{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3UFLGHTPXQYDANHRKNTIVAKYWX","short_pith_number":"pith:3UFLGHTP","canonical_record":{"source":{"id":"2411.06815","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T09:22:09Z","cross_cats_sorted":[],"title_canon_sha256":"f3b74be802af35d6630cef7132ad34096071c181ba54ccc675b576d497a0bdbe","abstract_canon_sha256":"aa9c002b08cbc72d399cc5aa351dc9809f33c1644c65b4687b51b1da0fcb016f"},"schema_version":"1.0"},"canonical_sha256":"dd0ab31e6fbc303034f153668a8158b5c0c4c26903a1584a1eb90f423f757e0f","source":{"kind":"arxiv","id":"2411.06815","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06815","created_at":"2026-07-05T09:33:52Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06815v1","created_at":"2026-07-05T09:33:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06815","created_at":"2026-07-05T09:33:52Z"},{"alias_kind":"pith_short_12","alias_value":"3UFLGHTPXQYD","created_at":"2026-07-05T09:33:52Z"},{"alias_kind":"pith_short_16","alias_value":"3UFLGHTPXQYDANHR","created_at":"2026-07-05T09:33:52Z"},{"alias_kind":"pith_short_8","alias_value":"3UFLGHTP","created_at":"2026-07-05T09:33:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3UFLGHTPXQYDANHRKNTIVAKYWX","target":"record","payload":{"canonical_record":{"source":{"id":"2411.06815","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T09:22:09Z","cross_cats_sorted":[],"title_canon_sha256":"f3b74be802af35d6630cef7132ad34096071c181ba54ccc675b576d497a0bdbe","abstract_canon_sha256":"aa9c002b08cbc72d399cc5aa351dc9809f33c1644c65b4687b51b1da0fcb016f"},"schema_version":"1.0"},"canonical_sha256":"dd0ab31e6fbc303034f153668a8158b5c0c4c26903a1584a1eb90f423f757e0f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:52.180926Z","signature_b64":"u6aGLG/CGaNw+iCNHLU2klfj7BEo6RLya2qvlY2cEpQlbXx5kKjFuvplARI+KXWm2PgcajEM8nk1lfDvgK6qCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd0ab31e6fbc303034f153668a8158b5c0c4c26903a1584a1eb90f423f757e0f","last_reissued_at":"2026-07-05T09:33:52.180432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:52.180432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.06815","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":"2026-07-05T09:33:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tn16WIcUWnzRD3xetMvZz5ieBe3Py5yFwkjbLK/Wmpp4qdqxfleqhL3rny/3tU0uQ7qqDv+xCYZpRyz1fKkpCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T17:41:32.522153Z"},"content_sha256":"6e428f327cbcd232308e5d97de82e2bb348459a3f01b8c4ed3eba7c5daf5d3ea","schema_version":"1.0","event_id":"sha256:6e428f327cbcd232308e5d97de82e2bb348459a3f01b8c4ed3eba7c5daf5d3ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3UFLGHTPXQYDANHRKNTIVAKYWX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Streetwise Agents: Empowering Offline RL Policies to Outsmart Exogenous Stochastic Disturbances in RTC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Soni, Anjaly Parayil, Chetan Bansal, Ching-An Cheng, Gabriel Mittag, Mayukh Das, Sami Khairy, Shivam Shandilya, Supriyo Ghosh, Vishak Gopal, Yasaman Hosseinkashi","submitted_at":"2024-11-11T09:22:09Z","abstract_excerpt":"The difficulty of exploring and training online on real production systems limits the scope of real-time online data/feedback-driven decision making. The most feasible approach is to adopt offline reinforcement learning from limited trajectory samples. However, after deployment, such policies fail due to exogenous factors that temporarily or permanently disturb/alter the transition distribution of the assumed decision process structure induced by offline samples. This results in critical policy failures and generalization errors in sensitive domains like Real-Time Communication (RTC). We solve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06815","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/2411.06815/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":"2026-07-05T09:33:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CG6sDn7JD2rR++lL1muzWs6AOARe6h+J+1E4MByR1eUaGua+I/Ohvlrl3Ar+ehQeFRNGEvRuHO16EUyVkTsZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T17:41:32.522647Z"},"content_sha256":"273d3e481e93b8f992b39f3bbb90822ae11a9199e389a3f4d80b21083b432acb","schema_version":"1.0","event_id":"sha256:273d3e481e93b8f992b39f3bbb90822ae11a9199e389a3f4d80b21083b432acb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3UFLGHTPXQYDANHRKNTIVAKYWX/bundle.json","state_url":"https://pith.science