{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AJ4ED5THE754PB2GBEBCOJXKRD","short_pith_number":"pith:AJ4ED5TH","canonical_record":{"source":{"id":"2408.05804","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-11T15:49:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"284f24caadea77b0d805f125d1fbb01cefdef20d15b13542637218931675252c","abstract_canon_sha256":"6756ac17e83b79c7c809c37b58088e0752dffdab55ac4b632fecacbb548f97dc"},"schema_version":"1.0"},"canonical_sha256":"027841f66727fbc7874609022726ea88ec46984456f9fa6c64b0eb30a52731fc","source":{"kind":"arxiv","id":"2408.05804","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05804","created_at":"2026-07-05T08:54:25Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05804v1","created_at":"2026-07-05T08:54:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05804","created_at":"2026-07-05T08:54:25Z"},{"alias_kind":"pith_short_12","alias_value":"AJ4ED5THE754","created_at":"2026-07-05T08:54:25Z"},{"alias_kind":"pith_short_16","alias_value":"AJ4ED5THE754PB2G","created_at":"2026-07-05T08:54:25Z"},{"alias_kind":"pith_short_8","alias_value":"AJ4ED5TH","created_at":"2026-07-05T08:54:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AJ4ED5THE754PB2GBEBCOJXKRD","target":"record","payload":{"canonical_record":{"source":{"id":"2408.05804","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-11T15:49:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"284f24caadea77b0d805f125d1fbb01cefdef20d15b13542637218931675252c","abstract_canon_sha256":"6756ac17e83b79c7c809c37b58088e0752dffdab55ac4b632fecacbb548f97dc"},"schema_version":"1.0"},"canonical_sha256":"027841f66727fbc7874609022726ea88ec46984456f9fa6c64b0eb30a52731fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:25.360240Z","signature_b64":"EsGdrlhtVufnB4lbf4I8CPQASh+w6g5JXnD8DXvo9/7tJFt+TJAjNiauiio5xpNWSzi3N4GXqZgZgkSRkCTFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"027841f66727fbc7874609022726ea88ec46984456f9fa6c64b0eb30a52731fc","last_reissued_at":"2026-07-05T08:54:25.359890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:25.359890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.05804","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":"2026-07-05T08:54:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5mf0lABGJjFM8UHIrdlfSfzh8NJPWNeQ93Ox6euqRjR/xpfchw9dvtQO+z3QQ6MsvXFiRv495SS6rBOhdywUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:36:02.237343Z"},"content_sha256":"6be59d50aff425a21fa60a470b5ff6cfcf9776f866e5424289ece09b660a7653","schema_version":"1.0","event_id":"sha256:6be59d50aff425a21fa60a470b5ff6cfcf9776f866e5424289ece09b660a7653"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AJ4ED5THE754PB2GBEBCOJXKRD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Grace Liu, Michael Tang","submitted_at":"2024-08-11T15:49:00Z","abstract_excerpt":"In this paper, we present empirical evidence of skills and directed exploration emerging from a simple RL algorithm long before any successful trials are observed. For example, in a manipulation task, the agent is given a single observation of the goal state and learns skills, first for moving its end-effector, then for pushing the block, and finally for picking up and placing the block. These skills emerge before the agent has ever successfully placed the block at the goal location and without the aid of any reward functions, demonstrations, or manually-specified distance metrics. Once the ag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05804","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/2408.05804/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":"2026-07-05T08:54:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t837j3BeZ4W6Uo6gxfS5pGvTNhl3HR/2679GWVDPsPOS6FX0I1791Ch+2G874x9oBgNBp7MBUwUDlo6WyUM3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:36:02.237872Z"},"content_sha256":"2046a5690844d89e3641664153328ee5cddf521c041ef0bfd0f154db8b4ffa64","schema_version":"1.0","event_id":"sha256:2046a5690844d89e3641664153328ee5cddf521c041ef0bfd0f154db8b4ffa64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AJ4ED5THE754PB2GBEBCOJXKRD/bundle.json","state_url":"https://pith.science/pith/AJ4ED5THE754