{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SJV46SW2ZVG2PNBWR4ECSERUFM","short_pith_number":"pith:SJV46SW2","schema_version":"1.0","canonical_sha256":"926bcf4adacd4da7b4368f082912342b0d7fa838012b7712a2b97a8b7ce5cb19","source":{"kind":"arxiv","id":"2606.07925","version":1},"attestation_state":"computed","paper":{"title":"ROSUM-MCTS: Monte Carlo Tree Search-Inspired HDL Code Summarization with Structural Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Apoorva Nitsure, Ashutosh Jadhav, Charles Mackin, David Beymer, Ehsan Degan, Luyao Shi, Prashanth Vijayaraghavan, Tyler Baldwin, Vandana Mukherjee","submitted_at":"2026-06-06T01:27:20Z","abstract_excerpt":"Large language models (LLMs) have shown promise in code summarization, yet their effectiveness for Hardware Description Languages (HDLs) like VHDL and Verilog remains underexplored. We propose ROSUM-MCTS, an LLM-guided approach inspired by Monte Carlo Tree Search (MCTS) that refines summaries through structured exploration and reinforcement-driven optimization. Our method integrates both local and global context via a hierarchical candidate expansion mechanism and optimizes summaries using a composite reward function balancing functional correctness (FC), local content adequacy (LCA), and flue"},"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":"2606.07925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T01:27:20Z","cross_cats_sorted":[],"title_canon_sha256":"6ac59cebf66cead09a35e03dca3f720eae05927be1ff6d70df9904b3020f4603","abstract_canon_sha256":"f8b248b7536e50dc9972d88f579c600584ab57348a86769deca939182aeaf3f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:55.573482Z","signature_b64":"QpeJ6NBT2KDrIzJxANmMHqpD7F2JUWiE/GvdQP54IfjGJsZ019R3KxmCVRotD6U9zBeQpo98H/tNpoh8jZw3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"926bcf4adacd4da7b4368f082912342b0d7fa838012b7712a2b97a8b7ce5cb19","last_reissued_at":"2026-06-09T01:04:55.573112Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:55.573112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ROSUM-MCTS: Monte Carlo Tree Search-Inspired HDL Code Summarization with Structural Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Apoorva Nitsure, Ashutosh Jadhav, Charles Mackin, David Beymer, Ehsan Degan, Luyao Shi, Prashanth Vijayaraghavan, Tyler Baldwin, Vandana Mukherjee","submitted_at":"2026-06-06T01:27:20Z","abstract_excerpt":"Large language models (LLMs) have shown promise in code summarization, yet their effectiveness for Hardware Description Languages (HDLs) like VHDL and Verilog remains underexplored. We propose ROSUM-MCTS, an LLM-guided approach inspired by Monte Carlo Tree Search (MCTS) that refines summaries through structured exploration and reinforcement-driven optimization. Our method integrates both local and global context via a hierarchical candidate expansion mechanism and optimizes summaries using a composite reward function balancing functional correctness (FC), local content adequacy (LCA), and flue"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07925","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/2606.07925/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":"2606.07925","created_at":"2026-06-09T01:04:55.573173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07925v1","created_at":"2026-06-09T01:04:55.573173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07925","created_at":"2026-06-09T01:04:55.573173+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJV46SW2ZVG2","created_at":"2026-06-09T01:04:55.573173+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJV46SW2ZVG2PNBW","created_at":"2026-06-09T01:04:55.573173+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJV46SW2","created_at":"2026-06-09T01:04:55.573173+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/SJV46SW2ZVG2PNBWR4ECSERUFM","json":"https://pith.science/pith/SJV46SW2ZVG2PNBWR4ECSERUFM.json","graph_json":"https://pith.science/api/pith-number/SJV46SW2ZVG2PNBWR4ECSERUFM/graph.json","events_json":"https://pith.science/api/pith-number/SJV46SW2ZVG2PNBWR4ECSERUFM/events.json","paper":"https://pith.science/paper/SJV46SW2"},"agent_actions":{"view_html":"https://pith.science/pith/SJV46SW2ZVG2PNBWR4ECSERUFM","download_json":"https://pith.science/pith/SJV46SW2ZVG2PNBWR4ECSERUFM.json","view_paper":"https://pith.science/paper/SJV46SW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07925&json=true","fetch_graph":"https://pith.science/api/pith-number/SJV46SW2ZVG2PNBWR4ECSERUFM/graph.json","fetch_events":"https://pith.science/api/pith-number/SJV46SW2ZVG2PNBWR4ECSERUFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJV46SW2ZVG2PNBWR4ECSERUFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJV46SW2ZVG2PNBWR4ECSERUFM/action/storage_attestation","attest_author":"https://pith.science/pith/SJV46SW2ZVG2PNBWR4ECSERUFM/action/author_attestation","sign_citation":"https://pith.science/pith/SJV46SW2ZVG2PNBWR4ECSERUFM/action/citation_signature","submit_replication":"https://pith.science/pith/SJV46SW2ZVG2PNBWR4ECSERUFM/action/replication_record"}},"created_at":"2026-06-09T01:04:55.573173+00:00","updated_at":"2026-06-09T01:04:55.573173+00:00"}