{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IT3WAX3GZVI46YIGLO4V3PDNUJ","short_pith_number":"pith:IT3WAX3G","canonical_record":{"source":{"id":"1804.00846","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-03T06:52:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1d242031584362a13f1fae50540d44f088e116b717d0f317ef0530fc62a475f0","abstract_canon_sha256":"cdde322568c639a62d1f047226578a59b2364edee1a7532a21c23df1383e4aee"},"schema_version":"1.0"},"canonical_sha256":"44f7605f66cd51cf61065bb95dbc6da24a21a59777414b01e39f49394910ad3f","source":{"kind":"arxiv","id":"1804.00846","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.00846","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"1804.00846v4","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00846","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"IT3WAX3GZVI4","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IT3WAX3GZVI46YIG","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IT3WAX3G","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IT3WAX3GZVI46YIGLO4V3PDNUJ","target":"record","payload":{"canonical_record":{"source":{"id":"1804.00846","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-03T06:52:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1d242031584362a13f1fae50540d44f088e116b717d0f317ef0530fc62a475f0","abstract_canon_sha256":"cdde322568c639a62d1f047226578a59b2364edee1a7532a21c23df1383e4aee"},"schema_version":"1.0"},"canonical_sha256":"44f7605f66cd51cf61065bb95dbc6da24a21a59777414b01e39f49394910ad3f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:43.355437Z","signature_b64":"5UicCz9kIvDX0rcudBDGA1M7XlEBVvafPv/9GQFJ+9Bs5Jjc1AamS0bfiSnDkWMzU08CEVY3i/XSsLSRPHSaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44f7605f66cd51cf61065bb95dbc6da24a21a59777414b01e39f49394910ad3f","last_reissued_at":"2026-05-17T23:42:43.354833Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:43.354833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.00846","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hpebd3Ah/7OOjPCLSBdDEYDVfmfB9nyuqX+70CAPO4WU/DmNVWAxzRaJX9KcAa12Q5nQVD8YfzR1lgr165NgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:13:00.545736Z"},"content_sha256":"53b1ed9bc031e628916e6712d684837cc50c914ae322f6a0f271f3c73335100c","schema_version":"1.0","event_id":"sha256:53b1ed9bc031e628916e6712d684837cc50c914ae322f6a0f271f3c73335100c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IT3WAX3GZVI46YIGLO4V3PDNUJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Search via Retrospective Imitation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aadyot Bhatnagar, Albert Zhao, Jialin Song, Masahiro Ono, Ravi Lanka, Yisong Yue","submitted_at":"2018-04-03T06:52:09Z","abstract_excerpt":"We study the problem of learning a good search policy for combinatorial search spaces. We propose retrospective imitation learning, which, after initial training by an expert, improves itself by learning from \\textit{retrospective inspections} of its own roll-outs. That is, when the policy eventually reaches a feasible solution in a combinatorial search tree after making mistakes and backtracks, it retrospectively constructs an improved search trace to the solution by removing backtracks, which is then used to further train the policy. A key feature of our approach is that it can iteratively s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00846","kind":"arxiv","version":4},"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":"2026-05-17T23:42:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IsJM9OWqXuMmYAWt6qr0wVFnDu8RwWl93Of5rVbkck/Bo7jxydNvIfCqVjxIaFkMWHdFQHw/o57dUsi0mk0DCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:13:00.546184Z"},"content_sha256":"661c54f4b307db90c979c6fb8d3d04d2bde32eb6bc12baff04cd641aaca33585","schema_version":"1.0","event_id":"sha256:661c54f4b307db90c979c6fb8d3d04d2bde32eb6bc12baff04cd641aaca33585"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IT3WAX3GZVI46YIGLO4V3PDNUJ/bundle.json","state_url":"https://pith.science/pith/IT3WAX3GZVI46YIGLO4V3PDNUJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IT3WAX3GZVI46YIGLO4V3PDNUJ/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":"2026-05-27T22:13:00Z","links":{"resolver":"https://pith.science/pith/IT3WAX3GZVI46YIGLO4V3PDNUJ","bundle":"https://pith.science/pith/IT3WAX3GZVI46YIGLO4V3PDNUJ/bundle.json","state":"https://pith.science/pith/IT3WAX3GZVI46YIGLO4V3PDNUJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IT3WAX3GZVI46YIGLO4V3PDNUJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IT3WAX3GZVI46YIGLO4V3PDNUJ","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":"cdde322568c639a62d1f047226578a59b2364edee1a7532a21c23df1383e4aee","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-03T06:52:09Z","title_canon_sha256":"1d242031584362a13f1fae50540d44f088e116b717d0f317ef0530fc62a475f0"},"schema_version":"1.0","source":{"id":"1804.00846","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.00846","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"1804.00846v4","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00846","created_at":"2026-05-17T23:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"IT3WAX3GZVI4","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IT3WAX3GZVI46YIG","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IT3WAX3G","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:661c54f4b307db90c979c6fb8d3d04d2bde32eb6bc12baff04cd641aaca33585","target":"graph","created_at":"2026-05-17T23:42:43Z","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 study the problem of learning a good search policy for combinatorial search spaces. We propose retrospective imitation learning, which, after initial training by an expert, improves itself by learning from \\textit{retrospective inspections} of its own roll-outs. That is, when the policy eventually reaches a feasible solution in a combinatorial search tree after making mistakes and backtracks, it retrospectively constructs an improved search trace to the solution by removing backtracks, which is then used to further train the policy. A key feature of our approach is that it can iteratively s","authors_text":"Aadyot Bhatnagar, Albert Zhao, Jialin Song, Masahiro Ono, Ravi Lanka, Yisong Yue","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-03T06:52:09Z","title":"Learning to Search via Retrospective Imitation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00846","kind":"arxiv","version":4},"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":"sha256:53b1ed9bc031e628916e6712d684837cc50c914ae322f6a0f271f3c73335100c","target":"record","created_at":"2026-05-17T23:42:43Z","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":"cdde322568c639a62d1f047226578a59b2364edee1a7532a21c23df1383e4aee","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-03T06:52:09Z","title_canon_sha256":"1d242031584362a13f1fae50540d44f088e116b717d0f317ef0530fc62a475f0"},"schema_version":"1.0","source":{"id":"1804.00846","kind":"arxiv","version":4}},"canonical_sha256":"44f7605f66cd51cf61065bb95dbc6da24a21a59777414b01e39f49394910ad3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44f7605f66cd51cf61065bb95dbc6da24a21a59777414b01e39f49394910ad3f","first_computed_at":"2026-05-17T23:42:43.354833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:43.354833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5UicCz9kIvDX0rcudBDGA1M7XlEBVvafPv/9GQFJ+9Bs5Jjc1AamS0bfiSnDkWMzU08CEVY3i/XSsLSRPHSaDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:43.355437Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.00846","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53b1ed9bc031e628916e6712d684837cc50c914ae322f6a0f271f3c73335100c","sha256:661c54f4b307db90c979c6fb8d3d04d2bde32eb6bc12baff04cd641aaca33585"],"state_sha256":"63c691dd07db67acd876d901c83f4a3081b8f5fa61b5929915708f19685571f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wtHFzHc+Ph8GsxrKhxcEWBE+RdBEF7ZUtjLU9IuPW8W84/2KgJO0YrYC8xeK8IaUn5kIxr/X8/LludojL3/3BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T22:13:00.549533Z","bundle_sha256":"c27dc2b8a1fcfc20750414f98f66c76ad7d590f575ea6bffb6260d2dfbaec4ab"}}