{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VLADR4IFIG6RE66QDNSS2PLLLK","short_pith_number":"pith:VLADR4IF","canonical_record":{"source":{"id":"2507.19437","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T17:08:16Z","cross_cats_sorted":[],"title_canon_sha256":"3acb9f59198acae7393e4ccffec300f066362ba7deeab4da00b7bf90c4229382","abstract_canon_sha256":"5b7d0436cab8a2f85af224ee8166f10023a237cff8186e10965184dc98a7ab28"},"schema_version":"1.0"},"canonical_sha256":"aac038f10541bd127bd01b652d3d6b5a80097b00bc6c76b36c539a9b9640a0b4","source":{"kind":"arxiv","id":"2507.19437","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19437","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19437v1","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19437","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"pith_short_12","alias_value":"VLADR4IFIG6R","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"pith_short_16","alias_value":"VLADR4IFIG6RE66Q","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"pith_short_8","alias_value":"VLADR4IF","created_at":"2026-07-05T11:43:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VLADR4IFIG6RE66QDNSS2PLLLK","target":"record","payload":{"canonical_record":{"source":{"id":"2507.19437","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T17:08:16Z","cross_cats_sorted":[],"title_canon_sha256":"3acb9f59198acae7393e4ccffec300f066362ba7deeab4da00b7bf90c4229382","abstract_canon_sha256":"5b7d0436cab8a2f85af224ee8166f10023a237cff8186e10965184dc98a7ab28"},"schema_version":"1.0"},"canonical_sha256":"aac038f10541bd127bd01b652d3d6b5a80097b00bc6c76b36c539a9b9640a0b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:25.313687Z","signature_b64":"8E1Th1DHlRjZuK/ofpULB33mjYUrupV2BGv57BNfgisC5ZWYNRE0E04H9DHgqtc9E2cURfZMxGtJM0xCKgboBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aac038f10541bd127bd01b652d3d6b5a80097b00bc6c76b36c539a9b9640a0b4","last_reissued_at":"2026-07-05T11:43:25.313165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:25.313165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.19437","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":"2026-07-05T11:43:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g4Qc8sJLUMVGCXixY7ZhiHB+WpbsMYTYxP1zVEOZ6iMbpDoQCqpd7MGO1oT5O3llnRjyyL4Z5T/ua+poadbpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:45:56.283325Z"},"content_sha256":"63d2684b1528a88882c77ee2d917d81ba8dba64a08b2d1cfe33ce09f09492c03","schema_version":"1.0","event_id":"sha256:63d2684b1528a88882c77ee2d917d81ba8dba64a08b2d1cfe33ce09f09492c03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VLADR4IFIG6RE66QDNSS2PLLLK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Observations Meet Actions: Learning Control-Sufficient Representations for Robust Policy Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongpeng Cao, Marco Caccamo, Naira Hovakimyan, Yuliang Gu","submitted_at":"2025-07-25T17:08:16Z","abstract_excerpt":"Capturing latent variations (\"contexts\") is key to deploying reinforcement-learning (RL) agents beyond their training regime. We recast context-based RL as a dual inference-control problem and formally characterize two properties and their hierarchy: observation sufficiency (preserving all predictive information) and control sufficiency (retaining decision-making relevant information). Exploiting this dichotomy, we derive a contextual evidence lower bound(ELBO)-style objective that cleanly separates representation learning from policy learning and optimizes it with Bottlenecked Contextual Poli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19437","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/2507.19437/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":"2026-07-05T11:43:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eNyvP40w+9vOMOdqjmd7NpCh9WNH4Oy+gv3mtQs2uv3bTpPw/U9eYrVv9ig4ZuwYndbqPdBSBAKNNoNwsIr0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:45:56.283991Z"},"content_sha256":"a6313f10fd6ff056e05fbfa7d82029c0bd2bb6a169423af925f3176bcecb574d","schema_version":"1.0","event_id":"sha256:a6313f10fd6ff056e05fbfa7d82029c0bd2bb6a169423af925f3176bcecb574d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VLADR4IFIG6RE66QDNSS2PLLLK/bundle.json","state_url":"https://pith.science