{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VSYNMMNEHXLINSCQ3N34ZLIPFA","short_pith_number":"pith:VSYNMMNE","canonical_record":{"source":{"id":"2608.11052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T15:22:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dad4b1e8afd2c6e107a3e43cf78aee6298a6cbe2f9fc72d98efc3c2e50bbcb24","abstract_canon_sha256":"7633696a726e20874bdc592225f283a683835aae1618a7283e7e6ee26a3b2781"},"schema_version":"1.0"},"canonical_sha256":"acb0d631a43dd686c850db77ccad0f2816fee23c08247334ddb2fdefb5c06cc5","source":{"kind":"arxiv","id":"2608.11052","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11052","created_at":"2026-08-12T01:24:30Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11052v1","created_at":"2026-08-12T01:24:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11052","created_at":"2026-08-12T01:24:30Z"},{"alias_kind":"pith_short_12","alias_value":"VSYNMMNEHXLI","created_at":"2026-08-12T01:24:30Z"},{"alias_kind":"pith_short_16","alias_value":"VSYNMMNEHXLINSCQ","created_at":"2026-08-12T01:24:30Z"},{"alias_kind":"pith_short_8","alias_value":"VSYNMMNE","created_at":"2026-08-12T01:24:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VSYNMMNEHXLINSCQ3N34ZLIPFA","target":"record","payload":{"canonical_record":{"source":{"id":"2608.11052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T15:22:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dad4b1e8afd2c6e107a3e43cf78aee6298a6cbe2f9fc72d98efc3c2e50bbcb24","abstract_canon_sha256":"7633696a726e20874bdc592225f283a683835aae1618a7283e7e6ee26a3b2781"},"schema_version":"1.0"},"canonical_sha256":"acb0d631a43dd686c850db77ccad0f2816fee23c08247334ddb2fdefb5c06cc5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:24:30.486909Z","signature_b64":"mbQYb4nb2nG9yOJnvYP3v2d9wFZUinFPaS6YrphKe84BEJxS+E2lsg4kbpNPCT18kbVhvzfTJ2ch6GbCD2gSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acb0d631a43dd686c850db77ccad0f2816fee23c08247334ddb2fdefb5c06cc5","last_reissued_at":"2026-08-12T01:24:30.485341Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:24:30.485341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.11052","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":"2026-08-12T01:24:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VfI+GVw/PEbAeRIGZ6YqlZtD2yOJAyNR+D3dqiB4dfk+CuVbtuMYfpsUWC83tNjvi7/2GNmWN9cIWYiCUc9+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:08:12.278121Z"},"content_sha256":"9142286bca19e1b6406de671a348a1bda40c3064b01d1c6eb2b108514844b40b","schema_version":"1.0","event_id":"sha256:9142286bca19e1b6406de671a348a1bda40c3064b01d1c6eb2b108514844b40b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VSYNMMNEHXLINSCQ3N34ZLIPFA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Hypergradient Descent for Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anna Barabanova, Ilya Levin, Karina Ivanova, Marina Sheshukova, Nikita Sevriukov, Sofiia Kasaeva, Uliana Gagarina","submitted_at":"2026-08-11T15:22:16Z","abstract_excerpt":"Inverse reinforcement learning (IRL) aims to recover a reward function under which the resulting policy reproduces the behavior observed in expert demonstrations. A natural approach is to formulate IRL as a bilevel optimization problem, in which the inner level corresponds to policy optimization under the learned reward and the outer level measures the discrepancy between the induced policy and expert data. However, this formulation is computationally challenging in practice because the outer update requires a hypergradient involving an inverse-Hessian-vector product for the inner objective. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11052","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/2608.11052/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":"2026-08-12T01:24:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"swNqymakpdwEWOLl9FbEfXJUP8kQKbM8UA6FAipubb/0lS2Iu+jggIB6VQighSQk942trqcys5+TdM5ht5OZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:08:12.279179Z"},"content_sha256":"23fb2f670af74f8a0cb5c00414b54fd5ce0324d47cfa5c97b939f68fc6f4dc3e","schema_version":"1.0","event_id":"sha256:23fb2f670af74f8a0cb5c00414b54fd5ce0324d47cfa5c97b939f68fc6f4dc3e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VSYNMMNEHXLINSCQ3N34ZLIPFA/bundle.json","state_url