{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QTO3XW4K5Q7OQINWICR432NPN2","short_pith_number":"pith:QTO3XW4K","schema_version":"1.0","canonical_sha256":"84ddbbdb8aec3ee821b640a3cde9af6e92268cee8d082cfaf42a6381f5e6cc0b","source":{"kind":"arxiv","id":"2407.06025","version":1},"attestation_state":"computed","paper":{"title":"iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aoyu Pang, Chung Shue Chen, Man-On Pun, Maonan Wang, Xi Xiong","submitted_at":"2024-07-08T15:22:49Z","abstract_excerpt":"Urban congestion remains a critical challenge, with traffic signal control (TSC) emerging as a potent solution. TSC is often modeled as a Markov Decision Process problem and then solved using reinforcement learning (RL), which has proven effective. However, the existing RL-based TSC system often overlooks imperfect observations caused by degraded communication, such as packet loss, delays, and noise, as well as rare real-life events not included in the reward function, such as unconsidered emergency vehicles. To address these limitations, we introduce a novel integration framework that combine"},"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":"2407.06025","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-08T15:22:49Z","cross_cats_sorted":[],"title_canon_sha256":"8da636520d77017574b0883f4505609ae8583e7bf343a668576140c8d8c8dd1b","abstract_canon_sha256":"83e62fc492418dfbb297cac1832da4db5fb33315f147b493ec8c67c508d74de6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:22.507725Z","signature_b64":"yI5b3Hz5PdJQ/4gpXdgZMiesBvH5x7y8OU8htfrCLgE0mY2hzQ4Ljc/9an85sv2n9+gwR0GrRROI45cLYiKcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84ddbbdb8aec3ee821b640a3cde9af6e92268cee8d082cfaf42a6381f5e6cc0b","last_reissued_at":"2026-07-05T08:41:22.507206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:22.507206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aoyu Pang, Chung Shue Chen, Man-On Pun, Maonan Wang, Xi Xiong","submitted_at":"2024-07-08T15:22:49Z","abstract_excerpt":"Urban congestion remains a critical challenge, with traffic signal control (TSC) emerging as a potent solution. TSC is often modeled as a Markov Decision Process problem and then solved using reinforcement learning (RL), which has proven effective. However, the existing RL-based TSC system often overlooks imperfect observations caused by degraded communication, such as packet loss, delays, and noise, as well as rare real-life events not included in the reward function, such as unconsidered emergency vehicles. To address these limitations, we introduce a novel integration framework that combine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06025","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/2407.06025/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":"2407.06025","created_at":"2026-07-05T08:41:22.507271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06025v1","created_at":"2026-07-05T08:41:22.507271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06025","created_at":"2026-07-05T08:41:22.507271+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTO3XW4K5Q7O","created_at":"2026-07-05T08:41:22.507271+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTO3XW4K5Q7OQINW","created_at":"2026-07-05T08:41:22.507271+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTO3XW4K","created_at":"2026-07-05T08:41:22.507271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00991","citing_title":"Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Support","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12542","citing_title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","ref_index":239,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29425","citing_title":"ReasonLight: A Multimodal Foundation Model-Enhanced Reinforcement Learning Framework for Zero-Shot Traffic Signal Control","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12542","citing_title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","ref_index":239,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTO3XW4K5Q7OQINWICR432NPN2","json":"https://pith.science/pith/QTO3XW4K5Q7OQINWICR432NPN2.json","graph_json":"https://pith.science/api/pith-number/QTO3XW4K5Q7OQINWICR432NPN2/graph.json","events_json":"https://pith.science/api/pith-number/QTO3XW4K5Q7OQINWICR432NPN2/events.json","paper":"https://pith.science/paper/QTO3XW4K"},"agent_actions":{"view_html":"https://pith.science/pith/QTO3XW4K5Q7OQINWICR432NPN2","download_json":"https://pith.science/pith/QTO3XW4K5Q7OQINWICR432NPN2.json","view_paper":"https://pith.science/paper/QTO3XW4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.06025&json=true","fetch_graph":"https://pith.science/api/pith-number/QTO3XW4K5Q7OQINWICR432NPN2/graph.json","fetch_events":"https://pith.science/api/pith-number/QTO3XW4K5Q7OQINWICR432NPN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTO3XW4K5Q7OQINWICR432NPN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTO3XW4K5Q7OQINWICR432NPN2/action/storage_attestation","attest_author":"https://pith.science/pith/QTO3XW4K5Q7OQINWICR432NPN2/action/author_attestation","sign_citation":"https://pith.science/pith/QTO3XW4K5Q7OQINWICR432NPN2/action/citation_signature","submit_replication":"https://pith.science/pith/QTO3XW4K5Q7OQINWICR432NPN2/action/replication_record"}},"created_at":"2026-07-05T08:41:22.507271+00:00","updated_at":"2026-07-05T08:41:22.507271+00:00"}