{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:N6PYG5VGWTBM4IFTG5R72R6MHQ","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":"bc2030086bfb21fa418906a4761ca673c0a4f57996c16a1404e8d04b4f444a73","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-09-30T18:14:07Z","title_canon_sha256":"82ca43c714efd6e9ab9ee0edf91094be3f2314412d346a241b29ff3a0828b518"},"schema_version":"1.0","source":{"id":"2210.00030","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.00030","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2210.00030v2","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00030","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"N6PYG5VGWTBM","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"N6PYG5VGWTBM4IFT","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"N6PYG5VG","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:67e2e564d67b9622276d6762a3c3b94dc59b2d104ee3da36bdc1efbe12acbc02","target":"graph","created_at":"2026-05-17T23:38:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Trained on large-scale Ego4D human videos and without any fine-tuning on in-domain, task-specific data, VIP's frozen representation can provide dense visual reward for an extensive set of simulated and real-robot tasks, enabling diverse reward-based visual control methods and significantly outperforming all prior pre-trained representations."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a value function learned solely from unlabeled human videos (via an action-free dual goal-conditioned objective) will produce rewards that remain effective when transferred to robotic embodiments and dynamics without further adaptation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"VIP learns a visual embedding from human videos whose distance defines dense, smooth rewards for arbitrary goal-image robot tasks without task-specific fine-tuning."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"VIP pre-trains a visual representation on unlabeled human videos that supplies dense rewards for many robot tasks without any fine-tuning."}],"snapshot_sha256":"7081886dfdfbd5fd18d4d774b4cc63125f1bd56d249e8c5522e05a7e35d571be"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1b1ef0bd48678cdddb68d27b987358f05254900d3727703f35c67576ef475588"},"paper":{"abstract_excerpt":"Reward and representation learning are two long-standing challenges for learning an expanding set of robot manipulation skills from sensory observations. Given the inherent cost and scarcity of in-domain, task-specific robot data, learning from large, diverse, offline human videos has emerged as a promising path towards acquiring a generally useful visual representation for control; however, how these human videos can be used for general-purpose reward learning remains an open question. We introduce $\\textbf{V}$alue-$\\textbf{I}$mplicit $\\textbf{P}$re-training (VIP), a self-supervised pre-train","authors_text":"Amy Zhang, Dinesh Jayaraman, Osbert Bastani, Shagun Sodhani, Vikash Kumar, Yecheng Jason Ma","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"VIP pre-trains a visual representation on unlabeled human videos that supplies dense rewards for many robot tasks without any fine-tuning.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-09-30T18:14:07Z","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"},"references":{"count":50,"internal_anchors":12,"resolved_work":50,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Human-to-robot imitation in the wild","work_id":"12b82950-4daa-40b8-bc3f-f94edd67d9db","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"arXiv preprint arXiv:2104.07749 , year=","work_id":"9f8cacca-a18f-412d-9656-7a5274a3531c","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"in-the- wild","work_id":"01177b56-50d1-4b53-8d24-b3f2b8e7809d","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Imagenet: A large-scale hierarchical image database","work_id":"5d051359-ffec-4827-bbc5-34901db20177","year":2009},{"cited_arxiv_id":"1810.04805","doi":"","is_internal_anchor":true,"ref_index":5,"title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","work_id":"ed240a10-5b19-406c-baa5-30803f465785","year":null}],"snapshot_sha256":"a461cc54d14940840e47210dbc36444b2a775bc158921bd108db6c52eb80dee8"},"source":{"id":"2210.00030","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T04:38:27.027004Z","id":"69fd1e82-176a-4ef7-a65a-792e795b7c3e","model_set":{"reader":"grok-4.3"},"one_line_summary":"VIP learns a visual embedding from human videos whose distance defines dense, smooth rewards for arbitrary goal-image robot tasks without task-specific fine-tuning.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"VIP pre-trains a visual representation on unlabeled human videos that supplies dense rewards for many robot tasks without any fine-tuning.","strongest_claim":"Trained on large-scale Ego4D human videos and without any fine-tuning on in-domain, task-specific data, VIP's frozen representation can provide dense visual reward for an extensive set of simulated and real-robot tasks, enabling diverse reward-based visual control methods and significantly outperforming all prior pre-trained representations.","weakest_assumption":"That a value function learned solely from unlabeled human videos (via an action-free dual goal-conditioned objective) will produce rewards that remain effective when transferred to robotic embodiments and dynamics without further adaptation."}},"verdict_id":"69fd1e82-176a-4ef7-a65a-792e795b7c3e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2383d44be75fe68701481cac016f2bdb0bae3d650a49d0346e35d01ab32db79c","target":"record","created_at":"2026-05-17T23:38:53Z","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":"bc2030086bfb21fa418906a4761ca673c0a4f57996c16a1404e8d04b4f444a73","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-09-30T18:14:07Z","title_canon_sha256":"82ca43c714efd6e9ab9ee0edf91094be3f2314412d346a241b29ff3a0828b518"},"schema_version":"1.0","source":{"id":"2210.00030","kind":"arxiv","version":2}},"canonical_sha256":"6f9f8376a6b4c2ce20b33763fd47cc3c21aff47ef3529e6361252bbae0bff9ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f9f8376a6b4c2ce20b33763fd47cc3c21aff47ef3529e6361252bbae0bff9ff","first_computed_at":"2026-05-17T23:38:53.500659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:53.500659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5aPiIm0Q31YKzhXFxzZA0pMeYUpN1i8BOEIkU89VxDB92LIGXv4SETYugzFiGdIE2TWUJPjgNB2Z5WtqBvrqDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:53.501332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.00030","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2383d44be75fe68701481cac016f2bdb0bae3d650a49d0346e35d01ab32db79c","sha256:67e2e564d67b9622276d6762a3c3b94dc59b2d104ee3da36bdc1efbe12acbc02"],"state_sha256":"e69a81af42da4d23d389b6f18bf7bba6c732a397ed86234119870c6c4de04e20"}