{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZWKN4UW2QH3ZX54KMG3HMB6WGM","short_pith_number":"pith:ZWKN4UW2","canonical_record":{"source":{"id":"2411.19133","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-28T13:34:15Z","cross_cats_sorted":[],"title_canon_sha256":"e3eea94f3ff4d1ffb09428d904c6dfbfbb9fc728a343b337b3d773dafe010d1f","abstract_canon_sha256":"faa3abc38ce8e26a843e6d4e35032f669ebf10a5d440aeaff6b2095397f6c5f7"},"schema_version":"1.0"},"canonical_sha256":"cd94de52da81f79bf78a61b67607d6333795813e600eb6525e9d50eb87206b06","source":{"kind":"arxiv","id":"2411.19133","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19133","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19133v2","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19133","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZWKN4UW2QH3Z","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"ZWKN4UW2QH3ZX54K","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"ZWKN4UW2","created_at":"2026-07-05T10:05:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZWKN4UW2QH3ZX54KMG3HMB6WGM","target":"record","payload":{"canonical_record":{"source":{"id":"2411.19133","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-28T13:34:15Z","cross_cats_sorted":[],"title_canon_sha256":"e3eea94f3ff4d1ffb09428d904c6dfbfbb9fc728a343b337b3d773dafe010d1f","abstract_canon_sha256":"faa3abc38ce8e26a843e6d4e35032f669ebf10a5d440aeaff6b2095397f6c5f7"},"schema_version":"1.0"},"canonical_sha256":"cd94de52da81f79bf78a61b67607d6333795813e600eb6525e9d50eb87206b06","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:14.942806Z","signature_b64":"FJrB925H8E5pqefK3cWaNYYFSAhY8lwVEzGsoJ47JqRk9cb6z0TISEUk+jW+i4XnXmsZciZ78OYJzp6qLrQVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd94de52da81f79bf78a61b67607d6333795813e600eb6525e9d50eb87206b06","last_reissued_at":"2026-07-05T10:05:14.942289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:14.942289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.19133","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VdZU6JAfRrJD9NZWCRgRuVPolH3RmLTVr/2snleR+l/NSErRMRAadJ7aMU5MDXNxzBFPVt+O25nBo1MGDY8IAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:15:45.900661Z"},"content_sha256":"d71873f9f7548b2de54f1c73ad9b66f460e25bcb5fb285afeb8e9ebfc974d53e","schema_version":"1.0","event_id":"sha256:d71873f9f7548b2de54f1c73ad9b66f460e25bcb5fb285afeb8e9ebfc974d53e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZWKN4UW2QH3ZX54KMG3HMB6WGM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bat{\\i}kan Bora Ormanc{\\i}, Phillip Swazinna, Steffen Udluft, Thomas A. Runkler","submitted_at":"2024-11-28T13:34:15Z","abstract_excerpt":"In this paper, we investigate offline reinforcement learning (RL) with the goal of training a single robust policy that generalizes effectively across environments with unseen dynamics. We propose a novel approach, Trajectory Encoding Augmentation (TEA), which extends the state space by integrating latent representations of environmental dynamics obtained from sequence encoders, such as AutoEncoders. Our findings show that incorporating these encodings with TEA improves the transferability of a single policy to novel environments with new dynamics, surpassing methods that rely solely on unmodi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19133","kind":"arxiv","version":2},"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/2411.19133/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":"2026-07-05T10:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2iJyYvxXdO0DGk7yhgz1ExQGdeSIy5VPZz6iyYjnCUgg9xtu+nTkta2wopcbu3GbM0aTv8gUh/KRd2p1t4UWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:15:45.901194Z"},"content_sha256":"aef93ac4d4ee60578e289f82f07a9bf29679cb909e6b6105528a0ec7bb5c574f","schema_version":"1.0","event_id":"sha256:aef93ac4d4ee60578e289f82f07a9bf29679cb909e6b6105528a0ec7bb5c574f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZWKN4UW2QH3ZX54KMG3HMB6WGM/bundle.json","state_url":"https://pith.science/pith/ZWKN4UW2QH3ZX54KMG3HMB6WGM