{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:D5APOQ4LJ4MEJYQ2YQCISBLXEY","short_pith_number":"pith:D5APOQ4L","canonical_record":{"source":{"id":"2607.27574","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T01:29:57Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"469e01747253b071dbe2889e59aab2bfb475dbe7591e6a3b106c790032897209","abstract_canon_sha256":"5a6401e246c0014263805fb8acd2dca008fa583757bcbd0af4314ff086b005a4"},"schema_version":"1.0"},"canonical_sha256":"1f40f7438b4f1844e21ac4048905772601dbab750851569487f266fabd511dfc","source":{"kind":"arxiv","id":"2607.27574","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27574","created_at":"2026-07-31T01:26:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27574v1","created_at":"2026-07-31T01:26:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27574","created_at":"2026-07-31T01:26:24Z"},{"alias_kind":"pith_short_12","alias_value":"D5APOQ4LJ4ME","created_at":"2026-07-31T01:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"D5APOQ4LJ4MEJYQ2","created_at":"2026-07-31T01:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"D5APOQ4L","created_at":"2026-07-31T01:26:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:D5APOQ4LJ4MEJYQ2YQCISBLXEY","target":"record","payload":{"canonical_record":{"source":{"id":"2607.27574","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T01:29:57Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"469e01747253b071dbe2889e59aab2bfb475dbe7591e6a3b106c790032897209","abstract_canon_sha256":"5a6401e246c0014263805fb8acd2dca008fa583757bcbd0af4314ff086b005a4"},"schema_version":"1.0"},"canonical_sha256":"1f40f7438b4f1844e21ac4048905772601dbab750851569487f266fabd511dfc","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f40f7438b4f1844e21ac4048905772601dbab750851569487f266fabd511dfc","last_reissued_at":"2026-07-31T01:26:24.961906Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:26:24.961906Z"},"source_kind":"arxiv","source_id":"2607.27574","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":"2026-07-31T01:26:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YsVkLhP+BMdyQ8zjleWTfDBiXAsRZjKHX9eCt3Y5OxdGTSiLTl+NQPpxZucSfnAGnoDD868lKj7jQnPE0IgbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:21:29.097460Z"},"content_sha256":"3efd93575b7c8074cd27ece60f25ecfde939d0bf6d18e3a61e334ea56a3bbc8b","schema_version":"1.0","event_id":"sha256:3efd93575b7c8074cd27ece60f25ecfde939d0bf6d18e3a61e334ea56a3bbc8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:D5APOQ4LJ4MEJYQ2YQCISBLXEY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Gradient Steering: Interventions from Behavioral Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Aur\\'elie Beynier, Nicolas Maudet, Yoann Poupart","submitted_at":"2026-07-30T01:29:57Z","abstract_excerpt":"Activation steering has emerged in large language models as a lightweight alternative for dynamically changing a model's behavior at inference time. However, we show that existing steering methods fail to steer even a simple policy in a two-route gridworld environment. To address this limitation, we propose Policy Gradient Steering (PGS), which formulates steering as a reinforcement learning problem. PGS accumulates gradients of a temporary behavioral objective over a small set of rollouts or demonstrations to construct a removable task vector. We first demonstrate the calibration and reversib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27574","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/2607.27574/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":"2026-07-31T01:26:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I+672LvkOhGdh5Gd1mg5QVQqQY0ZcC02Nm096zWLyxrwushS9d8UCVCVONBLFZtWXOMw9bsrNi9dJjMMhpwKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:21:29.097961Z"},"content_sha256":"e0b08ca7f9f48492989788e31184b50b095d158542505bf1e9b46885da21fbba","schema_version":"1.0","event_id":"sha256:e0b08ca7f9f48492989788e31184b50b095d158542505bf1e9b46885da21fbba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D5APOQ4LJ4MEJYQ2YQCISBLXEY/bundle.json","state_url":"https://