{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X55KYRKLTUXENQAM5JGYRX4RCY","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":"bd2c5d308b743d9eaf41003bd0de7e6b2c76da6730296002d547293473ff20a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T09:55:23Z","title_canon_sha256":"0ad8488d7e65e38822e9b7c5b74b5fa57cf7be97b1cb038e7ea872e3aa0bb11d"},"schema_version":"1.0","source":{"id":"2507.06701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06701","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06701v1","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06701","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"pith_short_12","alias_value":"X55KYRKLTUXE","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"pith_short_16","alias_value":"X55KYRKLTUXENQAM","created_at":"2026-07-05T11:34:21Z"},{"alias_kind":"pith_short_8","alias_value":"X55KYRKL","created_at":"2026-07-05T11:34:21Z"}],"graph_snapshots":[{"event_id":"sha256:2bc98c2c22c106ff9e739e5b4d6f717ae63a83d821770e9ba4c9af91d41496d0","target":"graph","created_at":"2026-07-05T11:34:21Z","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/2507.06701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation Learning from Observation (IfO) offers a powerful way to learn behaviors at large-scale: Unlike behavior cloning or offline reinforcement learning, IfO can leverage action-free demonstrations and thus circumvents the need for costly action-labeled demonstrations or reward functions. However, current IfO research focuses on idealized scenarios with mostly bimodal-quality data distributions, restricting the meaningfulness of the results. In contrast, this paper investigates more nuanced distributions and introduces a method to learn from such data, moving closer to a paradigm in which ","authors_text":"Abbas Abdolmaleki, Jost Tobias Springenberg, Markus Wulfmeier, Martina Zambelli, Martin Riedmiller, Michael Bloesch, Nicolas Heess, Philemon Brakel, Roland Hafner, Todor Davchev, William F Whitney","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T09:55:23Z","title":"Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06701","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":"sha256:2c53569fa443e8bbf6582421fa09c6391865e2bf9db9515a32bf46e9fff33d34","target":"record","created_at":"2026-07-05T11:34:21Z","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":"bd2c5d308b743d9eaf41003bd0de7e6b2c76da6730296002d547293473ff20a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T09:55:23Z","title_canon_sha256":"0ad8488d7e65e38822e9b7c5b74b5fa57cf7be97b1cb038e7ea872e3aa0bb11d"},"schema_version":"1.0","source":{"id":"2507.06701","kind":"arxiv","version":1}},"canonical_sha256":"bf7aac454b9d2e46c00cea4d88df91161d8d91bfc95ed102c0131c7a591df533","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf7aac454b9d2e46c00cea4d88df91161d8d91bfc95ed102c0131c7a591df533","first_computed_at":"2026-07-05T11:34:21.557074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:21.557074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tjw6ociT1ApSUh/9UcTxs3PrZWIecMfrAvV/Tmnu2ctrWB1k2BoM4DoaGagXHh6czmBQWMkGPQ6OoQO34iG7Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:21.557561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c53569fa443e8bbf6582421fa09c6391865e2bf9db9515a32bf46e9fff33d34","sha256:2bc98c2c22c106ff9e739e5b4d6f717ae63a83d821770e9ba4c9af91d41496d0"],"state_sha256":"927f6b8ef356418a9972bf2380755593d452ad26b201741bb24c65de4efd5ba7"}