{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Z5EA7PY63CUV3EN7ZSR77B5FQ2","short_pith_number":"pith:Z5EA7PY6","schema_version":"1.0","canonical_sha256":"cf480fbf1ed8a95d91bfcca3ff87a58693ffc7ea269d9c76dc826247a2945ee0","source":{"kind":"arxiv","id":"2306.12860","version":1},"attestation_state":"computed","paper":{"title":"Learning from Visual Observation via Offline Pretrained State-to-Go Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bohan Zhou, Jiechuan Jiang, Ke Li, Zongqing Lu","submitted_at":"2023-06-22T13:14:59Z","abstract_excerpt":"Learning from visual observation (LfVO), aiming at recovering policies from only visual observation data, is promising yet a challenging problem. Existing LfVO approaches either only adopt inefficient online learning schemes or require additional task-specific information like goal states, making them not suited for open-ended tasks. To address these issues, we propose a two-stage framework for learning from visual observation. In the first stage, we introduce and pretrain State-to-Go (STG) Transformer offline to predict and differentiate latent transitions of demonstrations. Subsequently, in "},"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":"2306.12860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-22T13:14:59Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e3731abc02b62cebc217c3cfd94642a58b3ab6ac65e5cecdb1eb1ec83296849e","abstract_canon_sha256":"1c1d5cff899795c94fc0c877547cf7580ca175f352eb60a80cc84ae46f341275"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:49.006608Z","signature_b64":"/bFItdFmFrpQBLCPVpXNJsJN0Kro3ijoIzGv8enyD81/BSqvE6vAEQU1cIJKGKE1cfMs1gJWFPfPfS3/bQhGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf480fbf1ed8a95d91bfcca3ff87a58693ffc7ea269d9c76dc826247a2945ee0","last_reissued_at":"2026-07-05T06:23:49.006087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:49.006087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from Visual Observation via Offline Pretrained State-to-Go Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bohan Zhou, Jiechuan Jiang, Ke Li, Zongqing Lu","submitted_at":"2023-06-22T13:14:59Z","abstract_excerpt":"Learning from visual observation (LfVO), aiming at recovering policies from only visual observation data, is promising yet a challenging problem. Existing LfVO approaches either only adopt inefficient online learning schemes or require additional task-specific information like goal states, making them not suited for open-ended tasks. To address these issues, we propose a two-stage framework for learning from visual observation. In the first stage, we introduce and pretrain State-to-Go (STG) Transformer offline to predict and differentiate latent transitions of demonstrations. Subsequently, in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12860","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/2306.12860/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":"2306.12860","created_at":"2026-07-05T06:23:49.006158+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12860v1","created_at":"2026-07-05T06:23:49.006158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12860","created_at":"2026-07-05T06:23:49.006158+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5EA7PY63CUV","created_at":"2026-07-05T06:23:49.006158+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5EA7PY63CUV3EN7","created_at":"2026-07-05T06:23:49.006158+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5EA7PY6","created_at":"2026-07-05T06:23:49.006158+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00796","citing_title":"Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z5EA7PY63CUV3EN7ZSR77B5FQ2","json":"https://pith.science/pith/Z5EA7PY63CUV3EN7ZSR77B5FQ2.json","graph_json":"https://pith.science/api/pith-number/Z5EA7PY63CUV3EN7ZSR77B5FQ2/graph.json","events_json":"https://pith.science/api/pith-number/Z5EA7PY63CUV3EN7ZSR77B5FQ2/events.json","paper":"https://pith.science/paper/Z5EA7PY6"},"agent_actions":{"view_html":"https://pith.science/pith/Z5EA7PY63CUV3EN7ZSR77B5FQ2","download_json":"https://pith.science/pith/Z5EA7PY63CUV3EN7ZSR77B5FQ2.json","view_paper":"https://pith.science/paper/Z5EA7PY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12860&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5EA7PY63CUV3EN7ZSR77B5FQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5EA7PY63CUV3EN7ZSR77B5FQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5EA7PY63CUV3EN7ZSR77B5FQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5EA7PY63CUV3EN7ZSR77B5FQ2/action/storage_attestation","attest_author":"https://pith.science/pith/Z5EA7PY63CUV3EN7ZSR77B5FQ2/action/author_attestation","sign_citation":"https://pith.science/pith/Z5EA7PY63CUV3EN7ZSR77B5FQ2/action/citation_signature","submit_replication":"https://pith.science/pith/Z5EA7PY63CUV3EN7ZSR77B5FQ2/action/replication_record"}},"created_at":"2026-07-05T06:23:49.006158+00:00","updated_at":"2026-07-05T06:23:49.006158+00:00"}