{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X55KYRKLTUXENQAM5JGYRX4RCY","short_pith_number":"pith:X55KYRKL","schema_version":"1.0","canonical_sha256":"bf7aac454b9d2e46c00cea4d88df91161d8d91bfc95ed102c0131c7a591df533","source":{"kind":"arxiv","id":"2507.06701","version":1},"attestation_state":"computed","paper":{"title":"Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","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","submitted_at":"2025-07-09T09:55:23Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.06701","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T09:55:23Z","cross_cats_sorted":[],"title_canon_sha256":"0ad8488d7e65e38822e9b7c5b74b5fa57cf7be97b1cb038e7ea872e3aa0bb11d","abstract_canon_sha256":"bd2c5d308b743d9eaf41003bd0de7e6b2c76da6730296002d547293473ff20a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:21.557561Z","signature_b64":"Tjw6ociT1ApSUh/9UcTxs3PrZWIecMfrAvV/Tmnu2ctrWB1k2BoM4DoaGagXHh6czmBQWMkGPQ6OoQO34iG7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf7aac454b9d2e46c00cea4d88df91161d8d91bfc95ed102c0131c7a591df533","last_reissued_at":"2026-07-05T11:34:21.557074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:21.557074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","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","submitted_at":"2025-07-09T09:55:23Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06701","kind":"arxiv","version":1},"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/2507.06701/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.06701","created_at":"2026-07-05T11:34:21.557140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06701v1","created_at":"2026-07-05T11:34:21.557140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06701","created_at":"2026-07-05T11:34:21.557140+00:00"},{"alias_kind":"pith_short_12","alias_value":"X55KYRKLTUXE","created_at":"2026-07-05T11:34:21.557140+00:00"},{"alias_kind":"pith_short_16","alias_value":"X55KYRKLTUXENQAM","created_at":"2026-07-05T11:34:21.557140+00:00"},{"alias_kind":"pith_short_8","alias_value":"X55KYRKL","created_at":"2026-07-05T11:34:21.557140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X55KYRKLTUXENQAM5JGYRX4RCY","json":"https://pith.science/pith/X55KYRKLTUXENQAM5JGYRX4RCY.json","graph_json":"https://pith.science/api/pith-number/X55KYRKLTUXENQAM5JGYRX4RCY/graph.json","events_json":"https://pith.science/api/pith-number/X55KYRKLTUXENQAM5JGYRX4RCY/events.json","paper":"https://pith.science/paper/X55KYRKL"},"agent_actions":{"view_html":"https://pith.science/pith/X55KYRKLTUXENQAM5JGYRX4RCY","download_json":"https://pith.science/pith/X55KYRKLTUXENQAM5JGYRX4RCY.json","view_paper":"https://pith.science/paper/X55KYRKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06701&json=true","fetch_graph":"https://pith.science/api/pith-number/X55KYRKLTUXENQAM5JGYRX4RCY/graph.json","fetch_events":"https://pith.science/api/pith-number/X55KYRKLTUXENQAM5JGYRX4RCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X55KYRKLTUXENQAM5JGYRX4RCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X55KYRKLTUXENQAM5JGYRX4RCY/action/storage_attestation","attest_author":"https://pith.science/pith/X55KYRKLTUXENQAM5JGYRX4RCY/action/author_attestation","sign_citation":"https://pith.science/pith/X55KYRKLTUXENQAM5JGYRX4RCY/action/citation_signature","submit_replication":"https://pith.science/pith/X55KYRKLTUXENQAM5JGYRX4RCY/action/replication_record"}},"created_at":"2026-07-05T11:34:21.557140+00:00","updated_at":"2026-07-05T11:34:21.557140+00:00"}