pith.science/pith/D5APOQ4LJ4MEJYQ2YQCISBLXEY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D5APOQ4LJ4MEJYQ2YQCISBLXEY/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":"2026-08-09T08:21:29Z","links":{"resolver":"https://pith.science/pith/D5APOQ4LJ4MEJYQ2YQCISBLXEY","bundle":"https://pith.science/pith/D5APOQ4LJ4MEJYQ2YQCISBLXEY/bundle.json","state":"https://pith.science/pith/D5APOQ4LJ4MEJYQ2YQCISBLXEY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D5APOQ4LJ4MEJYQ2YQCISBLXEY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D5APOQ4LJ4MEJYQ2YQCISBLXEY","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":"5a6401e246c0014263805fb8acd2dca008fa583757bcbd0af4314ff086b005a4","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T01:29:57Z","title_canon_sha256":"469e01747253b071dbe2889e59aab2bfb475dbe7591e6a3b106c790032897209"},"schema_version":"1.0","source":{"id":"2607.27574","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27574","created_at":"2026-07-31T01:26:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27574v1","created_at":"2026-07-31T01:26:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27574","created_at":"2026-07-31T01:26:24Z"},{"alias_kind":"pith_short_12","alias_value":"D5APOQ4LJ4ME","created_at":"2026-07-31T01:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"D5APOQ4LJ4MEJYQ2","created_at":"2026-07-31T01:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"D5APOQ4L","created_at":"2026-07-31T01:26:24Z"}],"graph_snapshots":[{"event_id":"sha256:e0b08ca7f9f48492989788e31184b50b095d158542505bf1e9b46885da21fbba","target":"graph","created_at":"2026-07-31T01:26:24Z","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/2607.27574/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Activation steering has emerged in large language models as a lightweight alternative for dynamically changing a model's behavior at inference time. However, we show that existing steering methods fail to steer even a simple policy in a two-route gridworld environment. To address this limitation, we propose Policy Gradient Steering (PGS), which formulates steering as a reinforcement learning problem. PGS accumulates gradients of a temporary behavioral objective over a small set of rollouts or demonstrations to construct a removable task vector. We first demonstrate the calibration and reversib","authors_text":"Aur\\'elie Beynier, Nicolas Maudet, Yoann Poupart","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T01:29:57Z","title":"Policy Gradient Steering: Interventions from Behavioral Objectives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27574","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":"sha256:3efd93575b7c8074cd27ece60f25ecfde939d0bf6d18e3a61e334ea56a3bbc8b","target":"record","created_at":"2026-07-31T01:26:24Z","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":"5a6401e246c0014263805fb8acd2dca008fa583757bcbd0af4314ff086b005a4","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T01:29:57Z","title_canon_sha256":"469e01747253b071dbe2889e59aab2bfb475dbe7591e6a3b106c790032897209"},"schema_version":"1.0","source":{"id":"2607.27574","kind":"arxiv","version":1}},"canonical_sha256":"1f40f7438b4f1844e21ac4048905772601dbab750851569487f266fabd511dfc","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f40f7438b4f1844e21ac4048905772601dbab750851569487f266fabd511dfc","first_computed_at":"2026-07-31T01:26:24.961906Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:26:24.961906Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27574","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3efd93575b7c8074cd27ece60f25ecfde939d0bf6d18e3a61e334ea56a3bbc8b","sha256:e0b08ca7f9f48492989788e31184b50b095d158542505bf1e9b46885da21fbba"],"state_sha256":"8e03686a763bceffcb7c71a908e8a1dc26b066a2a19c5f68df394062c7688bd3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jXbvWQfOrrQkUoDpj0ExXMoCUKATJwmLJ4Gdgt+OFa0E4ChK3IDto7bleC0+tC/fWJvAtkB3KvB5CACcZzjRAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:21:29.102436Z","bundle_sha256":"71f2c035514bf000cdc73523303c4574dfdc8d557881a73ee8d45eda5de8074e"}}