{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q37YGDT2SJAPMYX4AM2AOEWRBB","short_pith_number":"pith:Q37YGDT2","canonical_record":{"source":{"id":"2411.13211","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T11:19:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"af9ecdf4e2af31bcebd8b2d436714b6d9ec1096f552681f48c0f1fac11b3502f","abstract_canon_sha256":"fdc68ae6497a9b442e42f00987c7d1c019c97812fa58aff03722006d6ebe4d18"},"schema_version":"1.0"},"canonical_sha256":"86ff830e7a9240f662fc03340712d1087bdf60ec669281d5674544da0273861c","source":{"kind":"arxiv","id":"2411.13211","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13211","created_at":"2026-07-05T09:38:33Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13211v2","created_at":"2026-07-05T09:38:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13211","created_at":"2026-07-05T09:38:33Z"},{"alias_kind":"pith_short_12","alias_value":"Q37YGDT2SJAP","created_at":"2026-07-05T09:38:33Z"},{"alias_kind":"pith_short_16","alias_value":"Q37YGDT2SJAPMYX4","created_at":"2026-07-05T09:38:33Z"},{"alias_kind":"pith_short_8","alias_value":"Q37YGDT2","created_at":"2026-07-05T09:38:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q37YGDT2SJAPMYX4AM2AOEWRBB","target":"record","payload":{"canonical_record":{"source":{"id":"2411.13211","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T11:19:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"af9ecdf4e2af31bcebd8b2d436714b6d9ec1096f552681f48c0f1fac11b3502f","abstract_canon_sha256":"fdc68ae6497a9b442e42f00987c7d1c019c97812fa58aff03722006d6ebe4d18"},"schema_version":"1.0"},"canonical_sha256":"86ff830e7a9240f662fc03340712d1087bdf60ec669281d5674544da0273861c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:33.252703Z","signature_b64":"fOCA5KmAk23T47JRGVwwtWKYp4xu7WM+zFuzk/kpifQjxd6h5KMSEu5W6y5S0MpRXHWUXmPD4wxyt5mtHHlEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86ff830e7a9240f662fc03340712d1087bdf60ec669281d5674544da0273861c","last_reissued_at":"2026-07-05T09:38:33.252215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:33.252215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.13211","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:38:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iX8331eD901z7GJhtnfrLiLbBNU69QKg1/oSQpUU7Bj9ggkQM3uGyCvbZ8yJwcYxkYBJ2wICp3kotlosEm5GAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:05:36.809683Z"},"content_sha256":"d476c0fb064ced6324b79030473831c434b44068eab35e3203867fdcd241e229","schema_version":"1.0","event_id":"sha256:d476c0fb064ced6324b79030473831c434b44068eab35e3203867fdcd241e229"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q37YGDT2SJAPMYX4AM2AOEWRBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ViSTa Dataset: Do vision-language models understand sequential tasks?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Lindner, Evan Ryan Gunter, Ev\\v{z}en Wybitul, Mikhail Seleznyov","submitted_at":"2024-11-20T11:19:22Z","abstract_excerpt":"Using vision-language models (VLMs) as reward models in reinforcement learning holds promise for reducing costs and improving safety. So far, VLM reward models have only been used for goal-oriented tasks, where the agent must reach a particular final outcome. We explore VLMs' potential to supervise tasks that cannot be scored by the final state alone. To this end, we introduce ViSTa, a dataset for evaluating Vision-based understanding of Sequential Tasks. ViSTa comprises over 4,000 videos with step-by-step descriptions in virtual home, Minecraft, and real-world environments. Its novel hierarch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13211","kind":"arxiv","version":2},"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/2411.13211/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:38:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FDCqiCpNkv+U1eOqRqSBZiCeepR51eNzs429E/ajRPxP9Awz8w9mFsDPkXnY/TCGRXmvnyA6qM+USPZXkOR5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:05:36.810267Z"},"content_sha256":"62a4d67fdc6122c3cf69128ec744f399e43f9b7bafc1df88371aacd41cffc319","schema_version":"1.0","event_id":"sha256:62a4d67fdc6122c3cf69128ec744f399e43f9b7bafc1df88371aacd41cffc319"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q37YGDT2SJAPMYX4AM2AOEWRBB/bundle.json","state_url":"https://pith.science