/pith/3UFLGHTPXQYDANHRKNTIVAKYWX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3UFLGHTPXQYDANHRKNTIVAKYWX/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":"2026-08-22T17:41:32Z","links":{"resolver":"https://pith.science/pith/3UFLGHTPXQYDANHRKNTIVAKYWX","bundle":"https://pith.science/pith/3UFLGHTPXQYDANHRKNTIVAKYWX/bundle.json","state":"https://pith.science/pith/3UFLGHTPXQYDANHRKNTIVAKYWX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3UFLGHTPXQYDANHRKNTIVAKYWX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3UFLGHTPXQYDANHRKNTIVAKYWX","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":"aa9c002b08cbc72d399cc5aa351dc9809f33c1644c65b4687b51b1da0fcb016f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T09:22:09Z","title_canon_sha256":"f3b74be802af35d6630cef7132ad34096071c181ba54ccc675b576d497a0bdbe"},"schema_version":"1.0","source":{"id":"2411.06815","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06815","created_at":"2026-07-05T09:33:52Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06815v1","created_at":"2026-07-05T09:33:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06815","created_at":"2026-07-05T09:33:52Z"},{"alias_kind":"pith_short_12","alias_value":"3UFLGHTPXQYD","created_at":"2026-07-05T09:33:52Z"},{"alias_kind":"pith_short_16","alias_value":"3UFLGHTPXQYDANHR","created_at":"2026-07-05T09:33:52Z"},{"alias_kind":"pith_short_8","alias_value":"3UFLGHTP","created_at":"2026-07-05T09:33:52Z"}],"graph_snapshots":[{"event_id":"sha256:273d3e481e93b8f992b39f3bbb90822ae11a9199e389a3f4d80b21083b432acb","target":"graph","created_at":"2026-07-05T09:33:52Z","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/2411.06815/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The difficulty of exploring and training online on real production systems limits the scope of real-time online data/feedback-driven decision making. The most feasible approach is to adopt offline reinforcement learning from limited trajectory samples. However, after deployment, such policies fail due to exogenous factors that temporarily or permanently disturb/alter the transition distribution of the assumed decision process structure induced by offline samples. This results in critical policy failures and generalization errors in sensitive domains like Real-Time Communication (RTC). We solve","authors_text":"Aditya Soni, Anjaly Parayil, Chetan Bansal, Ching-An Cheng, Gabriel Mittag, Mayukh Das, Sami Khairy, Shivam Shandilya, Supriyo Ghosh, Vishak Gopal, Yasaman Hosseinkashi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T09:22:09Z","title":"Streetwise Agents: Empowering Offline RL Policies to Outsmart Exogenous Stochastic Disturbances in RTC"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06815","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":"sha256:6e428f327cbcd232308e5d97de82e2bb348459a3f01b8c4ed3eba7c5daf5d3ea","target":"record","created_at":"2026-07-05T09:33:52Z","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":"aa9c002b08cbc72d399cc5aa351dc9809f33c1644c65b4687b51b1da0fcb016f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T09:22:09Z","title_canon_sha256":"f3b74be802af35d6630cef7132ad34096071c181ba54ccc675b576d497a0bdbe"},"schema_version":"1.0","source":{"id":"2411.06815","kind":"arxiv","version":1}},"canonical_sha256":"dd0ab31e6fbc303034f153668a8158b5c0c4c26903a1584a1eb90f423f757e0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd0ab31e6fbc303034f153668a8158b5c0c4c26903a1584a1eb90f423f757e0f","first_computed_at":"2026-07-05T09:33:52.180432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:52.180432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u6aGLG/CGaNw+iCNHLU2klfj7BEo6RLya2qvlY2cEpQlbXx5kKjFuvplARI+KXWm2PgcajEM8nk1lfDvgK6qCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:52.180926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.06815","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e428f327cbcd232308e5d97de82e2bb348459a3f01b8c4ed3eba7c5daf5d3ea","sha256:273d3e481e93b8f992b39f3bbb90822ae11a9199e389a3f4d80b21083b432acb"],"state_sha256":"f4f13fe0cfbceb3364019c74aa150dccce5f7fdd4bf650a34848b90e6ca357f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5czKYWibBNwbjZMCGqywHWY/xiTPCeYKdzrEJeE/qhiIgJOtq5bxGuYg8KNaUSI08lHPxxp2ljHcnhLLo/0cDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T17:41:32.527541Z","bundle_sha256":"03814bfd11e4ff90c6a003df69023a548b396210fc760c730c18b0cdad7d1994"}}