{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WL576MLTB3EUMT2VEZRDHJ2PYU","short_pith_number":"pith:WL576MLT","canonical_record":{"source":{"id":"2607.10892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-12T19:48:46Z","cross_cats_sorted":[],"title_canon_sha256":"3f900c3ac603bd39cdbfe5f0867f9da7babc2e6625acf970874fd1ccbd15f0ad","abstract_canon_sha256":"c98873c9f27784d55bac88d36b70a09f2fe3314efb85e3352b91e1e3411a613c"},"schema_version":"1.0"},"canonical_sha256":"b2fbff31730ec9464f55266233a74fc5348708aeaf3dfe59455252493e2461eb","source":{"kind":"arxiv","id":"2607.10892","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10892","created_at":"2026-07-14T01:21:45Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10892v1","created_at":"2026-07-14T01:21:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10892","created_at":"2026-07-14T01:21:45Z"},{"alias_kind":"pith_short_12","alias_value":"WL576MLTB3EU","created_at":"2026-07-14T01:21:45Z"},{"alias_kind":"pith_short_16","alias_value":"WL576MLTB3EUMT2V","created_at":"2026-07-14T01:21:45Z"},{"alias_kind":"pith_short_8","alias_value":"WL576MLT","created_at":"2026-07-14T01:21:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WL576MLTB3EUMT2VEZRDHJ2PYU","target":"record","payload":{"canonical_record":{"source":{"id":"2607.10892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-12T19:48:46Z","cross_cats_sorted":[],"title_canon_sha256":"3f900c3ac603bd39cdbfe5f0867f9da7babc2e6625acf970874fd1ccbd15f0ad","abstract_canon_sha256":"c98873c9f27784d55bac88d36b70a09f2fe3314efb85e3352b91e1e3411a613c"},"schema_version":"1.0"},"canonical_sha256":"b2fbff31730ec9464f55266233a74fc5348708aeaf3dfe59455252493e2461eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:45.927923Z","signature_b64":"kQk2mrJ5esawDCipEQIc/pjXWptvSzeAD2xL1Z1B5aPMKf3gcXObyJ7DQAtnn/zZFwJU28lx/Bc9W4nBN+r6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2fbff31730ec9464f55266233a74fc5348708aeaf3dfe59455252493e2461eb","last_reissued_at":"2026-07-14T01:21:45.927069Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:45.927069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.10892","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T01:21:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Izz8t6ZPTdOYtMUj52LY1pTrtd8Q/C1jvQ0PNK4fOMSNlIBvnmVnWmEEZ5plspg3j0TR4X5FfzZ5jPrHcR/cCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:51:59.827018Z"},"content_sha256":"52c599999e7f1e711fc8bff0835e60af1c7993c613eeee6570dfe9ef8301d17e","schema_version":"1.0","event_id":"sha256:52c599999e7f1e711fc8bff0835e60af1c7993c613eeee6570dfe9ef8301d17e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WL576MLTB3EUMT2VEZRDHJ2PYU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Single Diffusion-Policy Controller for Multi-Task Block Pushing with Zero-Shot Sim-to-Real Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bo Dai, Haitong Ma, Haldun Balim, Na Li, Yang Hu","submitted_at":"2026-07-12T19:48:46Z","abstract_excerpt":"Diffusion policies have shown promising empirical performance in representing and learning complex maneuvers for robots using behavior cloning (BC). In this paper, we explore training diffusion policies from scratch using reinforcement learning (RL) for multi-task robotic manipulation. Specifically, we aim to train a single diffusion policy for block-pushing tasks with multiple shapes. The proposed framework features a simple policy loss function, which is a reweighted evidence lower bound used in BC-based diffusion policy training and can seamlessly serve as the policy learning module in RL a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10892","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/2607.10892/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T01:21:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UVpD71sC70LB+Z5xFHAFWiUe9KnzQTOtqFlwMrZLkoxbnMKdcNOpAg5FV5qZKBb7fk3KiR3kz0gP1Oc8v9ZnAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:51:59.828229Z"},"content_sha256":"f00dc3d8209256d1d64feb89b893e0515a1caf5540110049f1a95f370709c7cb","schema_version":"1.0","event_id":"sha256:f00dc3d8209256d1d64feb89b893e0515a1caf5540110049f1a95f370709c7cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WL576MLTB3EUMT2VEZRDHJ2PYU/bundle.json","state_url":"https