{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IBECZ25D7PSMLEMGWKCRAS42XN","short_pith_number":"pith:IBECZ25D","schema_version":"1.0","canonical_sha256":"40482ceba3fbe4c59186b285104b9abb6bf369b83c48c3ca2f16dac60392e565","source":{"kind":"arxiv","id":"2509.08270","version":1},"attestation_state":"computed","paper":{"title":"Interpretable Physics Reasoning and Performance Taxonomy in Vision-Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akshat Bhalani, Deepali Patil, Dev Mittal, Hadi Gala, Kavish Shah, Komal Kasat, Monali Deshmukh, Nikita Raichada, Pranav Pawar","submitted_at":"2025-09-10T04:15:01Z","abstract_excerpt":"As Vision-Language Models (VLMs) grow in sophistication, their ability to perform reasoning is coming under increasing supervision. While they excel at many tasks, their grasp of fundamental scientific principles, such as physics, remains an underexplored frontier. To reflect the advancements in these capabilities, we introduce a novel and accessible framework designed to rigorously evaluate VLMs on their understanding of 2D physics. Our framework features a pragmatic scenario generator that creates a diverse testbed of over 400 problems across four core domains: Projectile Motion, Collision D"},"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":"2509.08270","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T04:15:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f0892cd351148d8dcc3dc4e9c791d87812610d2d47d387992aab21fa12eae5c1","abstract_canon_sha256":"63117df9e75b5ff08c8be42edc5cfe54113d6287cc1b18880e53dfa32c556230"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:26.658271Z","signature_b64":"UpQAt/nbzHmqojvHQSZ3+TtLnt8MnwpW06ortUA8+RSY/fSMj+YLclXUpwi9YC7ctwAufGbEUF+R/8RTQxrKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40482ceba3fbe4c59186b285104b9abb6bf369b83c48c3ca2f16dac60392e565","last_reissued_at":"2026-07-05T12:08:26.657649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:26.657649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Physics Reasoning and Performance Taxonomy in Vision-Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akshat Bhalani, Deepali Patil, Dev Mittal, Hadi Gala, Kavish Shah, Komal Kasat, Monali Deshmukh, Nikita Raichada, Pranav Pawar","submitted_at":"2025-09-10T04:15:01Z","abstract_excerpt":"As Vision-Language Models (VLMs) grow in sophistication, their ability to perform reasoning is coming under increasing supervision. While they excel at many tasks, their grasp of fundamental scientific principles, such as physics, remains an underexplored frontier. To reflect the advancements in these capabilities, we introduce a novel and accessible framework designed to rigorously evaluate VLMs on their understanding of 2D physics. Our framework features a pragmatic scenario generator that creates a diverse testbed of over 400 problems across four core domains: Projectile Motion, Collision D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08270","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/2509.08270/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":"2509.08270","created_at":"2026-07-05T12:08:26.657722+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08270v1","created_at":"2026-07-05T12:08:26.657722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08270","created_at":"2026-07-05T12:08:26.657722+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBECZ25D7PSM","created_at":"2026-07-05T12:08:26.657722+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBECZ25D7PSMLEMG","created_at":"2026-07-05T12:08:26.657722+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBECZ25D","created_at":"2026-07-05T12:08:26.657722+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/IBECZ25D7PSMLEMGWKCRAS42XN","json":"https://pith.science/pith/IBECZ25D7PSMLEMGWKCRAS42XN.json","graph_json":"https://pith.science/api/pith-number/IBECZ25D7PSMLEMGWKCRAS42XN/graph.json","events_json":"https://pith.science/api/pith-number/IBECZ25D7PSMLEMGWKCRAS42XN/events.json","paper":"https://pith.science/paper/IBECZ25D"},"agent_actions":{"view_html":"https://pith.science/pith/IBECZ25D7PSMLEMGWKCRAS42XN","download_json":"https://pith.science/pith/IBECZ25D7PSMLEMGWKCRAS42XN.json","view_paper":"https://pith.science/paper/IBECZ25D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08270&json=true","fetch_graph":"https://pith.science/api/pith-number/IBECZ25D7PSMLEMGWKCRAS42XN/graph.json","fetch_events":"https://pith.science/api/pith-number/IBECZ25D7PSMLEMGWKCRAS42XN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBECZ25D7PSMLEMGWKCRAS42XN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBECZ25D7PSMLEMGWKCRAS42XN/action/storage_attestation","attest_author":"https://pith.science/pith/IBECZ25D7PSMLEMGWKCRAS42XN/action/author_attestation","sign_citation":"https://pith.science/pith/IBECZ25D7PSMLEMGWKCRAS42XN/action/citation_signature","submit_replication":"https://pith.science/pith/IBECZ25D7PSMLEMGWKCRAS42XN/action/replication_record"}},"created_at":"2026-07-05T12:08:26.657722+00:00","updated_at":"2026-07-05T12:08:26.657722+00:00"}