{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IPJG2MQMUSUV3WYLRKH2VECG2Z","short_pith_number":"pith:IPJG2MQM","schema_version":"1.0","canonical_sha256":"43d26d320ca4a95ddb0b8a8faa9046d65f0ae3bd5ce296dd44a0539eb16fffb0","source":{"kind":"arxiv","id":"2410.11013","version":2},"attestation_state":"computed","paper":{"title":"Incorporating Task Progress Knowledge for Subgoal Generation in Robotic Manipulation through Image Edits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Xuhui Kang, Yen-Ling Kuo","submitted_at":"2024-10-14T19:05:38Z","abstract_excerpt":"Understanding the progress of a task allows humans to not only track what has been done but also to better plan for future goals. We demonstrate TaKSIE, a novel framework that incorporates task progress knowledge into visual subgoal generation for robotic manipulation tasks. We jointly train a recurrent network with a latent diffusion model to generate the next visual subgoal based on the robot's current observation and the input language command. At execution time, the robot leverages a visual progress representation to monitor the task progress and adaptively samples the next visual subgoal "},"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":"2410.11013","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-14T19:05:38Z","cross_cats_sorted":[],"title_canon_sha256":"1256bead26a975de7445ab3e66b56bb8a60f8abce01aa2e6790f43914cefb344","abstract_canon_sha256":"78851495b54b16629485e3363db91deb922cd71484d09f9c0de26b880ed90728"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:52.895232Z","signature_b64":"xyS3rSAMVa8Rdw2WxvCIe3TF3u798x5UnJXHaXelf8PMLqC20F74yKyCbLdyRsbacadxrEITb/usmLg2Q2DNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43d26d320ca4a95ddb0b8a8faa9046d65f0ae3bd5ce296dd44a0539eb16fffb0","last_reissued_at":"2026-07-05T09:50:52.894673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:52.894673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating Task Progress Knowledge for Subgoal Generation in Robotic Manipulation through Image Edits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Xuhui Kang, Yen-Ling Kuo","submitted_at":"2024-10-14T19:05:38Z","abstract_excerpt":"Understanding the progress of a task allows humans to not only track what has been done but also to better plan for future goals. We demonstrate TaKSIE, a novel framework that incorporates task progress knowledge into visual subgoal generation for robotic manipulation tasks. We jointly train a recurrent network with a latent diffusion model to generate the next visual subgoal based on the robot's current observation and the input language command. At execution time, the robot leverages a visual progress representation to monitor the task progress and adaptively samples the next visual subgoal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11013","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.11013/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":"2410.11013","created_at":"2026-07-05T09:50:52.894742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11013v2","created_at":"2026-07-05T09:50:52.894742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11013","created_at":"2026-07-05T09:50:52.894742+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPJG2MQMUSUV","created_at":"2026-07-05T09:50:52.894742+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPJG2MQMUSUV3WYL","created_at":"2026-07-05T09:50:52.894742+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPJG2MQM","created_at":"2026-07-05T09:50:52.894742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24622","citing_title":"CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPJG2MQMUSUV3WYLRKH2VECG2Z","json":"https://pith.science/pith/IPJG2MQMUSUV3WYLRKH2VECG2Z.json","graph_json":"https://pith.science/api/pith-number/IPJG2MQMUSUV3WYLRKH2VECG2Z/graph.json","events_json":"https://pith.science/api/pith-number/IPJG2MQMUSUV3WYLRKH2VECG2Z/events.json","paper":"https://pith.science/paper/IPJG2MQM"},"agent_actions":{"view_html":"https://pith.science/pith/IPJG2MQMUSUV3WYLRKH2VECG2Z","download_json":"https://pith.science/pith/IPJG2MQMUSUV3WYLRKH2VECG2Z.json","view_paper":"https://pith.science/paper/IPJG2MQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11013&json=true","fetch_graph":"https://pith.science/api/pith-number/IPJG2MQMUSUV3WYLRKH2VECG2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/IPJG2MQMUSUV3WYLRKH2VECG2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPJG2MQMUSUV3WYLRKH2VECG2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPJG2MQMUSUV3WYLRKH2VECG2Z/action/storage_attestation","attest_author":"https://pith.science/pith/IPJG2MQMUSUV3WYLRKH2VECG2Z/action/author_attestation","sign_citation":"https://pith.science/pith/IPJG2MQMUSUV3WYLRKH2VECG2Z/action/citation_signature","submit_replication":"https://pith.science/pith/IPJG2MQMUSUV3WYLRKH2VECG2Z/action/replication_record"}},"created_at":"2026-07-05T09:50:52.894742+00:00","updated_at":"2026-07-05T09:50:52.894742+00:00"}