{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2BDVK3JANOKD4OEC7XIHEWRATD","short_pith_number":"pith:2BDVK3JA","canonical_record":{"source":{"id":"1803.01840","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-02T19:26:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1840b01ad80deeb6d3517b49f8ddeac31d1ac467ee07afd4167d19763bde0941","abstract_canon_sha256":"80d9ff25a83aa58aaa23723007f0c1bdd62c37e44885b9a90e824eab6e06889d"},"schema_version":"1.0"},"canonical_sha256":"d047556d206b943e3882fdd0725a2098c887c8924be437922aa8796e5c5a4ada","source":{"kind":"arxiv","id":"1803.01840","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01840","created_at":"2026-05-18T00:08:27Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01840v2","created_at":"2026-05-18T00:08:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01840","created_at":"2026-05-18T00:08:27Z"},{"alias_kind":"pith_short_12","alias_value":"2BDVK3JANOKD","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"2BDVK3JANOKD4OEC","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"2BDVK3JA","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2BDVK3JANOKD4OEC7XIHEWRATD","target":"record","payload":{"canonical_record":{"source":{"id":"1803.01840","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-02T19:26:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1840b01ad80deeb6d3517b49f8ddeac31d1ac467ee07afd4167d19763bde0941","abstract_canon_sha256":"80d9ff25a83aa58aaa23723007f0c1bdd62c37e44885b9a90e824eab6e06889d"},"schema_version":"1.0"},"canonical_sha256":"d047556d206b943e3882fdd0725a2098c887c8924be437922aa8796e5c5a4ada","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:27.039412Z","signature_b64":"1hISVgBsF2C71Lw+srnwkjgotZrc0f+mvdRzbShQvJZWIMnLjwt3uvBzctPkX8QecOtNJ44zwBBpJCZe7/2MAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d047556d206b943e3882fdd0725a2098c887c8924be437922aa8796e5c5a4ada","last_reissued_at":"2026-05-18T00:08:27.038954Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:27.038954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.01840","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":"2026-05-18T00:08:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3z/k3MuJ3gD3gQLw7xOCghRj6adJYdeUuClwkS4vJPfIqfVo/k6cBMW12dma7pnSYkV51KXOX3ipPXNRbky2Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:32:27.129625Z"},"content_sha256":"3670c0b5846f51027113a54fdf49b7a2683b594d96df829cfd86cd2e05b09451","schema_version":"1.0","event_id":"sha256:3670c0b5846f51027113a54fdf49b7a2683b594d96df829cfd86cd2e05b09451"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2BDVK3JANOKD4OEC7XIHEWRATD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TACO: Learning Task Decomposition via Temporal Alignment for Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ingmar Posner, Kyriacos Shiarlis, Markus Wulfmeier, Sasha Salter, Shimon Whiteson","submitted_at":"2018-03-02T19:26:16Z","abstract_excerpt":"Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks. By reusing the corresponding sub-policies within and between tasks, they provide training data for each policy from different high-level tasks and compose them to perform novel ones. Existing approaches to modular LfD focus either on learning a single high-level task or depend on domain knowledge and temporal segmentation. In contrast, we propose a weakly supervised, domain-agnostic approach based on task sketches, which include only the sequence of sub-tasks "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01840","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":""},"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":"2026-05-18T00:08:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dpr7R2cvlFU0D4xPiiJhpQt3t/v/0XXkfJU75Z/xcDszx+N/5I0UiwsL4LTXyLU2TI21pzE7OfJqIM1ZdxXBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:32:27.130261Z"},"content_sha256":"cea407fa8307f7bbefd8a5747c3c01932e5d9de45c43bc6b22d7613ee3f62c93","schema_version":"1.0","event_id":"sha256:cea407fa8307f7bbefd8a5747c3c01932e5d9de45c43bc6b22d7613ee3f62c93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2BDVK3JANOKD4OEC7XIHEWRATD/bundle.json","state_url":"https