{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T3JXRDPRP6RLOJY3MWCVQCRU3N","short_pith_number":"pith:T3JXRDPR","canonical_record":{"source":{"id":"2405.04549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-05T12:36:18Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"210091a0ef801589881db0cdb42c8063a9e702d0c6bf7487612dd1844eea496f","abstract_canon_sha256":"d531efda0015c5fc4de459aef8fa115d3741096dd0695fa790ff1b12c0a56c05"},"schema_version":"1.0"},"canonical_sha256":"9ed3788df17fa2b7271b6585580a34db570880de1db3629f0c1318ed4248d49e","source":{"kind":"arxiv","id":"2405.04549","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04549","created_at":"2026-07-05T08:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04549v1","created_at":"2026-07-05T08:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04549","created_at":"2026-07-05T08:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"T3JXRDPRP6RL","created_at":"2026-07-05T08:16:50Z"},{"alias_kind":"pith_short_16","alias_value":"T3JXRDPRP6RLOJY3","created_at":"2026-07-05T08:16:50Z"},{"alias_kind":"pith_short_8","alias_value":"T3JXRDPR","created_at":"2026-07-05T08:16:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T3JXRDPRP6RLOJY3MWCVQCRU3N","target":"record","payload":{"canonical_record":{"source":{"id":"2405.04549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-05T12:36:18Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"210091a0ef801589881db0cdb42c8063a9e702d0c6bf7487612dd1844eea496f","abstract_canon_sha256":"d531efda0015c5fc4de459aef8fa115d3741096dd0695fa790ff1b12c0a56c05"},"schema_version":"1.0"},"canonical_sha256":"9ed3788df17fa2b7271b6585580a34db570880de1db3629f0c1318ed4248d49e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:50.415405Z","signature_b64":"yJAU3ajDHKH9/eX2+ueFMfUSSn0rI86Nsds3f0ZJsRusWWOx7UTX8YzcR3DlcBguq5wvdmSSiX41xn/hquhyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ed3788df17fa2b7271b6585580a34db570880de1db3629f0c1318ed4248d49e","last_reissued_at":"2026-07-05T08:16:50.414928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:50.414928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.04549","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":"2026-07-05T08:16:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oLUkcm5p+RT6aNsk/NCSCjORyfcF367dd7GNxcSzsyTqnmSN2O23DZMD7gt9df3ruQdgR0ZXt4CO92M+cWmeCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:36:26.064354Z"},"content_sha256":"e56670b7226f8a8171b05907093903440dcc952d0f7a72efbd4ef134bc86bf67","schema_version":"1.0","event_id":"sha256:e56670b7226f8a8171b05907093903440dcc952d0f7a72efbd4ef134bc86bf67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T3JXRDPRP6RLOJY3MWCVQCRU3N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ClothPPO: A Proximal Policy Optimization Enhancing Framework for Robotic Cloth Manipulation with Observation-Aligned Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Libing Yang, Long Chen, Yang Li","submitted_at":"2024-05-05T12:36:18Z","abstract_excerpt":"Vision-based robotic cloth unfolding has made great progress recently. However, prior works predominantly rely on value learning and have not fully explored policy-based techniques. Recently, the success of reinforcement learning on the large language model has shown that the policy gradient algorithm can enhance policy with huge action space. In this paper, we introduce ClothPPO, a framework that employs a policy gradient algorithm based on actor-critic architecture to enhance a pre-trained model with huge 10^6 action spaces aligned with observation in the task of unfolding clothes. To this e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04549","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/2405.04549/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":"2026-07-05T08:16:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cPbHRZwYOFg79Jv6LU7kRDFZx98035w6X0hRO+oyWMfDpIdJjJemPcf7+WfVzikDJIxQHxarRhMCcxXaVerSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:36:26.064848Z"},"content_sha256":"26da5a793c1b40edb9d06d9b78afec005b1a50b5d575c25c41a8f48350793829","schema_version":"1.0","event_id":"sha256:26da5a793c1b40edb9d06d9b78afec005b1a50b5d575c25c41a8f48350793829"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T3JXRDPRP6RLOJY3MWCVQCRU3N/bundle.json","state_url":"https://pith.science