{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7WPFYBWZBMTM46XEMDYFE7RDFP","short_pith_number":"pith:7WPFYBWZ","canonical_record":{"source":{"id":"2407.09024","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-12T06:32:36Z","cross_cats_sorted":[],"title_canon_sha256":"e9198852646152fd498d38b689eaffed85efff504051cb5a31c353efbe3bc216","abstract_canon_sha256":"75eb265166b4542cebf37be2921012492d14f4d1fae3a855da15a5c0a0668b08"},"schema_version":"1.0"},"canonical_sha256":"fd9e5c06d90b26ce7ae460f0527e232be4b82acb7f017cf140c4cd2b2c5f9eaa","source":{"kind":"arxiv","id":"2407.09024","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09024","created_at":"2026-07-05T09:28:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09024v2","created_at":"2026-07-05T09:28:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09024","created_at":"2026-07-05T09:28:12Z"},{"alias_kind":"pith_short_12","alias_value":"7WPFYBWZBMTM","created_at":"2026-07-05T09:28:12Z"},{"alias_kind":"pith_short_16","alias_value":"7WPFYBWZBMTM46XE","created_at":"2026-07-05T09:28:12Z"},{"alias_kind":"pith_short_8","alias_value":"7WPFYBWZ","created_at":"2026-07-05T09:28:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7WPFYBWZBMTM46XEMDYFE7RDFP","target":"record","payload":{"canonical_record":{"source":{"id":"2407.09024","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-12T06:32:36Z","cross_cats_sorted":[],"title_canon_sha256":"e9198852646152fd498d38b689eaffed85efff504051cb5a31c353efbe3bc216","abstract_canon_sha256":"75eb265166b4542cebf37be2921012492d14f4d1fae3a855da15a5c0a0668b08"},"schema_version":"1.0"},"canonical_sha256":"fd9e5c06d90b26ce7ae460f0527e232be4b82acb7f017cf140c4cd2b2c5f9eaa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:12.990990Z","signature_b64":"zdLAXgPyZHadRZevU8bsRT8lhFh912hxrBzuer0/38aKwFA393uh6DUna5UlKkz+nCkP8V//smgUc9jVLBETBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd9e5c06d90b26ce7ae460f0527e232be4b82acb7f017cf140c4cd2b2c5f9eaa","last_reissued_at":"2026-07-05T09:28:12.990556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:12.990556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.09024","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":"2026-07-05T09:28:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mGuk4m63Agikufxr5WknqC6SkpFN3IDokiBRBfLmSkyyfT3g9ZNtua+Cvk1RcqFMrzUtgPJBMObe8KjwiKPQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:40:32.979918Z"},"content_sha256":"93a2efb5d7230391e3c1ce1b60fd453b6fd63884419955f55e3cd06545c97f30","schema_version":"1.0","event_id":"sha256:93a2efb5d7230391e3c1ce1b60fd453b6fd63884419955f55e3cd06545c97f30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7WPFYBWZBMTM46XEMDYFE7RDFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hang Su, Huayu Chen, Jun Zhu, Kaiwen Zheng","submitted_at":"2024-07-12T06:32:36Z","abstract_excerpt":"Drawing upon recent advances in language model alignment, we formulate offline Reinforcement Learning as a two-stage optimization problem: First pretraining expressive generative policies on reward-free behavior datasets, then fine-tuning these policies to align with task-specific annotations like Q-values. This strategy allows us to leverage abundant and diverse behavior data to enhance generalization and enable rapid adaptation to downstream tasks using minimal annotations. In particular, we introduce Efficient Diffusion Alignment (EDA) for solving continuous control problems. EDA utilizes d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09024","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/2407.09024/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":"2026-07-05T09:28:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Txj5FXVm6/DZ4XpMM4CjJR+EzP9zDFJI41yp2jN6JhESqq5bIz3eVgC+W0oDUziCXNYNDTpaayViEn9u0FMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:40:32.980535Z"},"content_sha256":"dc53fa20a05ef9def9475755c6b33c85fb9809ed19812fba3d51662e5768fbaa","schema_version":"1.0","event_id":"sha256:dc53fa20a05ef9def9475755c6b33c85fb9809ed19812fba3d51662e5768fbaa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7WPFYBWZBMTM46XEMDYFE7RDFP/bundle.json","state_url":"https://pith.science/pith/7WPFYBWZBMTM46XEMDYFE7RDFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7WPFYBWZBMTM46XEMDYFE7RDFP/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":"2026-08-10T01:40:32Z","links":{"resolver":"https://pith.science/pith/7WPFYBWZBMTM46XEMDYFE7RDFP","bundle":"https://pith.science/pith/7WPFYBWZBMTM46XEMDYFE7RDFP/bundle.json","state":"https://pith.science/pith/7WPFYBWZBMTM46XEMDYFE7RDFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7WPFYBWZBMTM46XEMDYFE7RDFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7WPFYBWZBMTM46XEMDYFE7RDFP","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":"75eb265166b4542cebf37be2921012492d14f4d1fae3a855da15a5c0a0668b08","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-12T06:32:36Z","title_canon_sha256":"e9198852646152fd498d38b689eaffed85efff504051cb5a31c353efbe3bc216"},"schema_version":"1.0","source":{"id":"2407.09024","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09024","created_at":"2026-07-05T09:28:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09024v2","created_at":"2026-07-05T09:28:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09024","created_at":"2026-07-05T09:28:12Z"},{"alias_kind":"pith_short_12","alias_value":"7WPFYBWZBMTM","created_at":"2026-07-05T09:28:12Z"},{"alias_kind":"pith_short_16","alias_value":"7WPFYBWZBMTM46XE","created_at":"2026-07-05T09:28:12Z"},{"alias_kind":"pith_short_8","alias_value":"7WPFYBWZ","created_at":"2026-07-05T09:28:12Z"}],"graph_snapshots":[{"event_id":"sha256:dc53fa20a05ef9def9475755c6b33c85fb9809ed19812fba3d51662e5768fbaa","target":"graph","created_at":"2026-07-05T09:28:12Z","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/2407.09024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Drawing upon recent advances in language model alignment, we formulate offline Reinforcement Learning as a two-stage optimization problem: First pretraining expressive generative policies on reward-free behavior datasets, then fine-tuning these policies to align with task-specific annotations like Q-values. This strategy allows us to leverage abundant and diverse behavior data to enhance generalization and enable rapid adaptation to downstream tasks using minimal annotations. In particular, we introduce Efficient Diffusion Alignment (EDA) for solving continuous control problems. EDA utilizes d","authors_text":"Hang Su, Huayu Chen, Jun Zhu, Kaiwen Zheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-12T06:32:36Z","title":"Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09024","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":"sha256:93a2efb5d7230391e3c1ce1b60fd453b6fd63884419955f55e3cd06545c97f30","target":"record","created_at":"2026-07-05T09:28:12Z","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":"75eb265166b4542cebf37be2921012492d14f4d1fae3a855da15a5c0a0668b08","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-12T06:32:36Z","title_canon_sha256":"e9198852646152fd498d38b689eaffed85efff504051cb5a31c353efbe3bc216"},"schema_version":"1.0","source":{"id":"2407.09024","kind":"arxiv","version":2}},"canonical_sha256":"fd9e5c06d90b26ce7ae460f0527e232be4b82acb7f017cf140c4cd2b2c5f9eaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd9e5c06d90b26ce7ae460f0527e232be4b82acb7f017cf140c4cd2b2c5f9eaa","first_computed_at":"2026-07-05T09:28:12.990556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:12.990556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zdLAXgPyZHadRZevU8bsRT8lhFh912hxrBzuer0/38aKwFA393uh6DUna5UlKkz+nCkP8V//smgUc9jVLBETBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:12.990990Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.09024","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93a2efb5d7230391e3c1ce1b60fd453b6fd63884419955f55e3cd06545c97f30","sha256:dc53fa20a05ef9def9475755c6b33c85fb9809ed19812fba3d51662e5768fbaa"],"state_sha256":"e8998f49df55455c8b10d296c358a86886c410a78ce0a357412c29608439cb0e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZM4hj9gdBW34taXVO5Oji4+247/RgdkJj8jxt8ivROP9+t6GsF7J2gGoycadvUvbm0btLBQVIHv7gtx+W+47AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T01:40:32.985375Z","bundle_sha256":"20cae4eea8433748c0eb6b5b49ca670215ae6f87d1f823e92718d3eccce3b5b6"}}