{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HE4GMHXHJUUOY3IWTPDGZI5KYL","short_pith_number":"pith:HE4GMHXH","schema_version":"1.0","canonical_sha256":"3938661ee74d28ec6d169bc66ca3aac2e6f38b866f2e9371e6b777c6bf329908","source":{"kind":"arxiv","id":"2312.03446","version":1},"attestation_state":"computed","paper":{"title":"Visual Hindsight Self-Imitation Learning for Interactive Navigation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Byoung-Tak Zhang, Kibeom Kim, Kisung Shin, Minsu Lee, Min Whoo Lee, Moonhoen Lee","submitted_at":"2023-12-05T05:34:12Z","abstract_excerpt":"Interactive visual navigation tasks, which involve following instructions to reach and interact with specific targets, are challenging not only because successful experiences are very rare but also because the complex visual inputs require a substantial number of samples. Previous methods for these tasks often rely on intricately designed dense rewards or the use of expensive expert data for imitation learning. To tackle these challenges, we propose a novel approach, Visual Hindsight Self-Imitation Learning (VHS) for enhancing sample efficiency through hindsight goal re-labeling and self-imita"},"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":"2312.03446","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-05T05:34:12Z","cross_cats_sorted":[],"title_canon_sha256":"446c0c3f2671c817f1467df47b7995370655ee7247011f038ff8b811292e0f28","abstract_canon_sha256":"12354599c10d7387c0ff36f02bd3e3b0b0e611d789f75b22bd734baaf5045ec2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:08.782224Z","signature_b64":"yHM3rIxNnhnAEAUYS5yc5Nl0FjQHLMONDGfTx5o5n5O8sN/PGnMdnlmn8AyZg/A6tURxdpKlnQmK8w9sp5YWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3938661ee74d28ec6d169bc66ca3aac2e6f38b866f2e9371e6b777c6bf329908","last_reissued_at":"2026-07-05T08:34:08.781742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:08.781742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Hindsight Self-Imitation Learning for Interactive Navigation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Byoung-Tak Zhang, Kibeom Kim, Kisung Shin, Minsu Lee, Min Whoo Lee, Moonhoen Lee","submitted_at":"2023-12-05T05:34:12Z","abstract_excerpt":"Interactive visual navigation tasks, which involve following instructions to reach and interact with specific targets, are challenging not only because successful experiences are very rare but also because the complex visual inputs require a substantial number of samples. Previous methods for these tasks often rely on intricately designed dense rewards or the use of expensive expert data for imitation learning. To tackle these challenges, we propose a novel approach, Visual Hindsight Self-Imitation Learning (VHS) for enhancing sample efficiency through hindsight goal re-labeling and self-imita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03446","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/2312.03446/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":"2312.03446","created_at":"2026-07-05T08:34:08.781798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03446v1","created_at":"2026-07-05T08:34:08.781798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03446","created_at":"2026-07-05T08:34:08.781798+00:00"},{"alias_kind":"pith_short_12","alias_value":"HE4GMHXHJUUO","created_at":"2026-07-05T08:34:08.781798+00:00"},{"alias_kind":"pith_short_16","alias_value":"HE4GMHXHJUUOY3IW","created_at":"2026-07-05T08:34:08.781798+00:00"},{"alias_kind":"pith_short_8","alias_value":"HE4GMHXH","created_at":"2026-07-05T08:34:08.781798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.17842","citing_title":"From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HE4GMHXHJUUOY3IWTPDGZI5KYL","json":"https://pith.science/pith/HE4GMHXHJUUOY3IWTPDGZI5KYL.json","graph_json":"https://pith.science/api/pith-number/HE4GMHXHJUUOY3IWTPDGZI5KYL/graph.json","events_json":"https://pith.science/api/pith-number/HE4GMHXHJUUOY3IWTPDGZI5KYL/events.json","paper":"https://pith.science/paper/HE4GMHXH"},"agent_actions":{"view_html":"https://pith.science/pith/HE4GMHXHJUUOY3IWTPDGZI5KYL","download_json":"https://pith.science/pith/HE4GMHXHJUUOY3IWTPDGZI5KYL.json","view_paper":"https://pith.science/paper/HE4GMHXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03446&json=true","fetch_graph":"https://pith.science/api/pith-number/HE4GMHXHJUUOY3IWTPDGZI5KYL/graph.json","fetch_events":"https://pith.science/api/pith-number/HE4GMHXHJUUOY3IWTPDGZI5KYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HE4GMHXHJUUOY3IWTPDGZI5KYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HE4GMHXHJUUOY3IWTPDGZI5KYL/action/storage_attestation","attest_author":"https://pith.science/pith/HE4GMHXHJUUOY3IWTPDGZI5KYL/action/author_attestation","sign_citation":"https://pith.science/pith/HE4GMHXHJUUOY3IWTPDGZI5KYL/action/citation_signature","submit_replication":"https://pith.science/pith/HE4GMHXHJUUOY3IWTPDGZI5KYL/action/replication_record"}},"created_at":"2026-07-05T08:34:08.781798+00:00","updated_at":"2026-07-05T08:34:08.781798+00:00"}