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZWKN4UW2QH3ZX54KMG3HMB6WGM/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":"2026-08-19T20:15:45Z","links":{"resolver":"https://pith.science/pith/ZWKN4UW2QH3ZX54KMG3HMB6WGM","bundle":"https://pith.science/pith/ZWKN4UW2QH3ZX54KMG3HMB6WGM/bundle.json","state":"https://pith.science/pith/ZWKN4UW2QH3ZX54KMG3HMB6WGM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZWKN4UW2QH3ZX54KMG3HMB6WGM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZWKN4UW2QH3ZX54KMG3HMB6WGM","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":"faa3abc38ce8e26a843e6d4e35032f669ebf10a5d440aeaff6b2095397f6c5f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-28T13:34:15Z","title_canon_sha256":"e3eea94f3ff4d1ffb09428d904c6dfbfbb9fc728a343b337b3d773dafe010d1f"},"schema_version":"1.0","source":{"id":"2411.19133","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19133","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19133v2","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19133","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZWKN4UW2QH3Z","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"ZWKN4UW2QH3ZX54K","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"ZWKN4UW2","created_at":"2026-07-05T10:05:14Z"}],"graph_snapshots":[{"event_id":"sha256:aef93ac4d4ee60578e289f82f07a9bf29679cb909e6b6105528a0ec7bb5c574f","target":"graph","created_at":"2026-07-05T10:05:14Z","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/2411.19133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we investigate offline reinforcement learning (RL) with the goal of training a single robust policy that generalizes effectively across environments with unseen dynamics. We propose a novel approach, Trajectory Encoding Augmentation (TEA), which extends the state space by integrating latent representations of environmental dynamics obtained from sequence encoders, such as AutoEncoders. Our findings show that incorporating these encodings with TEA improves the transferability of a single policy to novel environments with new dynamics, surpassing methods that rely solely on unmodi","authors_text":"Bat{\\i}kan Bora Ormanc{\\i}, Phillip Swazinna, Steffen Udluft, Thomas A. Runkler","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-28T13:34:15Z","title":"TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19133","kind":"arxiv","version":2},"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:d71873f9f7548b2de54f1c73ad9b66f460e25bcb5fb285afeb8e9ebfc974d53e","target":"record","created_at":"2026-07-05T10:05:14Z","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":"faa3abc38ce8e26a843e6d4e35032f669ebf10a5d440aeaff6b2095397f6c5f7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-28T13:34:15Z","title_canon_sha256":"e3eea94f3ff4d1ffb09428d904c6dfbfbb9fc728a343b337b3d773dafe010d1f"},"schema_version":"1.0","source":{"id":"2411.19133","kind":"arxiv","version":2}},"canonical_sha256":"cd94de52da81f79bf78a61b67607d6333795813e600eb6525e9d50eb87206b06","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd94de52da81f79bf78a61b67607d6333795813e600eb6525e9d50eb87206b06","first_computed_at":"2026-07-05T10:05:14.942289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:14.942289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FJrB925H8E5pqefK3cWaNYYFSAhY8lwVEzGsoJ47JqRk9cb6z0TISEUk+jW+i4XnXmsZciZ78OYJzp6qLrQVBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:14.942806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19133","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d71873f9f7548b2de54f1c73ad9b66f460e25bcb5fb285afeb8e9ebfc974d53e","sha256:aef93ac4d4ee60578e289f82f07a9bf29679cb909e6b6105528a0ec7bb5c574f"],"state_sha256":"f4fe43868bf328fdde5a6253e2bfa90883e00bc60c7ffd28042a9be899208807"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PWlsE9etwjArNjeq14wONqlrT5fyEIbo1nGJjSZ/ZhkdcrBEF2DIVnwV9Y3lSIRFRNn0iG9QyyNACO9g5RCFAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T20:15:45.906809Z","bundle_sha256":"83b5beca87f0e985c1578120ca3d6122045237dea55317cbe325df84e400ba4b"}}