{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:3RCIXS57LXCZAZFN5LJSPYN5X7","short_pith_number":"pith:3RCIXS57","schema_version":"1.0","canonical_sha256":"dc448bcbbf5dc59064adead327e1bdbfe8b80f1c6aed93e1cfb8ff247c3a0117","source":{"kind":"arxiv","id":"1612.02605","version":1},"attestation_state":"computed","paper":{"title":"Towards Information-Seeking Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Trischler, Alessandro Sordoni, Philip Bachman","submitted_at":"2016-12-08T11:47:01Z","abstract_excerpt":"We develop a general problem setting for training and testing the ability of agents to gather information efficiently. Specifically, we present a collection of tasks in which success requires searching through a partially-observed environment, for fragments of information which can be pieced together to accomplish various goals. We combine deep architectures with techniques from reinforcement learning to develop agents that solve our tasks. We shape the behavior of these agents by combining extrinsic and intrinsic rewards. We empirically demonstrate that these agents learn to search actively a"},"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":"1612.02605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-08T11:47:01Z","cross_cats_sorted":[],"title_canon_sha256":"835c6b98dea79b00040232dff7884ea5f7a6beb03a43faebaeffdddbca31174c","abstract_canon_sha256":"f26061d5cb1231332b552710df533e747dba550ebf226209453a0b3a1a7eb565"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:33.277702Z","signature_b64":"1VyZ+3dVlG+Mb1EDoRJRN3pFeO/35UU6Xq/xXBoH3Kt8oMaaMx4pmmE7sWxWdSjfIid6OxEYQptK5Vvs3NgyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc448bcbbf5dc59064adead327e1bdbfe8b80f1c6aed93e1cfb8ff247c3a0117","last_reissued_at":"2026-05-18T00:55:33.277151Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:33.277151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Information-Seeking Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Trischler, Alessandro Sordoni, Philip Bachman","submitted_at":"2016-12-08T11:47:01Z","abstract_excerpt":"We develop a general problem setting for training and testing the ability of agents to gather information efficiently. Specifically, we present a collection of tasks in which success requires searching through a partially-observed environment, for fragments of information which can be pieced together to accomplish various goals. We combine deep architectures with techniques from reinforcement learning to develop agents that solve our tasks. We shape the behavior of these agents by combining extrinsic and intrinsic rewards. We empirically demonstrate that these agents learn to search actively a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.02605","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":"1612.02605","created_at":"2026-05-18T00:55:33.277224+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.02605v1","created_at":"2026-05-18T00:55:33.277224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.02605","created_at":"2026-05-18T00:55:33.277224+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RCIXS57LXCZ","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RCIXS57LXCZAZFN","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RCIXS57","created_at":"2026-05-18T12:29:55.572404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7","json":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7.json","graph_json":"https://pith.science/api/pith-number/3RCIXS57LXCZAZFN5LJSPYN5X7/graph.json","events_json":"https://pith.science/api/pith-number/3RCIXS57LXCZAZFN5LJSPYN5X7/events.json","paper":"https://pith.science/paper/3RCIXS57"},"agent_actions":{"view_html":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7","download_json":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7.json","view_paper":"https://pith.science/paper/3RCIXS57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.02605&json=true","fetch_graph":"https://pith.science/api/pith-number/3RCIXS57LXCZAZFN5LJSPYN5X7/graph.json","fetch_events":"https://pith.science/api/pith-number/3RCIXS57LXCZAZFN5LJSPYN5X7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7/action/storage_attestation","attest_author":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7/action/author_attestation","sign_citation":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7/action/citation_signature","submit_replication":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7/action/replication_record"}},"created_at":"2026-05-18T00:55:33.277224+00:00","updated_at":"2026-05-18T00:55:33.277224+00:00"}