{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GG7J4I7GEG4FT2KWVPODVUTEIA","short_pith_number":"pith:GG7J4I7G","canonical_record":{"source":{"id":"2606.13461","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T15:16:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4a06bf4e83a3b0c9f5a975e3f670194ad9bc8be22efac088e9ada6b0225400b6","abstract_canon_sha256":"53fd173dc84038b1d5a55afd0ab28aa3a6c231f2e39628c05cb22f8ac6409f04"},"schema_version":"1.0"},"canonical_sha256":"31be9e23e621b859e956abdc3ad264402b79f8bfac6aeeccdb99bb92859d950d","source":{"kind":"arxiv","id":"2606.13461","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13461","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13461v1","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13461","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"pith_short_12","alias_value":"GG7J4I7GEG4F","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"pith_short_16","alias_value":"GG7J4I7GEG4FT2KW","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"pith_short_8","alias_value":"GG7J4I7G","created_at":"2026-06-12T01:10:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GG7J4I7GEG4FT2KWVPODVUTEIA","target":"record","payload":{"canonical_record":{"source":{"id":"2606.13461","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T15:16:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4a06bf4e83a3b0c9f5a975e3f670194ad9bc8be22efac088e9ada6b0225400b6","abstract_canon_sha256":"53fd173dc84038b1d5a55afd0ab28aa3a6c231f2e39628c05cb22f8ac6409f04"},"schema_version":"1.0"},"canonical_sha256":"31be9e23e621b859e956abdc3ad264402b79f8bfac6aeeccdb99bb92859d950d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:10:03.760207Z","signature_b64":"XvY6xiE1viMioWjqk3H5jO/zV1M8qAAeMyVcpgWf9TNSjjsLNZpC7hvX5YfnYt23OY7l9zJ8Edr2Bjr8alJfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31be9e23e621b859e956abdc3ad264402b79f8bfac6aeeccdb99bb92859d950d","last_reissued_at":"2026-06-12T01:10:03.759210Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:10:03.759210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.13461","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":"2026-06-12T01:10:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qobvaIUuP0nFvhTNTnLZzPQvO+i1elz823w0ZH9eRA30EWgNkkpSFsafTdNwHJepAYHe5C+zU145OrxG1RokDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T01:36:29.718207Z"},"content_sha256":"ae769281da0c92c9ad3cf29324f1db2509cd97a39e428621ccf9430dd5376ac9","schema_version":"1.0","event_id":"sha256:ae769281da0c92c9ad3cf29324f1db2509cd97a39e428621ccf9430dd5376ac9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GG7J4I7GEG4FT2KWVPODVUTEIA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Neural Model Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Shaivi Malik","submitted_at":"2026-06-11T15:16:42Z","abstract_excerpt":"Editing pretrained neural networks requires specialized algorithms tailored to specific objectives. Designing such algorithms is often time-consuming and demands significant effort. We present an exploratory framework that formulates neural model editing as a reinforcement learning problem, where agents modify models using reward feedback. We introduce two environments: MaskWorld, where agents scale weights multiplicatively, and ShiftWorld, where agents apply additive weight updates. The reward function combines a utility-preservation objective with a task-specific editing objective, enabling "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13461","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/2606.13461/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":"2026-06-12T01:10:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"viuaXl2huGx/9dHaSJA1OcdXPy6/cdcg0/ZWHbl7Ax8WV42Slnrc9Tnl7iRPbDdtVSjtMCBXtQ3QkoSqf2KDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T01:36:29.718829Z"},"content_sha256":"485188b53a17779d5d482cb9ac6d0e2ed2631b5bb1780d41ea6e0d1534116575","schema_version":"1.0","event_id":"sha256:485188b53a17779d5d482cb9ac6d0e2ed2631b5bb1780d41ea6e0d1534116575"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GG7J4I7GEG4FT2KWVPODVUTEIA/bundle.json","state_url":"https://pith.science/pith