{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BS2NNFHJELZJOGMKBSHHBYFUB3","short_pith_number":"pith:BS2NNFHJ","schema_version":"1.0","canonical_sha256":"0cb4d694e922f297198a0c8e70e0b40ef325dea5d040b4c5171e351cb61288d1","source":{"kind":"arxiv","id":"1705.05363","version":1},"attestation_state":"computed","paper":{"title":"Curiosity-driven Exploration by Self-supervised Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexei A. Efros, Deepak Pathak, Pulkit Agrawal, Trevor Darrell","submitted_at":"2017-05-15T17:56:22Z","abstract_excerpt":"In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agent's ability to predict the consequence of its own actions in a visual feature space learned by a self-supervised inverse dynamics model. Our formulation scales to high-dimensional continuous state spaces like images, bypasses the difficulties of directly predicting pixels, and, c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1705.05363","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-15T17:56:22Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO","stat.ML"],"title_canon_sha256":"ac9efaf79bfe9dad41ce037f11e67b421513c49e82192a1aafa7c250d82fc251","abstract_canon_sha256":"7dc690c63c1ade517ec367a8112a150100773ab09e47ccea58f015e1c495b195"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:30.700697Z","signature_b64":"fRlS/A4TRN6AqGudmSd4h+bkP5fhp/ZSmKkx3wJVEbwnuIt6RB2IB5NUSwgVv38fDLzzRKDBhZR3GaHBSYL9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cb4d694e922f297198a0c8e70e0b40ef325dea5d040b4c5171e351cb61288d1","last_reissued_at":"2026-05-18T00:44:30.700239Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:30.700239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curiosity-driven Exploration by Self-supervised Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexei A. Efros, Deepak Pathak, Pulkit Agrawal, Trevor Darrell","submitted_at":"2017-05-15T17:56:22Z","abstract_excerpt":"In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agent's ability to predict the consequence of its own actions in a visual feature space learned by a self-supervised inverse dynamics model. Our formulation scales to high-dimensional continuous state spaces like images, bypasses the difficulties of directly predicting pixels, and, c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.05363","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1705.05363","created_at":"2026-05-18T00:44:30.700303+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.05363v1","created_at":"2026-05-18T00:44:30.700303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.05363","created_at":"2026-05-18T00:44:30.700303+00:00"},{"alias_kind":"pith_short_12","alias_value":"BS2NNFHJELZJ","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BS2NNFHJELZJOGMK","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BS2NNFHJ","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1907.02050","citing_title":"Reasoning and Generalization in RL: A Tool Use Perspective","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06143","citing_title":"Neural Embedding for Physical Manipulations","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16477","citing_title":"Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":256,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12735","citing_title":"The Unified Autonomy Stack: Toward a Blueprint for Generalizable Robot Autonomy","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BS2NNFHJELZJOGMKBSHHBYFUB3","json":"https://pith.science/pith/BS2NNFHJELZJOGMKBSHHBYFUB3.json","graph_json":"https://pith.science/api/pith-number/BS2NNFHJELZJOGMKBSHHBYFUB3/graph.json","events_json":"https://pith.science/api/pith-number/BS2NNFHJELZJOGMKBSHHBYFUB3/events.json","paper":"https://pith.science/paper/BS2NNFHJ"},"agent_actions":{"view_html":"https://pith.science/pith/BS2NNFHJELZJOGMKBSHHBYFUB3","download_json":"https://pith.science/pith/BS2NNFHJELZJOGMKBSHHBYFUB3.json","view_paper":"https://pith.science/paper/BS2NNFHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.05363&json=true","fetch_graph":"https://pith.science/api/pith-number/BS2NNFHJELZJOGMKBSHHBYFUB3/graph.json","fetch_events":"https://pith.science/api/pith-number/BS2NNFHJELZJOGMKBSHHBYFUB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BS2NNFHJELZJOGMKBSHHBYFUB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BS2NNFHJELZJOGMKBSHHBYFUB3/action/storage_attestation","attest_author":"https://pith.science/pith/BS2NNFHJELZJOGMKBSHHBYFUB3/action/author_attestation","sign_citation":"https://pith.science/pith/BS2NNFHJELZJOGMKBSHHBYFUB3/action/citation_signature","submit_replication":"https://pith.science/pith/BS2NNFHJELZJOGMKBSHHBYFUB3/action/replication_record"}},"created_at":"2026-05-18T00:44:30.700303+00:00","updated_at":"2026-05-18T00:44:30.700303+00:00"}