{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MPKDLZVJCYMWIGVABJYRULGFQM","short_pith_number":"pith:MPKDLZVJ","canonical_record":{"source":{"id":"2605.25740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T11:54:04Z","cross_cats_sorted":[],"title_canon_sha256":"f9a68dba3e2ebac058b58e79881594bec16de131cafae7f469dd8dccbfcbdd41","abstract_canon_sha256":"d4bf92b3483b84b6b8c5f301dcbb9384a1075e05a098e30a3701e54c480eeec4"},"schema_version":"1.0"},"canonical_sha256":"63d435e6a91619641aa00a711a2cc5830c042351ae780fc641e213bbdac6634a","source":{"kind":"arxiv","id":"2605.25740","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25740","created_at":"2026-05-26T02:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25740v1","created_at":"2026-05-26T02:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25740","created_at":"2026-05-26T02:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"MPKDLZVJCYMW","created_at":"2026-05-26T02:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"MPKDLZVJCYMWIGVA","created_at":"2026-05-26T02:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"MPKDLZVJ","created_at":"2026-05-26T02:04:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MPKDLZVJCYMWIGVABJYRULGFQM","target":"record","payload":{"canonical_record":{"source":{"id":"2605.25740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T11:54:04Z","cross_cats_sorted":[],"title_canon_sha256":"f9a68dba3e2ebac058b58e79881594bec16de131cafae7f469dd8dccbfcbdd41","abstract_canon_sha256":"d4bf92b3483b84b6b8c5f301dcbb9384a1075e05a098e30a3701e54c480eeec4"},"schema_version":"1.0"},"canonical_sha256":"63d435e6a91619641aa00a711a2cc5830c042351ae780fc641e213bbdac6634a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:52.821124Z","signature_b64":"Ym+rOAFLLjGP/cyrxwvF7UqJL48DX4JFV5xNlzcY+6XTIFjLudz8F5+4sKMFV78JIjfomLNl0T4sLt8cZ/+uCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63d435e6a91619641aa00a711a2cc5830c042351ae780fc641e213bbdac6634a","last_reissued_at":"2026-05-26T02:04:52.820627Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:52.820627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.25740","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":"2026-05-26T02:04:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vx1T3lB5Phr+vIBIkaauLCzslkJhkFYkuhG2s/ufxunOUJT7mnoxTHEy3cpF0oWb4tw5eyR3gikPEFS6LXPNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T18:46:25.812744Z"},"content_sha256":"ba4455f8d2d82bb2c43a0f916533c9b3dd0b0f3ee9517c3a86c242214be72227","schema_version":"1.0","event_id":"sha256:ba4455f8d2d82bb2c43a0f916533c9b3dd0b0f3ee9517c3a86c242214be72227"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MPKDLZVJCYMWIGVABJYRULGFQM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Byeongchan Kim, Hyungkyu Kang, Min-hwan Oh","submitted_at":"2026-05-25T11:54:04Z","abstract_excerpt":"Offline goal-conditioned reinforcement learning (GCRL) provides a practical framework for obtaining goal-reaching policies from fixed datasets. However, learning a reliable goal-conditioned value function in long-horizon tasks remains challenging. In this paper, we identify erroneous generalization in goal-conditioned value functions as a fundamental bottleneck, and demonstrate that appropriate inductive bias in the value function is crucial for addressing the bottleneck. Building on these findings, we propose Latent-Aligned Value Learning (LAVL), an offline GCRL algorithm that integrates late"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25740","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/2605.25740/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":"2026-05-26T02:04:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n/z74PBh9FmQsvcnTL3J8IKO50EG86b990HsGK3ma01uZn5t4zOa97IJJL/fCfJNYos2ATKwjVwJcDMGdVsaDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T18:46:25.813124Z"},"content_sha256":"a342ffe72e2b89a3ef9e07a4d0c1d307e098a5839698e882b8a93056915d57b4","schema_version":"1.0","event_id":"sha256:a342ffe72e2b89a3ef9e07a4d0c1d307e098a5839698e882b8a93056915d57b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MPKDLZVJCYMWIGVABJYRULGFQM/bundle.json","state_url":"https://pith.science/pith/MPKDLZVJCYMWIGVABJYRULGFQM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MPKDLZVJCYMWIGVABJYRULGFQM/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":"2026-06-01T18:46:25Z","links":{"resolver":"https://pith.science/pith/MPKDLZVJCYMWIGVABJYRULGFQM","bundle":"https://pith.science/pith/MPKDLZVJCYMWIGVABJYRULGFQM/bundle.json","state":"https://pith.science/pith/MPKDLZVJCYMWIGVABJYRULGFQM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MPKDLZVJCYMWIGVABJYRULGFQM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MPKDLZVJCYMWIGVABJYRULGFQM","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":"d4bf92b3483b84b6b8c5f301dcbb9384a1075e05a098e30a3701e54c480eeec4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T11:54:04Z","title_canon_sha256":"f9a68dba3e2ebac058b58e79881594bec16de131cafae7f469dd8dccbfcbdd41"},"schema_version":"1.0","source":{"id":"2605.25740","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25740","created_at":"2026-05-26T02:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25740v1","created_at":"2026-05-26T02:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25740","created_at":"2026-05-26T02:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"MPKDLZVJCYMW","created_at":"2026-05-26T02:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"MPKDLZVJCYMWIGVA","created_at":"2026-05-26T02:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"MPKDLZVJ","created_at":"2026-05-26T02:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:a342ffe72e2b89a3ef9e07a4d0c1d307e098a5839698e882b8a93056915d57b4","target":"graph","created_at":"2026-05-26T02:04:52Z","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/2605.25740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline goal-conditioned reinforcement learning (GCRL) provides a practical framework for obtaining goal-reaching policies from fixed datasets. However, learning a reliable goal-conditioned value function in long-horizon tasks remains challenging. In this paper, we identify erroneous generalization in goal-conditioned value functions as a fundamental bottleneck, and demonstrate that appropriate inductive bias in the value function is crucial for addressing the bottleneck. Building on these findings, we propose Latent-Aligned Value Learning (LAVL), an offline GCRL algorithm that integrates late","authors_text":"Byeongchan Kim, Hyungkyu Kang, Min-hwan Oh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T11:54:04Z","title":"Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25740","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:ba4455f8d2d82bb2c43a0f916533c9b3dd0b0f3ee9517c3a86c242214be72227","target":"record","created_at":"2026-05-26T02:04:52Z","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":"d4bf92b3483b84b6b8c5f301dcbb9384a1075e05a098e30a3701e54c480eeec4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T11:54:04Z","title_canon_sha256":"f9a68dba3e2ebac058b58e79881594bec16de131cafae7f469dd8dccbfcbdd41"},"schema_version":"1.0","source":{"id":"2605.25740","kind":"arxiv","version":1}},"canonical_sha256":"63d435e6a91619641aa00a711a2cc5830c042351ae780fc641e213bbdac6634a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63d435e6a91619641aa00a711a2cc5830c042351ae780fc641e213bbdac6634a","first_computed_at":"2026-05-26T02:04:52.820627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:52.820627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ym+rOAFLLjGP/cyrxwvF7UqJL48DX4JFV5xNlzcY+6XTIFjLudz8F5+4sKMFV78JIjfomLNl0T4sLt8cZ/+uCA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:52.821124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25740","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba4455f8d2d82bb2c43a0f916533c9b3dd0b0f3ee9517c3a86c242214be72227","sha256:a342ffe72e2b89a3ef9e07a4d0c1d307e098a5839698e882b8a93056915d57b4"],"state_sha256":"4634d986d96279d790e936a40cd2ac611c78df77eea2c530d315ee5fe38add2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GU6WKLprLySKTd/ZKsFThjgE4AEqQtsTV5HaHKwdKE47GA6fi9gUCgFNEyprMA14emvMRqMhKt3tcY1xmCNKBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T18:46:25.815205Z","bundle_sha256":"3f0937d16fc81b72672ce99ea70dda66a573675e87f3fc07e2d6ea2123d7bb29"}}