPNE7BUQ2MHWM.json","graph_json":"https://pith.science/api/pith-number/PRMXXWVBJHK5DWPNE7BUQ2MHWM/graph.json","events_json":"https://pith.science/api/pith-number/PRMXXWVBJHK5DWPNE7BUQ2MHWM/events.json","paper":"https://pith.science/paper/PRMXXWVB"},"agent_actions":{"view_html":"https://pith.science/pith/PRMXXWVBJHK5DWPNE7BUQ2MHWM","download_json":"https://pith.science/pith/PRMXXWVBJHK5DWPNE7BUQ2MHWM.json","view_paper":"https://pith.science/paper/PRMXXWVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.13037&json=true","fetch_graph":"https://pith.science/api/pith-number/PRMXXWVBJHK5DWPNE7BUQ2MHWM/graph.json","fetch_events":"https://pith.science/api/pith-number/PRMXXWVBJHK5DWPNE7BUQ2MHWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRMXXWVBJHK5DWPNE7BUQ2MHWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRMXXWVBJHK5DWPNE7BUQ2MHWM/action/storage_attestation","attest_author":"https://pith.science/pith/PRMXXWVBJHK5DWPNE7BUQ2MHWM/action/author_attestation","sign_citation":"https://pith.science/pith/PRMXXWVBJHK5DWPNE7BUQ2MHWM/action/citation_signature","submit_replication":"https://pith.science/pith/PRMXXWVBJHK5DWPNE7BUQ2MHWM/action/replication_record"}},"created_at":"2026-07-05T02:01:47.076126+00:00","updated_at":"2026-07-05T02:01:47.076126+00:00"}