{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PRC5A65I6RK3MADC7ZBMGOD2OO","short_pith_number":"pith:PRC5A65I","canonical_record":{"source":{"id":"2105.05484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-05-12T07:46:56Z","cross_cats_sorted":[],"title_canon_sha256":"7df835fe476186a14bf3cf70f2cd7c6687296bd7bdf4c207fd36d67fb1a2a145","abstract_canon_sha256":"25b97016f6738b1c5af5325c2087355d6b0bf242d4cba1ae5286462a91e65e17"},"schema_version":"1.0"},"canonical_sha256":"7c45d07ba8f455b60062fe42c3387a73a7ab4f87926a2c0526d4487e6988a980","source":{"kind":"arxiv","id":"2105.05484","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.05484","created_at":"2026-07-05T02:39:51Z"},{"alias_kind":"arxiv_version","alias_value":"2105.05484v1","created_at":"2026-07-05T02:39:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05484","created_at":"2026-07-05T02:39:51Z"},{"alias_kind":"pith_short_12","alias_value":"PRC5A65I6RK3","created_at":"2026-07-05T02:39:51Z"},{"alias_kind":"pith_short_16","alias_value":"PRC5A65I6RK3MADC","created_at":"2026-07-05T02:39:51Z"},{"alias_kind":"pith_short_8","alias_value":"PRC5A65I","created_at":"2026-07-05T02:39:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PRC5A65I6RK3MADC7ZBMGOD2OO","target":"record","payload":{"canonical_record":{"source":{"id":"2105.05484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-05-12T07:46:56Z","cross_cats_sorted":[],"title_canon_sha256":"7df835fe476186a14bf3cf70f2cd7c6687296bd7bdf4c207fd36d67fb1a2a145","abstract_canon_sha256":"25b97016f6738b1c5af5325c2087355d6b0bf242d4cba1ae5286462a91e65e17"},"schema_version":"1.0"},"canonical_sha256":"7c45d07ba8f455b60062fe42c3387a73a7ab4f87926a2c0526d4487e6988a980","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:51.372512Z","signature_b64":"eiqpaa73QUhUA8CwDk1T8nyp0OEdFn9jVifd3rkuVJJTCWf8yC3v7/TbTTpI0ZP6Hs09JroQg7vC23heI6r6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c45d07ba8f455b60062fe42c3387a73a7ab4f87926a2c0526d4487e6988a980","last_reissued_at":"2026-07-05T02:39:51.372082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:51.372082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.05484","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":"2026-07-05T02:39:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hIOdC7pWR7a3MICY7ozhkcpavY4tZTPfkKcLZ08ZXzCPHHm4YE08umnzvyQBTsqLTN4f95ZQrg8CcccpsS2OAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:49:45.741069Z"},"content_sha256":"0e8bc99a37f33f9c1b2a7f6799b2dd23c07ef48aa1ede91fa5afc35d0f94e674","schema_version":"1.0","event_id":"sha256:0e8bc99a37f33f9c1b2a7f6799b2dd23c07ef48aa1ede91fa5afc35d0f94e674"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PRC5A65I6RK3MADC7ZBMGOD2OO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning a Skill-sequence-dependent Policy for Long-horizon Manipulation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jiaming Zhang, Jionglong Su, Zhenglong Sun, Zhihao Li","submitted_at":"2021-05-12T07:46:56Z","abstract_excerpt":"In recent years, the robotics community has made substantial progress in robotic manipulation using deep reinforcement learning (RL). Effectively learning of long-horizon tasks remains a challenging topic. Typical RL-based methods approximate long-horizon tasks as Markov decision processes and only consider current observation (images or other sensor information) as input state. However, such approximation ignores the fact that skill-sequence also plays a crucial role in long-horizon tasks. In this paper, we take both the observation and skill sequences into account and propose a skill-sequenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05484","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/2105.05484/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":"2026-07-05T02:39:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Obq+ldIIM/rHqwg81K8vo6leRvJeg7dWQwp8UuhpaSfRPp517WK9ijzj5+1uBdaermBUHIKq0r0/CFVLfPKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:49:45.741735Z"},"content_sha256":"5adb0504815175994a7073bc169da14cc18fe0feb4650f78c2b404d5286847ba","schema_version":"1.0","event_id":"sha256:5adb0504815175994a7073bc169da14cc18fe0feb4650f78c2b404d5286847ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PRC5A65I6RK3MADC7ZBMGOD2OO/bundle.json","state_url":"https://pith.science