{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5O3KXROKILYRJHXQQABAXORZH5","short_pith_number":"pith:5O3KXROK","canonical_record":{"source":{"id":"2101.04882","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-13T05:20:20Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"5520df27ee218cebbef39279daf3686799ce9efcbde0ff1fdddcb10f06fb3f5c","abstract_canon_sha256":"247d8a40864873ec91b9019cc6351f76025dde05da4be6670fe3f17a64c66a37"},"schema_version":"1.0"},"canonical_sha256":"ebb6abc5ca42f1149ef080020bba393f5aeb2e79aa85b21b94e5e5f8b5a52840","source":{"kind":"arxiv","id":"2101.04882","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.04882","created_at":"2026-07-05T02:21:00Z"},{"alias_kind":"arxiv_version","alias_value":"2101.04882v1","created_at":"2026-07-05T02:21:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.04882","created_at":"2026-07-05T02:21:00Z"},{"alias_kind":"pith_short_12","alias_value":"5O3KXROKILYR","created_at":"2026-07-05T02:21:00Z"},{"alias_kind":"pith_short_16","alias_value":"5O3KXROKILYRJHXQ","created_at":"2026-07-05T02:21:00Z"},{"alias_kind":"pith_short_8","alias_value":"5O3KXROK","created_at":"2026-07-05T02:21:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5O3KXROKILYRJHXQQABAXORZH5","target":"record","payload":{"canonical_record":{"source":{"id":"2101.04882","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-13T05:20:20Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"5520df27ee218cebbef39279daf3686799ce9efcbde0ff1fdddcb10f06fb3f5c","abstract_canon_sha256":"247d8a40864873ec91b9019cc6351f76025dde05da4be6670fe3f17a64c66a37"},"schema_version":"1.0"},"canonical_sha256":"ebb6abc5ca42f1149ef080020bba393f5aeb2e79aa85b21b94e5e5f8b5a52840","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:00.540435Z","signature_b64":"s0T+s5WeecpffSgQ6wj5LFq7FSH+Vz8D5oQdI9bx3aIl7O7mVs9BC0Tsd54QrKrrTs27GzVQUTZdBwB5dde5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebb6abc5ca42f1149ef080020bba393f5aeb2e79aa85b21b94e5e5f8b5a52840","last_reissued_at":"2026-07-05T02:21:00.539946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:00.539946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.04882","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":"2026-07-05T02:21:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TSBgLllniXb/mtXNaydZ70jJmjQD0/FNBEpgBaLamZpk90qznZ2ViBxiFpHmK/H88dRFYkru/FbvF0tEsd28Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:41:45.694485Z"},"content_sha256":"69c723295359e9ce54ddfd873337599005a5321dbf66985ffdfe9bc9afcba7aa","schema_version":"1.0","event_id":"sha256:69c723295359e9ce54ddfd873337599005a5321dbf66985ffdfe9bc9afcba7aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5O3KXROKILYRJHXQQABAXORZH5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Asymmetric self-play for automatic goal discovery in robotic manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Alex Paino, Arthur Petron, Casey Chu, Henrique P. d.O. Pinto, Hyeonwoo Noh, Ilge Akkaya, Lilian Weng, Matthias Plappert, OpenAI OpenAI, Peter Welinder, Qiming Yuan, Raul Sampedro, Ruben D'Sa, Tao Xu, Vineet Kosaraju, Wojciech Zaremba","submitted_at":"2021-01-13T05:20:20Z","abstract_excerpt":"We train a single, goal-conditioned policy that can solve many robotic manipulation tasks, including tasks with previously unseen goals and objects. We rely on asymmetric self-play for goal discovery, where two agents, Alice and Bob, play a game. Alice is asked to propose challenging goals and Bob aims to solve them. We show that this method can discover highly diverse and complex goals without any human priors. Bob can be trained with only sparse rewards, because the interaction between Alice and Bob results in a natural curriculum and Bob can learn from Alice's trajectory when relabeled as a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.04882","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/2101.04882/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":"2026-07-05T02:21:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EID8JcR0YJATvQilr4swkqFfah6tbzoNZUohHcdD51+WI4ciQUCXe9RPxmje8P5IoYwaw8XdGXrspXNKk0q7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:41:45.695100Z"},"content_sha256":"cff73d4d1bcbf1f62528184cabe0e07a5c1d07bfe90caeb28191742b166538e9","schema_version":"1.0","event_id":"sha256:cff73d4d1bcbf1f62528184cabe0e07a5c1d07bfe90caeb28191742b166538e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5O3KXROKILYRJHXQQABAXORZH5/bundle.json","state_url":"https://pith.science/pith/5O3KXROKILYRJHXQQABAXORZH5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5O3KXROKILYRJHXQQABAXORZH5/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":"2026-07-31T13:41:45Z","links":{"resolver":"https://pith.science/pith/5O3KXROKILYRJHXQQABAXORZH5","bundle":"https://pith.science/pith/5O3KXROKILYRJHXQQABAXORZH5/bundle.json","state":"https://pith.science/pith/5O3KXROKILYRJHXQQABAXORZH5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5O3KXROKILYRJHXQQABAXORZH5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5O3KXROKILYRJHXQQABAXORZH5","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":"247d8a40864873ec91b9019cc6351f76025dde05da4be6670fe3f17a64c66a37","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-13T05:20:20Z","title_canon_sha256":"5520df27ee218cebbef39279daf3686799ce9efcbde0ff1fdddcb10f06fb3f5c"},"schema_version":"1.0","source":{"id":"2101.04882","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.04882","created_at":"2026-07-05T02:21:00Z"},{"alias_kind":"arxiv_version","alias_value":"2101.04882v1","created_at":"2026-07-05T02:21:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.04882","created_at":"2026-07-05T02:21:00Z"},{"alias_kind":"pith_short_12","alias_value":"5O3KXROKILYR","created_at":"2026-07-05T02:21:00Z"},{"alias_kind":"pith_short_16","alias_value":"5O3KXROKILYRJHXQ","created_at":"2026-07-05T02:21:00Z"},{"alias_kind":"pith_short_8","alias_value":"5O3KXROK","created_at":"2026-07-05T02:21:00Z"}],"graph_snapshots":[{"event_id":"sha256:cff73d4d1bcbf1f62528184cabe0e07a5c1d07bfe90caeb28191742b166538e9","target":"graph","created_at":"2026-07-05T02:21:00Z","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/2101.04882/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We train a single, goal-conditioned policy that can solve many robotic manipulation tasks, including tasks with previously unseen goals and objects. We rely on asymmetric self-play for goal discovery, where two agents, Alice and Bob, play a game. Alice is asked to propose challenging goals and Bob aims to solve them. We show that this method can discover highly diverse and complex goals without any human priors. Bob can be trained with only sparse rewards, because the interaction between Alice and Bob results in a natural curriculum and Bob can learn from Alice's trajectory when relabeled as a","authors_text":"Alex Paino, Arthur Petron, Casey Chu, Henrique P. d.O. Pinto, Hyeonwoo Noh, Ilge Akkaya, Lilian Weng, Matthias Plappert, OpenAI OpenAI, Peter Welinder, Qiming Yuan, Raul Sampedro, Ruben D'Sa, Tao Xu, Vineet Kosaraju, Wojciech Zaremba","cross_cats":["cs.AI","cs.CV","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-13T05:20:20Z","title":"Asymmetric self-play for automatic goal discovery in robotic manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.04882","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":"sha256:69c723295359e9ce54ddfd873337599005a5321dbf66985ffdfe9bc9afcba7aa","target":"record","created_at":"2026-07-05T02:21:00Z","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":"247d8a40864873ec91b9019cc6351f76025dde05da4be6670fe3f17a64c66a37","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-13T05:20:20Z","title_canon_sha256":"5520df27ee218cebbef39279daf3686799ce9efcbde0ff1fdddcb10f06fb3f5c"},"schema_version":"1.0","source":{"id":"2101.04882","kind":"arxiv","version":1}},"canonical_sha256":"ebb6abc5ca42f1149ef080020bba393f5aeb2e79aa85b21b94e5e5f8b5a52840","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebb6abc5ca42f1149ef080020bba393f5aeb2e79aa85b21b94e5e5f8b5a52840","first_computed_at":"2026-07-05T02:21:00.539946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:21:00.539946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s0T+s5WeecpffSgQ6wj5LFq7FSH+Vz8D5oQdI9bx3aIl7O7mVs9BC0Tsd54QrKrrTs27GzVQUTZdBwB5dde5BA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:21:00.540435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.04882","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69c723295359e9ce54ddfd873337599005a5321dbf66985ffdfe9bc9afcba7aa","sha256:cff73d4d1bcbf1f62528184cabe0e07a5c1d07bfe90caeb28191742b166538e9"],"state_sha256":"cc8009db6da1eed548cca0a5d908722bacd571a42c1bfc47bc910de367cc3f39"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WW5NT39B0m9/OTwt1xI8//CjX8Ex1IalNOD7CgJz0JskzXlcyjKVEsBAgY6ewaYkvNwxfACAdnQpMqQtgVwIBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T13:41:45.699724Z","bundle_sha256":"8f753f556ac187d05fc73445d5f5167bb551d787f19120149f29a63526c52641"}}