{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:H5DW7VFOBR5K7NUXDBTLRMGRRN","short_pith_number":"pith:H5DW7VFO","canonical_record":{"source":{"id":"2401.09728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T05:17:30Z","cross_cats_sorted":[],"title_canon_sha256":"e8178321879824a5f1b4f407f4b753480907b12dbe8c7d93b57dcde7297d7d42","abstract_canon_sha256":"c4dec64715e3da9e7eff690eb58b39b83953be478fc1a12d46e4faaa69628820"},"schema_version":"1.0"},"canonical_sha256":"3f476fd4ae0c7aafb6971866b8b0d18b6da42aec43c0957876b8165d82b2dc1d","source":{"kind":"arxiv","id":"2401.09728","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09728","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09728v1","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09728","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"pith_short_12","alias_value":"H5DW7VFOBR5K","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"pith_short_16","alias_value":"H5DW7VFOBR5K7NUX","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"pith_short_8","alias_value":"H5DW7VFO","created_at":"2026-07-05T07:35:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:H5DW7VFOBR5K7NUXDBTLRMGRRN","target":"record","payload":{"canonical_record":{"source":{"id":"2401.09728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T05:17:30Z","cross_cats_sorted":[],"title_canon_sha256":"e8178321879824a5f1b4f407f4b753480907b12dbe8c7d93b57dcde7297d7d42","abstract_canon_sha256":"c4dec64715e3da9e7eff690eb58b39b83953be478fc1a12d46e4faaa69628820"},"schema_version":"1.0"},"canonical_sha256":"3f476fd4ae0c7aafb6971866b8b0d18b6da42aec43c0957876b8165d82b2dc1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:01.339152Z","signature_b64":"coyNycI54YTDxuwy1lAdtlbAiOZqjZt8oWGiNoCiD9wlsR0Js7shQR+SdNfx5vfzJymlAIdiA9zbW/uF7a7tCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f476fd4ae0c7aafb6971866b8b0d18b6da42aec43c0957876b8165d82b2dc1d","last_reissued_at":"2026-07-05T07:35:01.338649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:01.338649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.09728","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":"2026-07-05T07:35:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ow9jf2pPdT19+OG1/lw3trG/jGHR+N6kKw4be8K8XN6PtDth/hsonExYbHHFIpxRgXAkium7W0lNrDWFWRwbBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T11:03:35.173867Z"},"content_sha256":"47cf81b907132433bc04ddafe14dc7717930370881de3b455bd5a35030c957c8","schema_version":"1.0","event_id":"sha256:47cf81b907132433bc04ddafe14dc7717930370881de3b455bd5a35030c957c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:H5DW7VFOBR5K7NUXDBTLRMGRRN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Imitation Learning by Controlling the Effective Planning Horizon","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Byung-Jun Lee, Hee-Jun Ahn, Seong-Woong Shim","submitted_at":"2024-01-18T05:17:30Z","abstract_excerpt":"In offline imitation learning (IL), we generally assume only a handful of expert trajectories and a supplementary offline dataset from suboptimal behaviors to learn the expert policy. While it is now common to minimize the divergence between state-action visitation distributions so that the agent also considers the future consequences of an action, a sampling error in an offline dataset may lead to erroneous estimates of state-action visitations in the offline case. In this paper, we investigate the effect of controlling the effective planning horizon (i.e., reducing the discount factor) as op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09728","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.09728/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T07:35:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c9BkB6j1BlRsLW8S63/5C8g7oXWFgRMmSektgH1YJT2P52qlAs9LTC9fnpqRoOxrWZXBz0+uOOzrSye96TNtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T11:03:35.174241Z"},"content_sha256":"31e9259165529f7f2b79c8dcd7ce2341266422ed1dde6d4acd2e02777fe489b8","schema_version":"1.0","event_id":"sha256:31e9259165529f7f2b79c8dcd7ce2341266422ed1dde6d4acd2e02777fe489b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN/bundle.json","state_url":"https://pith.science/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN/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":"2026-07-14T11:03:35Z","links":{"resolver":"https://pith.science/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN","bundle":"https://pith.science/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN/bundle.json","state":"https://pith.science/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H5DW7VFOBR5K7NUXDBTLRMGRRN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H5DW7VFOBR5K7NUXDBTLRMGRRN","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":"c4dec64715e3da9e7eff690eb58b39b83953be478fc1a12d46e4faaa69628820","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T05:17:30Z","title_canon_sha256":"e8178321879824a5f1b4f407f4b753480907b12dbe8c7d93b57dcde7297d7d42"},"schema_version":"1.0","source":{"id":"2401.09728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09728","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09728v1","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09728","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"pith_short_12","alias_value":"H5DW7VFOBR5K","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"pith_short_16","alias_value":"H5DW7VFOBR5K7NUX","created_at":"2026-07-05T07:35:01Z"},{"alias_kind":"pith_short_8","alias_value":"H5DW7VFO","created_at":"2026-07-05T07:35:01Z"}],"graph_snapshots":[{"event_id":"sha256:31e9259165529f7f2b79c8dcd7ce2341266422ed1dde6d4acd2e02777fe489b8","target":"graph","created_at":"2026-07-05T07:35:01Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.09728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In offline imitation learning (IL), we generally assume only a handful of expert trajectories and a supplementary offline dataset from suboptimal behaviors to learn the expert policy. While it is now common to minimize the divergence between state-action visitation distributions so that the agent also considers the future consequences of an action, a sampling error in an offline dataset may lead to erroneous estimates of state-action visitations in the offline case. In this paper, we investigate the effect of controlling the effective planning horizon (i.e., reducing the discount factor) as op","authors_text":"Byung-Jun Lee, Hee-Jun Ahn, Seong-Woong Shim","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T05:17:30Z","title":"Offline Imitation Learning by Controlling the Effective Planning Horizon"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09728","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":"sha256:47cf81b907132433bc04ddafe14dc7717930370881de3b455bd5a35030c957c8","target":"record","created_at":"2026-07-05T07:35:01Z","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":"c4dec64715e3da9e7eff690eb58b39b83953be478fc1a12d46e4faaa69628820","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T05:17:30Z","title_canon_sha256":"e8178321879824a5f1b4f407f4b753480907b12dbe8c7d93b57dcde7297d7d42"},"schema_version":"1.0","source":{"id":"2401.09728","kind":"arxiv","version":1}},"canonical_sha256":"3f476fd4ae0c7aafb6971866b8b0d18b6da42aec43c0957876b8165d82b2dc1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f476fd4ae0c7aafb6971866b8b0d18b6da42aec43c0957876b8165d82b2dc1d","first_computed_at":"2026-07-05T07:35:01.338649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:35:01.338649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"coyNycI54YTDxuwy1lAdtlbAiOZqjZt8oWGiNoCiD9wlsR0Js7shQR+SdNfx5vfzJymlAIdiA9zbW/uF7a7tCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:35:01.339152Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.09728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47cf81b907132433bc04ddafe14dc7717930370881de3b455bd5a35030c957c8","sha256:31e9259165529f7f2b79c8dcd7ce2341266422ed1dde6d4acd2e02777fe489b8"],"state_sha256":"59c5ea9a5f2fa57a9c89f1232387be8409117c67c882572e3c6608d612b101db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+P0puwf/0tIgSIintgx/jo65uyoKDxEbrfppOGlp6MtAZBsbD00NnUCLFhBcAJT3IxqScG2dv5EhxjmBu/mFBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T11:03:35.176867Z","bundle_sha256":"4868cf95bd161fae2f5dc3deaeafbb5851ac5d33772f5908c1096551ec2d27fa"}}