/pith/PRC5A65I6RK3MADC7ZBMGOD2OO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PRC5A65I6RK3MADC7ZBMGOD2OO/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":"2026-07-06T14:49:45Z","links":{"resolver":"https://pith.science/pith/PRC5A65I6RK3MADC7ZBMGOD2OO","bundle":"https://pith.science/pith/PRC5A65I6RK3MADC7ZBMGOD2OO/bundle.json","state":"https://pith.science/pith/PRC5A65I6RK3MADC7ZBMGOD2OO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PRC5A65I6RK3MADC7ZBMGOD2OO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PRC5A65I6RK3MADC7ZBMGOD2OO","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":"25b97016f6738b1c5af5325c2087355d6b0bf242d4cba1ae5286462a91e65e17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-05-12T07:46:56Z","title_canon_sha256":"7df835fe476186a14bf3cf70f2cd7c6687296bd7bdf4c207fd36d67fb1a2a145"},"schema_version":"1.0","source":{"id":"2105.05484","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.05484","created_at":"2026-07-05T02:39:51Z"},{"alias_kind":"arxiv_version","alias_value":"2105.05484v1","created_at":"2026-07-05T02:39:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05484","created_at":"2026-07-05T02:39:51Z"},{"alias_kind":"pith_short_12","alias_value":"PRC5A65I6RK3","created_at":"2026-07-05T02:39:51Z"},{"alias_kind":"pith_short_16","alias_value":"PRC5A65I6RK3MADC","created_at":"2026-07-05T02:39:51Z"},{"alias_kind":"pith_short_8","alias_value":"PRC5A65I","created_at":"2026-07-05T02:39:51Z"}],"graph_snapshots":[{"event_id":"sha256:5adb0504815175994a7073bc169da14cc18fe0feb4650f78c2b404d5286847ba","target":"graph","created_at":"2026-07-05T02:39:51Z","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/2105.05484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, the robotics community has made substantial progress in robotic manipulation using deep reinforcement learning (RL). Effectively learning of long-horizon tasks remains a challenging topic. Typical RL-based methods approximate long-horizon tasks as Markov decision processes and only consider current observation (images or other sensor information) as input state. However, such approximation ignores the fact that skill-sequence also plays a crucial role in long-horizon tasks. In this paper, we take both the observation and skill sequences into account and propose a skill-sequenc","authors_text":"Jiaming Zhang, Jionglong Su, Zhenglong Sun, Zhihao Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-05-12T07:46:56Z","title":"Learning a Skill-sequence-dependent Policy for Long-horizon Manipulation Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05484","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":"sha256:0e8bc99a37f33f9c1b2a7f6799b2dd23c07ef48aa1ede91fa5afc35d0f94e674","target":"record","created_at":"2026-07-05T02:39:51Z","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":"25b97016f6738b1c5af5325c2087355d6b0bf242d4cba1ae5286462a91e65e17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-05-12T07:46:56Z","title_canon_sha256":"7df835fe476186a14bf3cf70f2cd7c6687296bd7bdf4c207fd36d67fb1a2a145"},"schema_version":"1.0","source":{"id":"2105.05484","kind":"arxiv","version":1}},"canonical_sha256":"7c45d07ba8f455b60062fe42c3387a73a7ab4f87926a2c0526d4487e6988a980","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c45d07ba8f455b60062fe42c3387a73a7ab4f87926a2c0526d4487e6988a980","first_computed_at":"2026-07-05T02:39:51.372082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:39:51.372082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eiqpaa73QUhUA8CwDk1T8nyp0OEdFn9jVifd3rkuVJJTCWf8yC3v7/TbTTpI0ZP6Hs09JroQg7vC23heI6r6Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:39:51.372512Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.05484","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e8bc99a37f33f9c1b2a7f6799b2dd23c07ef48aa1ede91fa5afc35d0f94e674","sha256:5adb0504815175994a7073bc169da14cc18fe0feb4650f78c2b404d5286847ba"],"state_sha256":"37c2a4c020a4c3ac2e8ad7ca5e61969f97d4490f837dbc224a2f8dfa164c120d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9AE7lMM4LQuPSdBWeb4zMaLj+6BYxW3X0mtwdDW3hYfWg1ZAKCyXzgREM1FoA3cR6cxFQ/C0yEyEelvTtrzkAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T14:49:45.744559Z","bundle_sha256":"66eb47c5bc48bdc73efb9e72c0d19746490bca3694bf6c34e07e1f030460868e"}}