{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XTXWWHI3T6NOL4RX2OWCYED6R7","short_pith_number":"pith:XTXWWHI3","canonical_record":{"source":{"id":"2606.25084","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T18:44:59Z","cross_cats_sorted":[],"title_canon_sha256":"9acc77cbb4d64dd79b9bc5a034193529c501e8e400046c33e491908cd031bbf7","abstract_canon_sha256":"0e0332e74555dbaf68e2abfa09284c22bd5570f02754faf7c9a1458f9c4b59a3"},"schema_version":"1.0"},"canonical_sha256":"bcef6b1d1b9f9ae5f237d3ac2c107e8febcbc35e1136268db211a76a1f26b0d8","source":{"kind":"arxiv","id":"2606.25084","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25084","created_at":"2026-06-25T00:18:17Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25084v1","created_at":"2026-06-25T00:18:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25084","created_at":"2026-06-25T00:18:17Z"},{"alias_kind":"pith_short_12","alias_value":"XTXWWHI3T6NO","created_at":"2026-06-25T00:18:17Z"},{"alias_kind":"pith_short_16","alias_value":"XTXWWHI3T6NOL4RX","created_at":"2026-06-25T00:18:17Z"},{"alias_kind":"pith_short_8","alias_value":"XTXWWHI3","created_at":"2026-06-25T00:18:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XTXWWHI3T6NOL4RX2OWCYED6R7","target":"record","payload":{"canonical_record":{"source":{"id":"2606.25084","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T18:44:59Z","cross_cats_sorted":[],"title_canon_sha256":"9acc77cbb4d64dd79b9bc5a034193529c501e8e400046c33e491908cd031bbf7","abstract_canon_sha256":"0e0332e74555dbaf68e2abfa09284c22bd5570f02754faf7c9a1458f9c4b59a3"},"schema_version":"1.0"},"canonical_sha256":"bcef6b1d1b9f9ae5f237d3ac2c107e8febcbc35e1136268db211a76a1f26b0d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:18:17.326153Z","signature_b64":"4arujpWFx/LKf1p+sPUjnGqLtoTloqlfeQfrNvfkMFUcnmWVmNGTJh2lQWFodKrb/YohwkYTbcevjAZHVidvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcef6b1d1b9f9ae5f237d3ac2c107e8febcbc35e1136268db211a76a1f26b0d8","last_reissued_at":"2026-06-25T00:18:17.325791Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:18:17.325791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.25084","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-25T00:18:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"foeblInfbimm9prHqjz8bhImc0f6LTxA2hf8E5TO+lfqr9JPyc+UX44kXyoyqbxvCJNurlQlTNKza0WZrhOWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:12:54.728107Z"},"content_sha256":"698bc9cc11993074774f64648ecfe82fd878c7bcdb67c91fe662b263eafef882","schema_version":"1.0","event_id":"sha256:698bc9cc11993074774f64648ecfe82fd878c7bcdb67c91fe662b263eafef882"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XTXWWHI3T6NOL4RX2OWCYED6R7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are We There Yet? Exploring the Capabilities of MLLMs in Assistive AI Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Avijit Dasgupta, C. V. Jawahar, Shayon Dasgupta","submitted_at":"2026-06-23T18:44:59Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have redefined visual understanding by combining vision encoders with large-scale language models. This unified architecture enables strong performance on tasks like image captioning, visual question answering, and multimodal dialogue, often in zero- and few-shot settings. Their general-purpose capabilities and flexible interfaces make MLLMs a promising foundation for real-world vision-language applications.\n  Assistive AI aims to help users interact with their environments through natural language. These scenarios demand robust visual recognition, cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25084","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/2606.25084/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-25T00:18:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"omp253rvlAj7yPcQ98rC4sgWgf+iGwseiJILuMmxgEEVn/UWU6q1MKE1r9O1UTAE+II5E/qS0XS8U6O75lmfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:12:54.728493Z"},"content_sha256":"c7b0b6afa32218ac9720c300fda5c606fa3eff852bfd0f789cf3b61380f2702f","schema_version":"1.0","event_id":"sha256:c7b0b6afa32218ac9720c300fda5c606fa3eff852bfd0f789cf3b61380f2702f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XTXWWHI3T6NOL4RX2OWCYED6R7/bundle.json","