{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:C7TTROWSLE7OPZO263EE3BT624","short_pith_number":"pith:C7TTROWS","schema_version":"1.0","canonical_sha256":"17e738bad2593ee7e5daf6c84d867ed70ed2cc1d14f322f0de607c7c1036e6ed","source":{"kind":"arxiv","id":"2205.12648","version":1},"attestation_state":"computed","paper":{"title":"Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aleksandra Faust, Honglak Lee, Hyunjae Woo, Izzeddin Gur, Jongwook Choi, lyubing qiang, Sungryull Sohn","submitted_at":"2022-05-25T10:44:25Z","abstract_excerpt":"We tackle real-world problems with complex structures beyond the pixel-based game or simulator. We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph that defines a set of subtasks and their dependencies that are unknown to the agent. Different from the previous meta-rl methods trying to directly infer the unstructured task embedding, our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks, and use it as a prior to improve the task inference in"},"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":"2205.12648","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-25T10:44:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c74955abfaf8fc529d1c792ca425d96c62a2d879972a934d218316330a84c303","abstract_canon_sha256":"6d0f6d75cde2ac8ae04b0bf4031a06a5ded20e1007058c5a0b044ccec7549771"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:28.452752Z","signature_b64":"c3b8ZaJM3yzwnDl3DP7mzvv3ImiNR/LJcNlrsX9srRk0mSd1LsowPvXcntF3b6c9fEv4h58bCisIxd37xT54BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17e738bad2593ee7e5daf6c84d867ed70ed2cc1d14f322f0de607c7c1036e6ed","last_reissued_at":"2026-07-05T04:26:28.452227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:28.452227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aleksandra Faust, Honglak Lee, Hyunjae Woo, Izzeddin Gur, Jongwook Choi, lyubing qiang, Sungryull Sohn","submitted_at":"2022-05-25T10:44:25Z","abstract_excerpt":"We tackle real-world problems with complex structures beyond the pixel-based game or simulator. We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph that defines a set of subtasks and their dependencies that are unknown to the agent. Different from the previous meta-rl methods trying to directly infer the unstructured task embedding, our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks, and use it as a prior to improve the task inference in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12648","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/2205.12648/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":"2205.12648","created_at":"2026-07-05T04:26:28.452300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12648v1","created_at":"2026-07-05T04:26:28.452300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12648","created_at":"2026-07-05T04:26:28.452300+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7TTROWSLE7O","created_at":"2026-07-05T04:26:28.452300+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7TTROWSLE7OPZO2","created_at":"2026-07-05T04:26:28.452300+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7TTROWS","created_at":"2026-07-05T04:26:28.452300+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/C7TTROWSLE7OPZO263EE3BT624","json":"https://pith.science/pith/C7TTROWSLE7OPZO263EE3BT624.json","graph_json":"https://pith.science/api/pith-number/C7TTROWSLE7OPZO263EE3BT624/graph.json","events_json":"https://pith.science/api/pith-number/C7TTROWSLE7OPZO263EE3BT624/events.json","paper":"https://pith.science/paper/C7TTROWS"},"agent_actions":{"view_html":"https://pith.science/pith/C7TTROWSLE7OPZO263EE3BT624","download_json":"https://pith.science/pith/C7TTROWSLE7OPZO263EE3BT624.json","view_paper":"https://pith.science/paper/C7TTROWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12648&json=true","fetch_graph":"https://pith.science/api/pith-number/C7TTROWSLE7OPZO263EE3BT624/graph.json","fetch_events":"https://pith.science/api/pith-number/C7TTROWSLE7OPZO263EE3BT624/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7TTROWSLE7OPZO263EE3BT624/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7TTROWSLE7OPZO263EE3BT624/action/storage_attestation","attest_author":"https://pith.science/pith/C7TTROWSLE7OPZO263EE3BT624/action/author_attestation","sign_citation":"https://pith.science/pith/C7TTROWSLE7OPZO263EE3BT624/action/citation_signature","submit_replication":"https://pith.science/pith/C7TTROWSLE7OPZO263EE3BT624/action/replication_record"}},"created_at":"2026-07-05T04:26:28.452300+00:00","updated_at":"2026-07-05T04:26:28.452300+00:00"}