PB2GBEBCOJXKRD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AJ4ED5THE754PB2GBEBCOJXKRD/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":"2026-08-17T18:36:02Z","links":{"resolver":"https://pith.science/pith/AJ4ED5THE754PB2GBEBCOJXKRD","bundle":"https://pith.science/pith/AJ4ED5THE754PB2GBEBCOJXKRD/bundle.json","state":"https://pith.science/pith/AJ4ED5THE754PB2GBEBCOJXKRD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AJ4ED5THE754PB2GBEBCOJXKRD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AJ4ED5THE754PB2GBEBCOJXKRD","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":"6756ac17e83b79c7c809c37b58088e0752dffdab55ac4b632fecacbb548f97dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-11T15:49:00Z","title_canon_sha256":"284f24caadea77b0d805f125d1fbb01cefdef20d15b13542637218931675252c"},"schema_version":"1.0","source":{"id":"2408.05804","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05804","created_at":"2026-07-05T08:54:25Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05804v1","created_at":"2026-07-05T08:54:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05804","created_at":"2026-07-05T08:54:25Z"},{"alias_kind":"pith_short_12","alias_value":"AJ4ED5THE754","created_at":"2026-07-05T08:54:25Z"},{"alias_kind":"pith_short_16","alias_value":"AJ4ED5THE754PB2G","created_at":"2026-07-05T08:54:25Z"},{"alias_kind":"pith_short_8","alias_value":"AJ4ED5TH","created_at":"2026-07-05T08:54:25Z"}],"graph_snapshots":[{"event_id":"sha256:2046a5690844d89e3641664153328ee5cddf521c041ef0bfd0f154db8b4ffa64","target":"graph","created_at":"2026-07-05T08:54:25Z","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/2408.05804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present empirical evidence of skills and directed exploration emerging from a simple RL algorithm long before any successful trials are observed. For example, in a manipulation task, the agent is given a single observation of the goal state and learns skills, first for moving its end-effector, then for pushing the block, and finally for picking up and placing the block. These skills emerge before the agent has ever successfully placed the block at the goal location and without the aid of any reward functions, demonstrations, or manually-specified distance metrics. Once the ag","authors_text":"Benjamin Eysenbach, Grace Liu, Michael Tang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-11T15:49:00Z","title":"A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05804","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":"sha256:6be59d50aff425a21fa60a470b5ff6cfcf9776f866e5424289ece09b660a7653","target":"record","created_at":"2026-07-05T08:54:25Z","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":"6756ac17e83b79c7c809c37b58088e0752dffdab55ac4b632fecacbb548f97dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-11T15:49:00Z","title_canon_sha256":"284f24caadea77b0d805f125d1fbb01cefdef20d15b13542637218931675252c"},"schema_version":"1.0","source":{"id":"2408.05804","kind":"arxiv","version":1}},"canonical_sha256":"027841f66727fbc7874609022726ea88ec46984456f9fa6c64b0eb30a52731fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"027841f66727fbc7874609022726ea88ec46984456f9fa6c64b0eb30a52731fc","first_computed_at":"2026-07-05T08:54:25.359890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:25.359890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EsGdrlhtVufnB4lbf4I8CPQASh+w6g5JXnD8DXvo9/7tJFt+TJAjNiauiio5xpNWSzi3N4GXqZgZgkSRkCTFDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:25.360240Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.05804","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6be59d50aff425a21fa60a470b5ff6cfcf9776f866e5424289ece09b660a7653","sha256:2046a5690844d89e3641664153328ee5cddf521c041ef0bfd0f154db8b4ffa64"],"state_sha256":"ff94ea4c4b0b41bdfd966c1816e3378f81f33233fd996906d9806a35756e2f9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cLXXozPWGtvHMLHJxau56OLxFXQ2A9d2jLiefQZ9HTGsvyS4LT3n+kZJkvsvhMY68AUL04nyFNpskIJiGHRDCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:36:02.243022Z","bundle_sha256":"f60e9211deb274aed7ee67b6f07fb07c0c026866fa852d8f1bc968b56ce7b339"}}