/pith/VLADR4IFIG6RE66QDNSS2PLLLK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VLADR4IFIG6RE66QDNSS2PLLLK/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":"2026-07-07T05:45:56Z","links":{"resolver":"https://pith.science/pith/VLADR4IFIG6RE66QDNSS2PLLLK","bundle":"https://pith.science/pith/VLADR4IFIG6RE66QDNSS2PLLLK/bundle.json","state":"https://pith.science/pith/VLADR4IFIG6RE66QDNSS2PLLLK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VLADR4IFIG6RE66QDNSS2PLLLK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VLADR4IFIG6RE66QDNSS2PLLLK","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":"5b7d0436cab8a2f85af224ee8166f10023a237cff8186e10965184dc98a7ab28","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T17:08:16Z","title_canon_sha256":"3acb9f59198acae7393e4ccffec300f066362ba7deeab4da00b7bf90c4229382"},"schema_version":"1.0","source":{"id":"2507.19437","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19437","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19437v1","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19437","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"pith_short_12","alias_value":"VLADR4IFIG6R","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"pith_short_16","alias_value":"VLADR4IFIG6RE66Q","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"pith_short_8","alias_value":"VLADR4IF","created_at":"2026-07-05T11:43:25Z"}],"graph_snapshots":[{"event_id":"sha256:a6313f10fd6ff056e05fbfa7d82029c0bd2bb6a169423af925f3176bcecb574d","target":"graph","created_at":"2026-07-05T11:43:25Z","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/2507.19437/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Capturing latent variations (\"contexts\") is key to deploying reinforcement-learning (RL) agents beyond their training regime. We recast context-based RL as a dual inference-control problem and formally characterize two properties and their hierarchy: observation sufficiency (preserving all predictive information) and control sufficiency (retaining decision-making relevant information). Exploiting this dichotomy, we derive a contextual evidence lower bound(ELBO)-style objective that cleanly separates representation learning from policy learning and optimizes it with Bottlenecked Contextual Poli","authors_text":"Hongpeng Cao, Marco Caccamo, Naira Hovakimyan, Yuliang Gu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T17:08:16Z","title":"Observations Meet Actions: Learning Control-Sufficient Representations for Robust Policy Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19437","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":"sha256:63d2684b1528a88882c77ee2d917d81ba8dba64a08b2d1cfe33ce09f09492c03","target":"record","created_at":"2026-07-05T11:43:25Z","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":"5b7d0436cab8a2f85af224ee8166f10023a237cff8186e10965184dc98a7ab28","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T17:08:16Z","title_canon_sha256":"3acb9f59198acae7393e4ccffec300f066362ba7deeab4da00b7bf90c4229382"},"schema_version":"1.0","source":{"id":"2507.19437","kind":"arxiv","version":1}},"canonical_sha256":"aac038f10541bd127bd01b652d3d6b5a80097b00bc6c76b36c539a9b9640a0b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aac038f10541bd127bd01b652d3d6b5a80097b00bc6c76b36c539a9b9640a0b4","first_computed_at":"2026-07-05T11:43:25.313165Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:25.313165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8E1Th1DHlRjZuK/ofpULB33mjYUrupV2BGv57BNfgisC5ZWYNRE0E04H9DHgqtc9E2cURfZMxGtJM0xCKgboBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:25.313687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19437","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63d2684b1528a88882c77ee2d917d81ba8dba64a08b2d1cfe33ce09f09492c03","sha256:a6313f10fd6ff056e05fbfa7d82029c0bd2bb6a169423af925f3176bcecb574d"],"state_sha256":"671f01e8f83e0b50c2a068910044b94716b38b66367e6346917c4591d496fa36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v63ZMT//e9QB+Q0JbZwftNHRhERFblJPh2dNPxWrxjoMG83EQufW8ul2JjbNUI4qhhMPAmAb8pXHfwKU0M0aDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:45:56.287904Z","bundle_sha256":"169e96e86e2a716966b2a96699ed9955fd7c99c4efdc14f8f6d5b930678f2835"}}