{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BT53RUBKX2S2F6TZVUH6ZHY73J","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":"55071045150d700750b486967efb4f4d2bc997ee4a7398d4dbdbca1d96147bfc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-24T06:20:08Z","title_canon_sha256":"77e965a3a6d224ca71f5f03b93a464c5c822c2efbf92f4744528c62c7d76a00e"},"schema_version":"1.0","source":{"id":"2504.17282","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17282","created_at":"2026-07-05T10:53:25Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17282v1","created_at":"2026-07-05T10:53:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17282","created_at":"2026-07-05T10:53:25Z"},{"alias_kind":"pith_short_12","alias_value":"BT53RUBKX2S2","created_at":"2026-07-05T10:53:25Z"},{"alias_kind":"pith_short_16","alias_value":"BT53RUBKX2S2F6TZ","created_at":"2026-07-05T10:53:25Z"},{"alias_kind":"pith_short_8","alias_value":"BT53RUBK","created_at":"2026-07-05T10:53:25Z"}],"graph_snapshots":[{"event_id":"sha256:77c3949826115160b23f5913eb00210c2ee7c3c07ea77dc71fb2dd0852bedf0c","target":"graph","created_at":"2026-07-05T10:53:25Z","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/2504.17282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agents that can autonomously navigate the web through a graphical user interface (GUI) using a unified action space (e.g., mouse and keyboard actions) can require very large amounts of domain-specific expert demonstrations to achieve good performance. Low sample efficiency is often exacerbated in sparse-reward and large-action-space environments, such as a web GUI, where only a few actions are relevant in any given situation. In this work, we consider the low-data regime, with limited or no access to expert behavior. To enable sample-efficient learning, we explore the effect of constraining th","authors_text":"Ankit Anand, David Venuto, Doina Precup, Flemming Kondrup, Khimya Khetarpal, Lynn Cherif","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-24T06:20:08Z","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17282","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":"sha256:67d5a58b8821965ac15f91172eb9867d6fdf971632ba6a454fd5f8e44c8c0d9a","target":"record","created_at":"2026-07-05T10:53:25Z","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":"55071045150d700750b486967efb4f4d2bc997ee4a7398d4dbdbca1d96147bfc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-24T06:20:08Z","title_canon_sha256":"77e965a3a6d224ca71f5f03b93a464c5c822c2efbf92f4744528c62c7d76a00e"},"schema_version":"1.0","source":{"id":"2504.17282","kind":"arxiv","version":1}},"canonical_sha256":"0cfbb8d02abea5a2fa79ad0fec9f1fda552a9c98e5ab4ae4257a1910c4bf21ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cfbb8d02abea5a2fa79ad0fec9f1fda552a9c98e5ab4ae4257a1910c4bf21ef","first_computed_at":"2026-07-05T10:53:25.844641Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:25.844641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yLgOR9m7WPfcvIpMt/tg/a05olkp9psz5gsdeDt8ewZvZDauBjOajPjhOFbOQNLMhY3/QAODqdWJ5dLM/ORnDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:25.845188Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.17282","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67d5a58b8821965ac15f91172eb9867d6fdf971632ba6a454fd5f8e44c8c0d9a","sha256:77c3949826115160b23f5913eb00210c2ee7c3c07ea77dc71fb2dd0852bedf0c"],"state_sha256":"3a8c979e2e16b4e9eed59fab7938fb5538114dc20698490221a58fec75ce0b50"}