":"https://pith.science/pith/VSYNMMNEHXLINSCQ3N34ZLIPFA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VSYNMMNEHXLINSCQ3N34ZLIPFA/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":"2026-08-18T20:08:12Z","links":{"resolver":"https://pith.science/pith/VSYNMMNEHXLINSCQ3N34ZLIPFA","bundle":"https://pith.science/pith/VSYNMMNEHXLINSCQ3N34ZLIPFA/bundle.json","state":"https://pith.science/pith/VSYNMMNEHXLINSCQ3N34ZLIPFA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VSYNMMNEHXLINSCQ3N34ZLIPFA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VSYNMMNEHXLINSCQ3N34ZLIPFA","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":"7633696a726e20874bdc592225f283a683835aae1618a7283e7e6ee26a3b2781","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T15:22:16Z","title_canon_sha256":"dad4b1e8afd2c6e107a3e43cf78aee6298a6cbe2f9fc72d98efc3c2e50bbcb24"},"schema_version":"1.0","source":{"id":"2608.11052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11052","created_at":"2026-08-12T01:24:30Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11052v1","created_at":"2026-08-12T01:24:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11052","created_at":"2026-08-12T01:24:30Z"},{"alias_kind":"pith_short_12","alias_value":"VSYNMMNEHXLI","created_at":"2026-08-12T01:24:30Z"},{"alias_kind":"pith_short_16","alias_value":"VSYNMMNEHXLINSCQ","created_at":"2026-08-12T01:24:30Z"},{"alias_kind":"pith_short_8","alias_value":"VSYNMMNE","created_at":"2026-08-12T01:24:30Z"}],"graph_snapshots":[{"event_id":"sha256:23fb2f670af74f8a0cb5c00414b54fd5ce0324d47cfa5c97b939f68fc6f4dc3e","target":"graph","created_at":"2026-08-12T01:24:30Z","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/2608.11052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inverse reinforcement learning (IRL) aims to recover a reward function under which the resulting policy reproduces the behavior observed in expert demonstrations. A natural approach is to formulate IRL as a bilevel optimization problem, in which the inner level corresponds to policy optimization under the learned reward and the outer level measures the discrepancy between the induced policy and expert data. However, this formulation is computationally challenging in practice because the outer update requires a hypergradient involving an inverse-Hessian-vector product for the inner objective. W","authors_text":"Anna Barabanova, Ilya Levin, Karina Ivanova, Marina Sheshukova, Nikita Sevriukov, Sofiia Kasaeva, Uliana Gagarina","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T15:22:16Z","title":"Efficient Hypergradient Descent for Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11052","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":"sha256:9142286bca19e1b6406de671a348a1bda40c3064b01d1c6eb2b108514844b40b","target":"record","created_at":"2026-08-12T01:24:30Z","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":"7633696a726e20874bdc592225f283a683835aae1618a7283e7e6ee26a3b2781","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-11T15:22:16Z","title_canon_sha256":"dad4b1e8afd2c6e107a3e43cf78aee6298a6cbe2f9fc72d98efc3c2e50bbcb24"},"schema_version":"1.0","source":{"id":"2608.11052","kind":"arxiv","version":1}},"canonical_sha256":"acb0d631a43dd686c850db77ccad0f2816fee23c08247334ddb2fdefb5c06cc5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acb0d631a43dd686c850db77ccad0f2816fee23c08247334ddb2fdefb5c06cc5","first_computed_at":"2026-08-12T01:24:30.485341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:24:30.485341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mbQYb4nb2nG9yOJnvYP3v2d9wFZUinFPaS6YrphKe84BEJxS+E2lsg4kbpNPCT18kbVhvzfTJ2ch6GbCD2gSBg==","signature_status":"signed_v1","signed_at":"2026-08-12T01:24:30.486909Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9142286bca19e1b6406de671a348a1bda40c3064b01d1c6eb2b108514844b40b","sha256:23fb2f670af74f8a0cb5c00414b54fd5ce0324d47cfa5c97b939f68fc6f4dc3e"],"state_sha256":"10b6404820eba01ce28d60970de7f72edee104ea8e6cb264f2fed96f82b351ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zUjziu/lbTtptskC2gXBn/S6mX1n2An18hDYILnm6gE0YpDasd78+nCm493Ys8buXQCZ+YLhlGlJJtXJdLQwCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:08:12.284836Z","bundle_sha256":"b0b129de99d8b6f66aac1d5ea0c13bcdc1b847d3fd938553459b820b5a659018"}}