/pith/Q37YGDT2SJAPMYX4AM2AOEWRBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q37YGDT2SJAPMYX4AM2AOEWRBB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T04:05:36Z","links":{"resolver":"https://pith.science/pith/Q37YGDT2SJAPMYX4AM2AOEWRBB","bundle":"https://pith.science/pith/Q37YGDT2SJAPMYX4AM2AOEWRBB/bundle.json","state":"https://pith.science/pith/Q37YGDT2SJAPMYX4AM2AOEWRBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q37YGDT2SJAPMYX4AM2AOEWRBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q37YGDT2SJAPMYX4AM2AOEWRBB","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":"fdc68ae6497a9b442e42f00987c7d1c019c97812fa58aff03722006d6ebe4d18","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T11:19:22Z","title_canon_sha256":"af9ecdf4e2af31bcebd8b2d436714b6d9ec1096f552681f48c0f1fac11b3502f"},"schema_version":"1.0","source":{"id":"2411.13211","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13211","created_at":"2026-07-05T09:38:33Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13211v2","created_at":"2026-07-05T09:38:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13211","created_at":"2026-07-05T09:38:33Z"},{"alias_kind":"pith_short_12","alias_value":"Q37YGDT2SJAP","created_at":"2026-07-05T09:38:33Z"},{"alias_kind":"pith_short_16","alias_value":"Q37YGDT2SJAPMYX4","created_at":"2026-07-05T09:38:33Z"},{"alias_kind":"pith_short_8","alias_value":"Q37YGDT2","created_at":"2026-07-05T09:38:33Z"}],"graph_snapshots":[{"event_id":"sha256:62a4d67fdc6122c3cf69128ec744f399e43f9b7bafc1df88371aacd41cffc319","target":"graph","created_at":"2026-07-05T09:38:33Z","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/2411.13211/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using vision-language models (VLMs) as reward models in reinforcement learning holds promise for reducing costs and improving safety. So far, VLM reward models have only been used for goal-oriented tasks, where the agent must reach a particular final outcome. We explore VLMs' potential to supervise tasks that cannot be scored by the final state alone. To this end, we introduce ViSTa, a dataset for evaluating Vision-based understanding of Sequential Tasks. ViSTa comprises over 4,000 videos with step-by-step descriptions in virtual home, Minecraft, and real-world environments. Its novel hierarch","authors_text":"David Lindner, Evan Ryan Gunter, Ev\\v{z}en Wybitul, Mikhail Seleznyov","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T11:19:22Z","title":"ViSTa Dataset: Do vision-language models understand sequential tasks?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13211","kind":"arxiv","version":2},"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:d476c0fb064ced6324b79030473831c434b44068eab35e3203867fdcd241e229","target":"record","created_at":"2026-07-05T09:38:33Z","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":"fdc68ae6497a9b442e42f00987c7d1c019c97812fa58aff03722006d6ebe4d18","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T11:19:22Z","title_canon_sha256":"af9ecdf4e2af31bcebd8b2d436714b6d9ec1096f552681f48c0f1fac11b3502f"},"schema_version":"1.0","source":{"id":"2411.13211","kind":"arxiv","version":2}},"canonical_sha256":"86ff830e7a9240f662fc03340712d1087bdf60ec669281d5674544da0273861c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86ff830e7a9240f662fc03340712d1087bdf60ec669281d5674544da0273861c","first_computed_at":"2026-07-05T09:38:33.252215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:33.252215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fOCA5KmAk23T47JRGVwwtWKYp4xu7WM+zFuzk/kpifQjxd6h5KMSEu5W6y5S0MpRXHWUXmPD4wxyt5mtHHlEDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:33.252703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13211","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d476c0fb064ced6324b79030473831c434b44068eab35e3203867fdcd241e229","sha256:62a4d67fdc6122c3cf69128ec744f399e43f9b7bafc1df88371aacd41cffc319"],"state_sha256":"2dcb13f7da6adcd854e8679ecc3f84b50330502a3ed06bc7cc1333b2eeb6ed18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2iQLKRP3lZlxsnbsR0nda8KMO6wWs+fdD7Fwaw7ffQ+4owRh3fxKFE30sA04Z6fd0TpYJ+yLELpow/YKVApiCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:05:36.814423Z","bundle_sha256":"8f130bc56847ec529c7e35cbdd45d6cb69a6b04b3d15bfb8e6988208f0ae1614"}}