state_url":"https://pith.science/pith/XTXWWHI3T6NOL4RX2OWCYED6R7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XTXWWHI3T6NOL4RX2OWCYED6R7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T04:12:54Z","links":{"resolver":"https://pith.science/pith/XTXWWHI3T6NOL4RX2OWCYED6R7","bundle":"https://pith.science/pith/XTXWWHI3T6NOL4RX2OWCYED6R7/bundle.json","state":"https://pith.science/pith/XTXWWHI3T6NOL4RX2OWCYED6R7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XTXWWHI3T6NOL4RX2OWCYED6R7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XTXWWHI3T6NOL4RX2OWCYED6R7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0e0332e74555dbaf68e2abfa09284c22bd5570f02754faf7c9a1458f9c4b59a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T18:44:59Z","title_canon_sha256":"9acc77cbb4d64dd79b9bc5a034193529c501e8e400046c33e491908cd031bbf7"},"schema_version":"1.0","source":{"id":"2606.25084","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25084","created_at":"2026-06-25T00:18:17Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25084v1","created_at":"2026-06-25T00:18:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25084","created_at":"2026-06-25T00:18:17Z"},{"alias_kind":"pith_short_12","alias_value":"XTXWWHI3T6NO","created_at":"2026-06-25T00:18:17Z"},{"alias_kind":"pith_short_16","alias_value":"XTXWWHI3T6NOL4RX","created_at":"2026-06-25T00:18:17Z"},{"alias_kind":"pith_short_8","alias_value":"XTXWWHI3","created_at":"2026-06-25T00:18:17Z"}],"graph_snapshots":[{"event_id":"sha256:c7b0b6afa32218ac9720c300fda5c606fa3eff852bfd0f789cf3b61380f2702f","target":"graph","created_at":"2026-06-25T00:18:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.25084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have redefined visual understanding by combining vision encoders with large-scale language models. This unified architecture enables strong performance on tasks like image captioning, visual question answering, and multimodal dialogue, often in zero- and few-shot settings. Their general-purpose capabilities and flexible interfaces make MLLMs a promising foundation for real-world vision-language applications.\n  Assistive AI aims to help users interact with their environments through natural language. These scenarios demand robust visual recognition, cont","authors_text":"Avijit Dasgupta, C. V. Jawahar, Shayon Dasgupta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T18:44:59Z","title":"Are We There Yet? Exploring the Capabilities of MLLMs in Assistive AI Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25084","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:698bc9cc11993074774f64648ecfe82fd878c7bcdb67c91fe662b263eafef882","target":"record","created_at":"2026-06-25T00:18:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0e0332e74555dbaf68e2abfa09284c22bd5570f02754faf7c9a1458f9c4b59a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T18:44:59Z","title_canon_sha256":"9acc77cbb4d64dd79b9bc5a034193529c501e8e400046c33e491908cd031bbf7"},"schema_version":"1.0","source":{"id":"2606.25084","kind":"arxiv","version":1}},"canonical_sha256":"bcef6b1d1b9f9ae5f237d3ac2c107e8febcbc35e1136268db211a76a1f26b0d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcef6b1d1b9f9ae5f237d3ac2c107e8febcbc35e1136268db211a76a1f26b0d8","first_computed_at":"2026-06-25T00:18:17.325791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T00:18:17.325791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4arujpWFx/LKf1p+sPUjnGqLtoTloqlfeQfrNvfkMFUcnmWVmNGTJh2lQWFodKrb/YohwkYTbcevjAZHVidvDw==","signature_status":"signed_v1","signed_at":"2026-06-25T00:18:17.326153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25084","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:698bc9cc11993074774f64648ecfe82fd878c7bcdb67c91fe662b263eafef882","sha256:c7b0b6afa32218ac9720c300fda5c606fa3eff852bfd0f789cf3b61380f2702f"],"state_sha256":"5c68f9b468ec926da6d3974707177be347141a08f41cf9b6fcc2b0118e746b05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zbSDOuGXiP7e8ZeaK0oh0nzE+1Cd86tksmoYpIuzwYvwiO28a6/acaWcr5PLPkaH8/j3xUmXukwwrCkRS5QoAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:12:54.730488Z","bundle_sha256":"9f00526051f7c40c34484d59a76e2231f212360f58c6f8261695591ffddef1b9"}}