{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:3RCIXS57LXCZAZFN5LJSPYN5X7","short_pith_number":"pith:3RCIXS57","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"},"canonical_sha256":"dc448bcbbf5dc59064adead327e1bdbfe8b80f1c6aed93e1cfb8ff247c3a0117","source":{"kind":"arxiv","id":"1612.02605","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.02605","created_at":"2026-05-18T00:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"1612.02605v1","created_at":"2026-05-18T00:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.02605","created_at":"2026-05-18T00:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"3RCIXS57LXCZ","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"3RCIXS57LXCZAZFN","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"3RCIXS57","created_at":"2026-05-18T12:29:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:3RCIXS57LXCZAZFN5LJSPYN5X7","target":"record","payload":{"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"},"canonical_sha256":"dc448bcbbf5dc59064adead327e1bdbfe8b80f1c6aed93e1cfb8ff247c3a0117","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"},"source_kind":"arxiv","source_id":"1612.02605","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":"2026-05-18T00:55:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iL7cWdThoN2sIhtnE9ZkE0fzAz3vol0ZzwjB4Db5XQVbDNAkncVNSIIpbTGvcDlxAfoYU5Zu/aUrSej/TaYmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T12:22:23.653046Z"},"content_sha256":"2ae1177ae65a53f93d74b691558a56a22fbf112d52a357da8dc0689bcb797140","schema_version":"1.0","event_id":"sha256:2ae1177ae65a53f93d74b691558a56a22fbf112d52a357da8dc0689bcb797140"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:3RCIXS57LXCZAZFN5LJSPYN5X7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:55:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hHey0dOXDG/aBfRAuKlOR9iUT9G8EBr55xBHtgLM38pTQO0wajcw2EtU5Wg0Ji40T6bGwSxWKdKyiRZm7yUqAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T12:22:23.653502Z"},"content_sha256":"e1c4829d2374c7b8953a2fccd92043eb572f942147d6ef2cd86649c34016f4dc","schema_version":"1.0","event_id":"sha256:e1c4829d2374c7b8953a2fccd92043eb572f942147d6ef2cd86649c34016f4dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7/bundle.json","state_url":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RCIXS57LXCZAZFN5LJSPYN5X7/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":"2026-05-25T12:22:23Z","links":{"resolver":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7","bundle":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7/bundle.json","state":"https://pith.science/pith/3RCIXS57LXCZAZFN5LJSPYN5X7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RCIXS57LXCZAZFN5LJSPYN5X7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:3RCIXS57LXCZAZFN5LJSPYN5X7","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":"f26061d5cb1231332b552710df533e747dba550ebf226209453a0b3a1a7eb565","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-08T11:47:01Z","title_canon_sha256":"835c6b98dea79b00040232dff7884ea5f7a6beb03a43faebaeffdddbca31174c"},"schema_version":"1.0","source":{"id":"1612.02605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.02605","created_at":"2026-05-18T00:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"1612.02605v1","created_at":"2026-05-18T00:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.02605","created_at":"2026-05-18T00:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"3RCIXS57LXCZ","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"3RCIXS57LXCZAZFN","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"3RCIXS57","created_at":"2026-05-18T12:29:55Z"}],"graph_snapshots":[{"event_id":"sha256:e1c4829d2374c7b8953a2fccd92043eb572f942147d6ef2cd86649c34016f4dc","target":"graph","created_at":"2026-05-18T00:55:33Z","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"},"paper":{"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","authors_text":"Adam Trischler, Alessandro Sordoni, Philip Bachman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-08T11:47:01Z","title":"Towards Information-Seeking Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.02605","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":"sha256:2ae1177ae65a53f93d74b691558a56a22fbf112d52a357da8dc0689bcb797140","target":"record","created_at":"2026-05-18T00:55:33Z","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":"f26061d5cb1231332b552710df533e747dba550ebf226209453a0b3a1a7eb565","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-08T11:47:01Z","title_canon_sha256":"835c6b98dea79b00040232dff7884ea5f7a6beb03a43faebaeffdddbca31174c"},"schema_version":"1.0","source":{"id":"1612.02605","kind":"arxiv","version":1}},"canonical_sha256":"dc448bcbbf5dc59064adead327e1bdbfe8b80f1c6aed93e1cfb8ff247c3a0117","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc448bcbbf5dc59064adead327e1bdbfe8b80f1c6aed93e1cfb8ff247c3a0117","first_computed_at":"2026-05-18T00:55:33.277151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:55:33.277151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1VyZ+3dVlG+Mb1EDoRJRN3pFeO/35UU6Xq/xXBoH3Kt8oMaaMx4pmmE7sWxWdSjfIid6OxEYQptK5Vvs3NgyCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:55:33.277702Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.02605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ae1177ae65a53f93d74b691558a56a22fbf112d52a357da8dc0689bcb797140","sha256:e1c4829d2374c7b8953a2fccd92043eb572f942147d6ef2cd86649c34016f4dc"],"state_sha256":"4e4c6b70d725bfb365b5c8c36a8fd3355d1d671ba41824a58de35d5d8d91f341"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"munl/NuydpyM7yBw43+ylRsMOSbHYToNoOhkosgIAwAVLeGyLeGvEUuUN6emkM1tzvoyOEmEOjun9H2KOC4kDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T12:22:23.656717Z","bundle_sha256":"c9fe328bbeed8d3b6f56f63a9d0ae1cf29a24298154f6c0bfd1e408a45f04f2e"}}