/GG7J4I7GEG4FT2KWVPODVUTEIA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GG7J4I7GEG4FT2KWVPODVUTEIA/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":"2026-07-04T01:36:29Z","links":{"resolver":"https://pith.science/pith/GG7J4I7GEG4FT2KWVPODVUTEIA","bundle":"https://pith.science/pith/GG7J4I7GEG4FT2KWVPODVUTEIA/bundle.json","state":"https://pith.science/pith/GG7J4I7GEG4FT2KWVPODVUTEIA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GG7J4I7GEG4FT2KWVPODVUTEIA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GG7J4I7GEG4FT2KWVPODVUTEIA","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":"53fd173dc84038b1d5a55afd0ab28aa3a6c231f2e39628c05cb22f8ac6409f04","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T15:16:42Z","title_canon_sha256":"4a06bf4e83a3b0c9f5a975e3f670194ad9bc8be22efac088e9ada6b0225400b6"},"schema_version":"1.0","source":{"id":"2606.13461","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13461","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13461v1","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13461","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"pith_short_12","alias_value":"GG7J4I7GEG4F","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"pith_short_16","alias_value":"GG7J4I7GEG4FT2KW","created_at":"2026-06-12T01:10:03Z"},{"alias_kind":"pith_short_8","alias_value":"GG7J4I7G","created_at":"2026-06-12T01:10:03Z"}],"graph_snapshots":[{"event_id":"sha256:485188b53a17779d5d482cb9ac6d0e2ed2631b5bb1780d41ea6e0d1534116575","target":"graph","created_at":"2026-06-12T01:10:03Z","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/2606.13461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Editing pretrained neural networks requires specialized algorithms tailored to specific objectives. Designing such algorithms is often time-consuming and demands significant effort. We present an exploratory framework that formulates neural model editing as a reinforcement learning problem, where agents modify models using reward feedback. We introduce two environments: MaskWorld, where agents scale weights multiplicatively, and ShiftWorld, where agents apply additive weight updates. The reward function combines a utility-preservation objective with a task-specific editing objective, enabling ","authors_text":"Shaivi Malik","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T15:16:42Z","title":"Reinforcement Learning for Neural Model Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13461","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:ae769281da0c92c9ad3cf29324f1db2509cd97a39e428621ccf9430dd5376ac9","target":"record","created_at":"2026-06-12T01:10:03Z","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":"53fd173dc84038b1d5a55afd0ab28aa3a6c231f2e39628c05cb22f8ac6409f04","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T15:16:42Z","title_canon_sha256":"4a06bf4e83a3b0c9f5a975e3f670194ad9bc8be22efac088e9ada6b0225400b6"},"schema_version":"1.0","source":{"id":"2606.13461","kind":"arxiv","version":1}},"canonical_sha256":"31be9e23e621b859e956abdc3ad264402b79f8bfac6aeeccdb99bb92859d950d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31be9e23e621b859e956abdc3ad264402b79f8bfac6aeeccdb99bb92859d950d","first_computed_at":"2026-06-12T01:10:03.759210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:10:03.759210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XvY6xiE1viMioWjqk3H5jO/zV1M8qAAeMyVcpgWf9TNSjjsLNZpC7hvX5YfnYt23OY7l9zJ8Edr2Bjr8alJfBQ==","signature_status":"signed_v1","signed_at":"2026-06-12T01:10:03.760207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13461","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae769281da0c92c9ad3cf29324f1db2509cd97a39e428621ccf9430dd5376ac9","sha256:485188b53a17779d5d482cb9ac6d0e2ed2631b5bb1780d41ea6e0d1534116575"],"state_sha256":"c84fbc875e9e3da20cedb9ed2138409717c70a9d9b0ce15d2323e8211e0eaba2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZbX9y4NgWcdVp3VVqq739xpKuC/uOEd88iMYr4ncrp/2J+PKBAcQEQZqR81kdzi1UaRIw77dJ4ue+vrr716XDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T01:36:29.722199Z","bundle_sha256":"f35da0f5bdf6ef18cd6d1714006d86cbadf45107dc677f67d8b00cd8673a5b85"}}