/pith/T3JXRDPRP6RLOJY3MWCVQCRU3N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T3JXRDPRP6RLOJY3MWCVQCRU3N/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":"2026-08-10T13:36:26Z","links":{"resolver":"https://pith.science/pith/T3JXRDPRP6RLOJY3MWCVQCRU3N","bundle":"https://pith.science/pith/T3JXRDPRP6RLOJY3MWCVQCRU3N/bundle.json","state":"https://pith.science/pith/T3JXRDPRP6RLOJY3MWCVQCRU3N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T3JXRDPRP6RLOJY3MWCVQCRU3N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T3JXRDPRP6RLOJY3MWCVQCRU3N","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":"d531efda0015c5fc4de459aef8fa115d3741096dd0695fa790ff1b12c0a56c05","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-05T12:36:18Z","title_canon_sha256":"210091a0ef801589881db0cdb42c8063a9e702d0c6bf7487612dd1844eea496f"},"schema_version":"1.0","source":{"id":"2405.04549","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04549","created_at":"2026-07-05T08:16:50Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04549v1","created_at":"2026-07-05T08:16:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04549","created_at":"2026-07-05T08:16:50Z"},{"alias_kind":"pith_short_12","alias_value":"T3JXRDPRP6RL","created_at":"2026-07-05T08:16:50Z"},{"alias_kind":"pith_short_16","alias_value":"T3JXRDPRP6RLOJY3","created_at":"2026-07-05T08:16:50Z"},{"alias_kind":"pith_short_8","alias_value":"T3JXRDPR","created_at":"2026-07-05T08:16:50Z"}],"graph_snapshots":[{"event_id":"sha256:26da5a793c1b40edb9d06d9b78afec005b1a50b5d575c25c41a8f48350793829","target":"graph","created_at":"2026-07-05T08:16:50Z","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/2405.04549/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-based robotic cloth unfolding has made great progress recently. However, prior works predominantly rely on value learning and have not fully explored policy-based techniques. Recently, the success of reinforcement learning on the large language model has shown that the policy gradient algorithm can enhance policy with huge action space. In this paper, we introduce ClothPPO, a framework that employs a policy gradient algorithm based on actor-critic architecture to enhance a pre-trained model with huge 10^6 action spaces aligned with observation in the task of unfolding clothes. To this e","authors_text":"Libing Yang, Long Chen, Yang Li","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-05T12:36:18Z","title":"ClothPPO: A Proximal Policy Optimization Enhancing Framework for Robotic Cloth Manipulation with Observation-Aligned Action Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04549","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:e56670b7226f8a8171b05907093903440dcc952d0f7a72efbd4ef134bc86bf67","target":"record","created_at":"2026-07-05T08:16:50Z","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":"d531efda0015c5fc4de459aef8fa115d3741096dd0695fa790ff1b12c0a56c05","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-05T12:36:18Z","title_canon_sha256":"210091a0ef801589881db0cdb42c8063a9e702d0c6bf7487612dd1844eea496f"},"schema_version":"1.0","source":{"id":"2405.04549","kind":"arxiv","version":1}},"canonical_sha256":"9ed3788df17fa2b7271b6585580a34db570880de1db3629f0c1318ed4248d49e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ed3788df17fa2b7271b6585580a34db570880de1db3629f0c1318ed4248d49e","first_computed_at":"2026-07-05T08:16:50.414928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:50.414928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yJAU3ajDHKH9/eX2+ueFMfUSSn0rI86Nsds3f0ZJsRusWWOx7UTX8YzcR3DlcBguq5wvdmSSiX41xn/hquhyAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:50.415405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.04549","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e56670b7226f8a8171b05907093903440dcc952d0f7a72efbd4ef134bc86bf67","sha256:26da5a793c1b40edb9d06d9b78afec005b1a50b5d575c25c41a8f48350793829"],"state_sha256":"91ffe61b59e5f0d1cfa7a7c1c0a0f85cde56302ff8b02e3d8e637d0fbd822fc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h8MO7WvTI3NDQuc/RBFL/3VDHcQLRvO13O8IkiU5RzJ1IWpz6EXJw6X+SzOew1pxLsvHZvXLFvkGVCqHJAZbDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T13:36:26.068450Z","bundle_sha256":"bcc48b86b81f8d05a89b7a852d2dbab5d32a6fd30f553682a0c6cf41aa64b6e6"}}