://pith.science/pith/2BDVK3JANOKD4OEC7XIHEWRATD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2BDVK3JANOKD4OEC7XIHEWRATD/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":"2026-05-31T01:32:27Z","links":{"resolver":"https://pith.science/pith/2BDVK3JANOKD4OEC7XIHEWRATD","bundle":"https://pith.science/pith/2BDVK3JANOKD4OEC7XIHEWRATD/bundle.json","state":"https://pith.science/pith/2BDVK3JANOKD4OEC7XIHEWRATD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2BDVK3JANOKD4OEC7XIHEWRATD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2BDVK3JANOKD4OEC7XIHEWRATD","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":"80d9ff25a83aa58aaa23723007f0c1bdd62c37e44885b9a90e824eab6e06889d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-02T19:26:16Z","title_canon_sha256":"1840b01ad80deeb6d3517b49f8ddeac31d1ac467ee07afd4167d19763bde0941"},"schema_version":"1.0","source":{"id":"1803.01840","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01840","created_at":"2026-05-18T00:08:27Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01840v2","created_at":"2026-05-18T00:08:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01840","created_at":"2026-05-18T00:08:27Z"},{"alias_kind":"pith_short_12","alias_value":"2BDVK3JANOKD","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"2BDVK3JANOKD4OEC","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"2BDVK3JA","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:cea407fa8307f7bbefd8a5747c3c01932e5d9de45c43bc6b22d7613ee3f62c93","target":"graph","created_at":"2026-05-18T00:08:27Z","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"},"paper":{"abstract_excerpt":"Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks. By reusing the corresponding sub-policies within and between tasks, they provide training data for each policy from different high-level tasks and compose them to perform novel ones. Existing approaches to modular LfD focus either on learning a single high-level task or depend on domain knowledge and temporal segmentation. In contrast, we propose a weakly supervised, domain-agnostic approach based on task sketches, which include only the sequence of sub-tasks ","authors_text":"Ingmar Posner, Kyriacos Shiarlis, Markus Wulfmeier, Sasha Salter, Shimon Whiteson","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-02T19:26:16Z","title":"TACO: Learning Task Decomposition via Temporal Alignment for Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01840","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":"sha256:3670c0b5846f51027113a54fdf49b7a2683b594d96df829cfd86cd2e05b09451","target":"record","created_at":"2026-05-18T00:08:27Z","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":"80d9ff25a83aa58aaa23723007f0c1bdd62c37e44885b9a90e824eab6e06889d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-02T19:26:16Z","title_canon_sha256":"1840b01ad80deeb6d3517b49f8ddeac31d1ac467ee07afd4167d19763bde0941"},"schema_version":"1.0","source":{"id":"1803.01840","kind":"arxiv","version":2}},"canonical_sha256":"d047556d206b943e3882fdd0725a2098c887c8924be437922aa8796e5c5a4ada","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d047556d206b943e3882fdd0725a2098c887c8924be437922aa8796e5c5a4ada","first_computed_at":"2026-05-18T00:08:27.038954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:27.038954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1hISVgBsF2C71Lw+srnwkjgotZrc0f+mvdRzbShQvJZWIMnLjwt3uvBzctPkX8QecOtNJ44zwBBpJCZe7/2MAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:27.039412Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.01840","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3670c0b5846f51027113a54fdf49b7a2683b594d96df829cfd86cd2e05b09451","sha256:cea407fa8307f7bbefd8a5747c3c01932e5d9de45c43bc6b22d7613ee3f62c93"],"state_sha256":"01f33add681c379e3800f6efbb24c5eca26f6b979a273af2f19adfba9bc4758d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VRFe6eL5UFE4ZiEylAZLpdhjIpix73gPwa7IPreh+ZNTvU7PNHzu/RFceazQq5CNKdGoMLUiBIzr2pmPqYlFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T01:32:27.133435Z","bundle_sha256":"01bf4047c759fb919c28ce65ba4d34ae5ec02a65423f7c9b203b2e0d4956e616"}}