{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SG7AWKCZNG5YPOXFGUSBGRNXDA","short_pith_number":"pith:SG7AWKCZ","schema_version":"1.0","canonical_sha256":"91be0b285969bb87bae535241345b7180a5a6de5fe122e48ff2523d875f0430c","source":{"kind":"arxiv","id":"1709.10489","version":3},"attestation_state":"computed","paper":{"title":"Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Adam Villaflor, Bosen Ding, Gregory Kahn, Pieter Abbeel, Sergey Levine","submitted_at":"2017-09-29T16:47:14Z","abstract_excerpt":"Enabling robots to autonomously navigate complex environments is essential for real-world deployment. Prior methods approach this problem by having the robot maintain an internal map of the world, and then use a localization and planning method to navigate through the internal map. However, these approaches often include a variety of assumptions, are computationally intensive, and do not learn from failures. In contrast, learning-based methods improve as the robot acts in the environment, but are difficult to deploy in the real-world due to their high sample complexity. To address the need to "},"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":"1709.10489","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-29T16:47:14Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"296d49e8b937aeb405d2fcbd71e3ae91af930753824f2a97d682fd7fb85c3967","abstract_canon_sha256":"5ca142c66bf6a5754c7447c5f5bf6cd57fc1b190c56f72404c116f7f40b48583"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:42.028311Z","signature_b64":"Ec8nVqPGAhGLBK5ZKsZADlj4mQykNXdtM3hCSjYC4SmdwzzxOIk49IAm2QmRwFtSs7pXBdzV8cX6pWLpXaRzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91be0b285969bb87bae535241345b7180a5a6de5fe122e48ff2523d875f0430c","last_reissued_at":"2026-05-18T00:15:42.027706Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:42.027706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Adam Villaflor, Bosen Ding, Gregory Kahn, Pieter Abbeel, Sergey Levine","submitted_at":"2017-09-29T16:47:14Z","abstract_excerpt":"Enabling robots to autonomously navigate complex environments is essential for real-world deployment. Prior methods approach this problem by having the robot maintain an internal map of the world, and then use a localization and planning method to navigate through the internal map. However, these approaches often include a variety of assumptions, are computationally intensive, and do not learn from failures. In contrast, learning-based methods improve as the robot acts in the environment, but are difficult to deploy in the real-world due to their high sample complexity. To address the need to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.10489","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":""},"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":"1709.10489","created_at":"2026-05-18T00:15:42.027803+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.10489v3","created_at":"2026-05-18T00:15:42.027803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.10489","created_at":"2026-05-18T00:15:42.027803+00:00"},{"alias_kind":"pith_short_12","alias_value":"SG7AWKCZNG5Y","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SG7AWKCZNG5YPOXF","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SG7AWKCZ","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.01713","citing_title":"End-to-end Decentralized Multi-robot Navigation in Unknown Complex Environments via Deep Reinforcement Learning","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SG7AWKCZNG5YPOXFGUSBGRNXDA","json":"https://pith.science/pith/SG7AWKCZNG5YPOXFGUSBGRNXDA.json","graph_json":"https://pith.science/api/pith-number/SG7AWKCZNG5YPOXFGUSBGRNXDA/graph.json","events_json":"https://pith.science/api/pith-number/SG7AWKCZNG5YPOXFGUSBGRNXDA/events.json","paper":"https://pith.science/paper/SG7AWKCZ"},"agent_actions":{"view_html":"https://pith.science/pith/SG7AWKCZNG5YPOXFGUSBGRNXDA","download_json":"https://pith.science/pith/SG7AWKCZNG5YPOXFGUSBGRNXDA.json","view_paper":"https://pith.science/paper/SG7AWKCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.10489&json=true","fetch_graph":"https://pith.science/api/pith-number/SG7AWKCZNG5YPOXFGUSBGRNXDA/graph.json","fetch_events":"https://pith.science/api/pith-number/SG7AWKCZNG5YPOXFGUSBGRNXDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SG7AWKCZNG5YPOXFGUSBGRNXDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SG7AWKCZNG5YPOXFGUSBGRNXDA/action/storage_attestation","attest_author":"https://pith.science/pith/SG7AWKCZNG5YPOXFGUSBGRNXDA/action/author_attestation","sign_citation":"https://pith.science/pith/SG7AWKCZNG5YPOXFGUSBGRNXDA/action/citation_signature","submit_replication":"https://pith.science/pith/SG7AWKCZNG5YPOXFGUSBGRNXDA/action/replication_record"}},"created_at":"2026-05-18T00:15:42.027803+00:00","updated_at":"2026-05-18T00:15:42.027803+00:00"}