{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YU6J5STR7Q2QFCAJQFYAAMC63P","short_pith_number":"pith:YU6J5STR","canonical_record":{"source":{"id":"1903.10077","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-24T23:13:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dd8caaf1cdd1aa72cbda436eb1d37c54223242ce593e5b0ba632127bd4b647c3","abstract_canon_sha256":"8beda394f44057b7e4c92a07c3ee159f78e6daac576797dc94f953d5943451d9"},"schema_version":"1.0"},"canonical_sha256":"c53c9eca71fc35028809817000305edbff4d9e6aa45e458d7fe366f832cc1ec6","source":{"kind":"arxiv","id":"1903.10077","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.10077","created_at":"2026-05-17T23:50:32Z"},{"alias_kind":"arxiv_version","alias_value":"1903.10077v1","created_at":"2026-05-17T23:50:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10077","created_at":"2026-05-17T23:50:32Z"},{"alias_kind":"pith_short_12","alias_value":"YU6J5STR7Q2Q","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YU6J5STR7Q2QFCAJ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YU6J5STR","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YU6J5STR7Q2QFCAJQFYAAMC63P","target":"record","payload":{"canonical_record":{"source":{"id":"1903.10077","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-24T23:13:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dd8caaf1cdd1aa72cbda436eb1d37c54223242ce593e5b0ba632127bd4b647c3","abstract_canon_sha256":"8beda394f44057b7e4c92a07c3ee159f78e6daac576797dc94f953d5943451d9"},"schema_version":"1.0"},"canonical_sha256":"c53c9eca71fc35028809817000305edbff4d9e6aa45e458d7fe366f832cc1ec6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:32.964621Z","signature_b64":"X8ZCp4D/QRSJBoX5vYKUEehATdq2tPiKKEGR4/M1jDAPdSs9AeSblL9rn4JgyzfCq5au2EiyGIznDxaTnVXuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c53c9eca71fc35028809817000305edbff4d9e6aa45e458d7fe366f832cc1ec6","last_reissued_at":"2026-05-17T23:50:32.964121Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:32.964121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.10077","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":"2026-05-17T23:50:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oAV9FBe0Em8na+PaqC64LCn+FTVZOOZ3ZLW4vSaFvFJcb24CRFOqVZJ/xNwdqz6dkM1EHtnRLxYclNZouH9bBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:54:44.574719Z"},"content_sha256":"d2bac85e0d79047ce710509cc8a78070a601756d35831278610eebf8b29ecddf","schema_version":"1.0","event_id":"sha256:d2bac85e0d79047ce710509cc8a78070a601756d35831278610eebf8b29ecddf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YU6J5STR7Q2QFCAJQFYAAMC63P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Truly Batch Apprenticeship Learning with Deep Successor Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Donghun Lee, Finale Doshi-Velez, Srivatsan Srinivasan","submitted_at":"2019-03-24T23:13:27Z","abstract_excerpt":"We introduce a novel apprenticeship learning algorithm to learn an expert's underlying reward structure in off-policy model-free \\emph{batch} settings. Unlike existing methods that require a dynamics model or additional data acquisition for on-policy evaluation, our algorithm requires only the batch data of observed expert behavior. Such settings are common in real-world tasks---health care, finance or industrial processes ---where accurate simulators do not exist or data acquisition is costly. To address challenges in batch settings, we introduce Deep Successor Feature Networks(DSFN) that