://pith.science/pith/WL576MLTB3EUMT2VEZRDHJ2PYU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WL576MLTB3EUMT2VEZRDHJ2PYU/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":"2026-08-04T13:51:59Z","links":{"resolver":"https://pith.science/pith/WL576MLTB3EUMT2VEZRDHJ2PYU","bundle":"https://pith.science/pith/WL576MLTB3EUMT2VEZRDHJ2PYU/bundle.json","state":"https://pith.science/pith/WL576MLTB3EUMT2VEZRDHJ2PYU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WL576MLTB3EUMT2VEZRDHJ2PYU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WL576MLTB3EUMT2VEZRDHJ2PYU","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":"c98873c9f27784d55bac88d36b70a09f2fe3314efb85e3352b91e1e3411a613c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-12T19:48:46Z","title_canon_sha256":"3f900c3ac603bd39cdbfe5f0867f9da7babc2e6625acf970874fd1ccbd15f0ad"},"schema_version":"1.0","source":{"id":"2607.10892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10892","created_at":"2026-07-14T01:21:45Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10892v1","created_at":"2026-07-14T01:21:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10892","created_at":"2026-07-14T01:21:45Z"},{"alias_kind":"pith_short_12","alias_value":"WL576MLTB3EU","created_at":"2026-07-14T01:21:45Z"},{"alias_kind":"pith_short_16","alias_value":"WL576MLTB3EUMT2V","created_at":"2026-07-14T01:21:45Z"},{"alias_kind":"pith_short_8","alias_value":"WL576MLT","created_at":"2026-07-14T01:21:45Z"}],"graph_snapshots":[{"event_id":"sha256:f00dc3d8209256d1d64feb89b893e0515a1caf5540110049f1a95f370709c7cb","target":"graph","created_at":"2026-07-14T01:21:45Z","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/2607.10892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion policies have shown promising empirical performance in representing and learning complex maneuvers for robots using behavior cloning (BC). In this paper, we explore training diffusion policies from scratch using reinforcement learning (RL) for multi-task robotic manipulation. Specifically, we aim to train a single diffusion policy for block-pushing tasks with multiple shapes. The proposed framework features a simple policy loss function, which is a reweighted evidence lower bound used in BC-based diffusion policy training and can seamlessly serve as the policy learning module in RL a","authors_text":"Bo Dai, Haitong Ma, Haldun Balim, Na Li, Yang Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-12T19:48:46Z","title":"A Single Diffusion-Policy Controller for Multi-Task Block Pushing with Zero-Shot Sim-to-Real Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10892","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":"sha256:52c599999e7f1e711fc8bff0835e60af1c7993c613eeee6570dfe9ef8301d17e","target":"record","created_at":"2026-07-14T01:21:45Z","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":"c98873c9f27784d55bac88d36b70a09f2fe3314efb85e3352b91e1e3411a613c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-12T19:48:46Z","title_canon_sha256":"3f900c3ac603bd39cdbfe5f0867f9da7babc2e6625acf970874fd1ccbd15f0ad"},"schema_version":"1.0","source":{"id":"2607.10892","kind":"arxiv","version":1}},"canonical_sha256":"b2fbff31730ec9464f55266233a74fc5348708aeaf3dfe59455252493e2461eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2fbff31730ec9464f55266233a74fc5348708aeaf3dfe59455252493e2461eb","first_computed_at":"2026-07-14T01:21:45.927069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:21:45.927069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kQk2mrJ5esawDCipEQIc/pjXWptvSzeAD2xL1Z1B5aPMKf3gcXObyJ7DQAtnn/zZFwJU28lx/Bc9W4nBN+r6BQ==","signature_status":"signed_v1","signed_at":"2026-07-14T01:21:45.927923Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52c599999e7f1e711fc8bff0835e60af1c7993c613eeee6570dfe9ef8301d17e","sha256:f00dc3d8209256d1d64feb89b893e0515a1caf5540110049f1a95f370709c7cb"],"state_sha256":"bf73b88915b5cd75de09048e78b223c28d3b2afa6e8ffef4baadb58067b6d5fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O22Ntj2R9VyUZGasa+aje5+7p1RahrFrw5eCHx68Ys1unR4PdvZpMABS1B8zrqFTRciQGZWS2RtvZn06YkCjAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:51:59.839426Z","bundle_sha256":"a0a66f3ce175ed6167f333497023c721c3cb2b3cb96f2e679d56901a57e619ce"}}