{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5MQZFVEFUTKRRCVJIB2PNQ56KB","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":"68e99364031898fdc622710efaadcddd465d640a7f0bbf48e0d5a4b3560077da","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T16:54:11Z","title_canon_sha256":"34ba897f533d6700fa067dd0e61e8ec81e16ec1bc4a8a02f7bdbd789bba80964"},"schema_version":"1.0","source":{"id":"2303.07280","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.07280","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"arxiv_version","alias_value":"2303.07280v1","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07280","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"pith_short_12","alias_value":"5MQZFVEFUTKR","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"pith_short_16","alias_value":"5MQZFVEFUTKRRCVJ","created_at":"2026-07-05T05:50:34Z"},{"alias_kind":"pith_short_8","alias_value":"5MQZFVEF","created_at":"2026-07-05T05:50:34Z"}],"graph_snapshots":[{"event_id":"sha256:f79e14dcf5372d35dc728c23278414c71f8e42efc86aa54fee6e60e702543532","target":"graph","created_at":"2026-07-05T05:50:34Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.07280/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detecting successful behaviour is crucial for training intelligent agents. As such, generalisable reward models are a prerequisite for agents that can learn to generalise their behaviour. In this work we focus on developing robust success detectors that leverage large, pretrained vision-language models (Flamingo, Alayrac et al. (2022)) and human reward annotations. Concretely, we treat success detection as a visual question answering (VQA) problem, denoted SuccessVQA. We study success detection across three vastly different domains: (i) interactive language-conditioned agents in a simulated ho","authors_text":"Akhil Raju, Felix Hill, Jessica Landon, Ksenia Konyushkova, Misha Denil, Nando de Freitas, Serkan Cabi, Yuqing Du","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T16:54:11Z","title":"Vision-Language Models as Success Detectors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07280","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:62aadb28ff899e11451c7ed38dea4a626e0e8bfc1f2a1310e86b8c078b8a17a4","target":"record","created_at":"2026-07-05T05:50:34Z","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":"68e99364031898fdc622710efaadcddd465d640a7f0bbf48e0d5a4b3560077da","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-13T16:54:11Z","title_canon_sha256":"34ba897f533d6700fa067dd0e61e8ec81e16ec1bc4a8a02f7bdbd789bba80964"},"schema_version":"1.0","source":{"id":"2303.07280","kind":"arxiv","version":1}},"canonical_sha256":"eb2192d485a4d5188aa94074f6c3be5045135668917b21236a0ecca40d270964","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb2192d485a4d5188aa94074f6c3be5045135668917b21236a0ecca40d270964","first_computed_at":"2026-07-05T05:50:34.501964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:50:34.501964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QQJxfPNcWoBA4Aq1hktCgfUSvcaA1WVhUe5u8OhSHhuMFyZVwPcICP9jcfa8gnHf62mBdHwiITh0LdTSeE3hAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:50:34.502410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.07280","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62aadb28ff899e11451c7ed38dea4a626e0e8bfc1f2a1310e86b8c078b8a17a4","sha256:f79e14dcf5372d35dc728c23278414c71f8e42efc86aa54fee6e60e702543532"],"state_sha256":"1f0347dde97ed342a20399d8bb187bc39ec6937de527155b46e236b3b78f0c08"}