est"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10077","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":"2026-05-17T23:50:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ceH162zm9/PEZsm89JJZBcxOTIYVhQKpGlLH2TkpMB4KGGhO9/hfs/3bklkxM752nZsXr9Fj5xbhOBLEs3bHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:54:44.575072Z"},"content_sha256":"e0915c36354b926b71e7e4974a0c97cb7811326680e10d6a4c675ca4c5eef1f9","schema_version":"1.0","event_id":"sha256:e0915c36354b926b71e7e4974a0c97cb7811326680e10d6a4c675ca4c5eef1f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P/bundle.json","state_url":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YU6J5STR7Q2QFCAJQFYAAMC63P/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":"2026-05-28T01:54:44Z","links":{"resolver":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P","bundle":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P/bundle.json","state":"https://pith.science/pith/YU6J5STR7Q2QFCAJQFYAAMC63P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YU6J5STR7Q2QFCAJQFYAAMC63P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YU6J5STR7Q2QFCAJQFYAAMC63P","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":"8beda394f44057b7e4c92a07c3ee159f78e6daac576797dc94f953d5943451d9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-24T23:13:27Z","title_canon_sha256":"dd8caaf1cdd1aa72cbda436eb1d37c54223242ce593e5b0ba632127bd4b647c3"},"schema_version":"1.0","source":{"id":"1903.10077","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.10077","created_at":"2026-05-17T23:50:32Z"},{"alias_kind":"arxiv_version","alias_value":"1903.10077v1","created_at":"2026-05-17T23:50:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10077","created_at":"2026-05-17T23:50:32Z"},{"alias_kind":"pith_short_12","alias_value":"YU6J5STR7Q2Q","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YU6J5STR7Q2QFCAJ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YU6J5STR","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:e0915c36354b926b71e7e4974a0c97cb7811326680e10d6a4c675ca4c5eef1f9","target":"graph","created_at":"2026-05-17T23:50:32Z","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 introduce a novel apprenticeship learning algorithm to learn an expert's underlying reward structure in off-policy model-free \\emph{batch} settings. Unlike existing methods that require a dynamics model or additional data acquisition for on-policy evaluation, our algorithm requires only the batch data of observed expert behavior. Such settings are common in real-world tasks---health care, finance or industrial processes ---where accurate simulators do not exist or data acquisition is costly. To address challenges in batch settings, we introduce Deep Successor Feature Networks(DSFN) that est","authors_text":"Donghun Lee, Finale Doshi-Velez, Srivatsan Srinivasan","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-24T23:13:27Z","title":"Truly Batch Apprenticeship Learning with Deep Successor Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10077","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:d2bac85e0d79047ce710509cc8a78070a601756d35831278610eebf8b29ecddf","target":"record","created_at":"2026-05-17T23:50:32Z","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":"8beda394f44057b7e4c92a07c3ee159f78e6daac576797dc94f953d5943451d9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-24T23:13:27Z","title_canon_sha256":"dd8caaf1cdd1aa72cbda436eb1d37c54223242ce593e5b0ba632127bd4b647c3"},"schema_version":"1.0","source":{"id":"1903.10077","kind":"arxiv","version":1}},"canonical_sha256":"c53c9eca71fc35028809817000305edbff4d9e6aa45e458d7fe366f832cc1ec6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c53c9eca71fc35028809817000305edbff4d9e6aa45e458d7fe366f832cc1ec6","first_computed_at":"2026-05-17T23:50:32.964121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:32.964121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X8ZCp4D/QRSJBoX5vYKUEehATdq2tPiKKEGR4/M1jDAPdSs9AeSblL9rn4JgyzfCq5au2EiyGIznDxaTnVXuAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:32.964621Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.10077","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2bac85e0d79047ce710509cc8a78070a601756d35831278610eebf8b29ecddf","sha256:e0915c36354b926b71e7e4974a0c97cb7811326680e10d6a4c675ca4c5eef1f9"],"state_sha256":"bdd187b0db8363255afaa1871af4b75a268c235769e92fcc19f6a18f173cf74f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SMWqdBo6mzXEL2fpB7K209fYfmpeqJSH2/ckaKwqnbszPYnK1oU/w7mHBjIC+iGT6Mnh36HxXy/KumlbeS7OBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T01:54:44.577047Z","bundle_sha256":"f5d040c8b75801a451cf3c1483292020f98878b6aaf913c20cf2abc13abbfe34"}}