{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T6CLO4FL74BPYMSDZHMG33UXO2","short_pith_number":"pith:T6CLO4FL","schema_version":"1.0","canonical_sha256":"9f84b770abff02fc3243c9d86dee9776b135988e2c0fcc598f33fffcbe45909e","source":{"kind":"arxiv","id":"2605.19559","version":1},"attestation_state":"computed","paper":{"title":"EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dian Jiao, Tianwei Lin, Wenqiao Zhang, Yang Dai","submitted_at":"2026-05-19T09:02:20Z","abstract_excerpt":"The rapid development of Multimodal Large Language Models (MLLMs) has led to growing interest in egocentric video understanding, specifically the ability for MLLMs to recognize fine-grained hand-object interactions, track object state changes over time, and reason about manipulative processes in dynamic environments from a first-person perspective. However, existing egocentric video benchmarks suffer from \\textbf{limited grounded rationale evaluation}, offering limited support for fine-grained operation-centric reasoning and rarely examining whether model rationales are grounded in explicit sp"},"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":"2605.19559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T09:02:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"32c5e08f4d4cad5fce60d398e55670a9dd0e0bdf257b322d72c89e706fc9c49d","abstract_canon_sha256":"a3341d513d9aae64ad6de8316610e9bfd3abf61d498f80d4e2ae4ba6eea0078c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:51.794506Z","signature_b64":"QNjb0FJ5Mw4Fpvcxoda4/XatOkC0YJzk9YfRkEtykWRG6hI2sqJBwZdUGPiXMdAQY6voF326Uj5yN5b3EkM8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f84b770abff02fc3243c9d86dee9776b135988e2c0fcc598f33fffcbe45909e","last_reissued_at":"2026-05-20T01:05:51.793779Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:51.793779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dian Jiao, Tianwei Lin, Wenqiao Zhang, Yang Dai","submitted_at":"2026-05-19T09:02:20Z","abstract_excerpt":"The rapid development of Multimodal Large Language Models (MLLMs) has led to growing interest in egocentric video understanding, specifically the ability for MLLMs to recognize fine-grained hand-object interactions, track object state changes over time, and reason about manipulative processes in dynamic environments from a first-person perspective. However, existing egocentric video benchmarks suffer from \\textbf{limited grounded rationale evaluation}, offering limited support for fine-grained operation-centric reasoning and rarely examining whether model rationales are grounded in explicit sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19559","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/2605.19559/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":"2605.19559","created_at":"2026-05-20T01:05:51.793909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19559v1","created_at":"2026-05-20T01:05:51.793909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19559","created_at":"2026-05-20T01:05:51.793909+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6CLO4FL74BP","created_at":"2026-05-20T01:05:51.793909+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6CLO4FL74BPYMSD","created_at":"2026-05-20T01:05:51.793909+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6CLO4FL","created_at":"2026-05-20T01:05:51.793909+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/T6CLO4FL74BPYMSDZHMG33UXO2","json":"https://pith.science/pith/T6CLO4FL74BPYMSDZHMG33UXO2.json","graph_json":"https://pith.science/api/pith-number/T6CLO4FL74BPYMSDZHMG33UXO2/graph.json","events_json":"https://pith.science/api/pith-number/T6CLO4FL74BPYMSDZHMG33UXO2/events.json","paper":"https://pith.science/paper/T6CLO4FL"},"agent_actions":{"view_html":"https://pith.science/pith/T6CLO4FL74BPYMSDZHMG33UXO2","download_json":"https://pith.science/pith/T6CLO4FL74BPYMSDZHMG33UXO2.json","view_paper":"https://pith.science/paper/T6CLO4FL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19559&json=true","fetch_graph":"https://pith.science/api/pith-number/T6CLO4FL74BPYMSDZHMG33UXO2/graph.json","fetch_events":"https://pith.science/api/pith-number/T6CLO4FL74BPYMSDZHMG33UXO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6CLO4FL74BPYMSDZHMG33UXO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6CLO4FL74BPYMSDZHMG33UXO2/action/storage_attestation","attest_author":"https://pith.science/pith/T6CLO4FL74BPYMSDZHMG33UXO2/action/author_attestation","sign_citation":"https://pith.science/pith/T6CLO4FL74BPYMSDZHMG33UXO2/action/citation_signature","submit_replication":"https://pith.science/pith/T6CLO4FL74BPYMSDZHMG33UXO2/action/replication_record"}},"created_at":"2026-05-20T01:05:51.793909+00:00","updated_at":"2026-05-20T01:05:51.793909+00:00"}