{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RORN2USOLMRL6VS5HK7DDF6FD3","short_pith_number":"pith:RORN2USO","schema_version":"1.0","canonical_sha256":"8ba2dd524e5b22bf565d3abe3197c51ec1882d352bf6113bf11e6af7fd5d4e50","source":{"kind":"arxiv","id":"2509.04549","version":1},"attestation_state":"computed","paper":{"title":"Manipulating Transformer-Based Models: Controllability, Steerability, and Robust Interventions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Faruk Alpay, Taylan Alpay","submitted_at":"2025-09-04T17:32:56Z","abstract_excerpt":"Transformer-based language models excel in NLP tasks, but fine-grained control remains challenging. This paper explores methods for manipulating transformer models through principled interventions at three levels: prompts, activations, and weights. We formalize controllable text generation as an optimization problem addressable via prompt engineering, parameter-efficient fine-tuning, model editing, and reinforcement learning. We introduce a unified framework encompassing prompt-level steering, activation interventions, and weight-space edits. We analyze robustness and safety implications, incl"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.04549","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-04T17:32:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b628015f45e4273f2ca0bddf9fafc6465dbf7a8f11c03e8939588825a89e089d","abstract_canon_sha256":"a0576881994695e20671ed43bb270c648e24e1811a18f0b925dd9f4754e648d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:25.123016Z","signature_b64":"sBCZT0OsX80OACY0u5c+wwDCfV6PVNFMk73v106OFA/EkJTRUrhi4DJNPfo+JQjwOsCikACl2BOqG6elLlPIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ba2dd524e5b22bf565d3abe3197c51ec1882d352bf6113bf11e6af7fd5d4e50","last_reissued_at":"2026-07-05T12:05:25.122597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:25.122597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Manipulating Transformer-Based Models: Controllability, Steerability, and Robust Interventions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Faruk Alpay, Taylan Alpay","submitted_at":"2025-09-04T17:32:56Z","abstract_excerpt":"Transformer-based language models excel in NLP tasks, but fine-grained control remains challenging. This paper explores methods for manipulating transformer models through principled interventions at three levels: prompts, activations, and weights. We formalize controllable text generation as an optimization problem addressable via prompt engineering, parameter-efficient fine-tuning, model editing, and reinforcement learning. We introduce a unified framework encompassing prompt-level steering, activation interventions, and weight-space edits. We analyze robustness and safety implications, incl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04549","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/2509.04549/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.04549","created_at":"2026-07-05T12:05:25.122657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04549v1","created_at":"2026-07-05T12:05:25.122657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04549","created_at":"2026-07-05T12:05:25.122657+00:00"},{"alias_kind":"pith_short_12","alias_value":"RORN2USOLMRL","created_at":"2026-07-05T12:05:25.122657+00:00"},{"alias_kind":"pith_short_16","alias_value":"RORN2USOLMRL6VS5","created_at":"2026-07-05T12:05:25.122657+00:00"},{"alias_kind":"pith_short_8","alias_value":"RORN2USO","created_at":"2026-07-05T12:05:25.122657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RORN2USOLMRL6VS5HK7DDF6FD3","json":"https://pith.science/pith/RORN2USOLMRL6VS5HK7DDF6FD3.json","graph_json":"https://pith.science/api/pith-number/RORN2USOLMRL6VS5HK7DDF6FD3/graph.json","events_json":"https://pith.science/api/pith-number/RORN2USOLMRL6VS5HK7DDF6FD3/events.json","paper":"https://pith.science/paper/RORN2USO"},"agent_actions":{"view_html":"https://pith.science/pith/RORN2USOLMRL6VS5HK7DDF6FD3","download_json":"https://pith.science/pith/RORN2USOLMRL6VS5HK7DDF6FD3.json","view_paper":"https://pith.science/paper/RORN2USO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04549&json=true","fetch_graph":"https://pith.science/api/pith-number/RORN2USOLMRL6VS5HK7DDF6FD3/graph.json","fetch_events":"https://pith.science/api/pith-number/RORN2USOLMRL6VS5HK7DDF6FD3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RORN2USOLMRL6VS5HK7DDF6FD3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RORN2USOLMRL6VS5HK7DDF6FD3/action/storage_attestation","attest_author":"https://pith.science/pith/RORN2USOLMRL6VS5HK7DDF6FD3/action/author_attestation","sign_citation":"https://pith.science/pith/RORN2USOLMRL6VS5HK7DDF6FD3/action/citation_signature","submit_replication":"https://pith.science/pith/RORN2USOLMRL6VS5HK7DDF6FD3/action/replication_record"}},"created_at":"2026-07-05T12:05:25.122657+00:00","updated_at":"2026-07-05T12:05:25.122657+00:00"}