{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SDEMYDDY5D4LDVUV6V4VIZWOUB","short_pith_number":"pith:SDEMYDDY","schema_version":"1.0","canonical_sha256":"90c8cc0c78e8f8b1d695f5795466cea04660e6dd5dfb3b8bd68f200a87accadf","source":{"kind":"arxiv","id":"2404.12926","version":2},"attestation_state":"computed","paper":{"title":"MM-PhyRLHF: Reinforcement Learning Framework for Multimodal Physics Question-Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adarsh Raj Shivam, Apoorv Singh, Astha Verma, Avinash Anand, Chhavi Kirtani, Janak Kapuriya, Jatin Kumar, Jay Saraf, Naman Lal, Rajiv Ratn Shah","submitted_at":"2024-04-19T14:52:57Z","abstract_excerpt":"Recent advancements in LLMs have shown their significant potential in tasks like text summarization and generation. Yet, they often encounter difficulty while solving complex physics problems that require arithmetic calculation and a good understanding of concepts. Moreover, many physics problems include images that contain important details required to understand the problem's context. We propose an LMM-based chatbot to answer multimodal physics MCQs. For domain adaptation, we utilize the MM-PhyQA dataset comprising Indian high school-level multimodal physics problems. To improve the LMM's pe"},"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":"2404.12926","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-19T14:52:57Z","cross_cats_sorted":[],"title_canon_sha256":"ee586627844fe822072e5bd959d6c07df75119df79ffd318abcec41aa39c3a2f","abstract_canon_sha256":"21247521c995d1ae31384fddbf4bd33388a2741ea1fbca86b0d055b63cfb4f85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:45.789451Z","signature_b64":"u1AZ0TFR8p6fGHb4F0fszzvnJ9JC27rcTixmfyRh3EVoeC8Dj+fiEF42nWnGkaqmkYt4jJtTjQnNSxK/e6UdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90c8cc0c78e8f8b1d695f5795466cea04660e6dd5dfb3b8bd68f200a87accadf","last_reissued_at":"2026-07-05T09:59:45.788941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:45.788941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-PhyRLHF: Reinforcement Learning Framework for Multimodal Physics Question-Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adarsh Raj Shivam, Apoorv Singh, Astha Verma, Avinash Anand, Chhavi Kirtani, Janak Kapuriya, Jatin Kumar, Jay Saraf, Naman Lal, Rajiv Ratn Shah","submitted_at":"2024-04-19T14:52:57Z","abstract_excerpt":"Recent advancements in LLMs have shown their significant potential in tasks like text summarization and generation. Yet, they often encounter difficulty while solving complex physics problems that require arithmetic calculation and a good understanding of concepts. Moreover, many physics problems include images that contain important details required to understand the problem's context. We propose an LMM-based chatbot to answer multimodal physics MCQs. For domain adaptation, we utilize the MM-PhyQA dataset comprising Indian high school-level multimodal physics problems. To improve the LMM's pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12926","kind":"arxiv","version":2},"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/2404.12926/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":"2404.12926","created_at":"2026-07-05T09:59:45.789017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.12926v2","created_at":"2026-07-05T09:59:45.789017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12926","created_at":"2026-07-05T09:59:45.789017+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDEMYDDY5D4L","created_at":"2026-07-05T09:59:45.789017+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDEMYDDY5D4LDVUV","created_at":"2026-07-05T09:59:45.789017+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDEMYDDY","created_at":"2026-07-05T09:59:45.789017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00821","citing_title":"Improving Physics Reasoning in Large Language Models Using Mixture of Refinement Agents","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDEMYDDY5D4LDVUV6V4VIZWOUB","json":"https://pith.science/pith/SDEMYDDY5D4LDVUV6V4VIZWOUB.json","graph_json":"https://pith.science/api/pith-number/SDEMYDDY5D4LDVUV6V4VIZWOUB/graph.json","events_json":"https://pith.science/api/pith-number/SDEMYDDY5D4LDVUV6V4VIZWOUB/events.json","paper":"https://pith.science/paper/SDEMYDDY"},"agent_actions":{"view_html":"https://pith.science/pith/SDEMYDDY5D4LDVUV6V4VIZWOUB","download_json":"https://pith.science/pith/SDEMYDDY5D4LDVUV6V4VIZWOUB.json","view_paper":"https://pith.science/paper/SDEMYDDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.12926&json=true","fetch_graph":"https://pith.science/api/pith-number/SDEMYDDY5D4LDVUV6V4VIZWOUB/graph.json","fetch_events":"https://pith.science/api/pith-number/SDEMYDDY5D4LDVUV6V4VIZWOUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDEMYDDY5D4LDVUV6V4VIZWOUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDEMYDDY5D4LDVUV6V4VIZWOUB/action/storage_attestation","attest_author":"https://pith.science/pith/SDEMYDDY5D4LDVUV6V4VIZWOUB/action/author_attestation","sign_citation":"https://pith.science/pith/SDEMYDDY5D4LDVUV6V4VIZWOUB/action/citation_signature","submit_replication":"https://pith.science/pith/SDEMYDDY5D4LDVUV6V4VIZWOUB/action/replication_record"}},"created_at":"2026-07-05T09:59:45.789017+00:00","updated_at":"2026-07-05T09:59:45.789017+00:00"}