{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2NHOXSZADZCROBT6CVZXRSBMVM","short_pith_number":"pith:2NHOXSZA","canonical_record":{"source":{"id":"2506.16450","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T16:35:49Z","cross_cats_sorted":[],"title_canon_sha256":"b6d089d2858f31bc0b8e3902f02ad24d8117d26b07bea28d5c2192bcd784b5d2","abstract_canon_sha256":"132c84e2257416bd66e765c7d65d709e6eb6c4126e0369574155272b27a5ea4d"},"schema_version":"1.0"},"canonical_sha256":"d34eebcb201e4517067e157378c82cab26a2f8c4f193f1e3a5d730ec74c711b0","source":{"kind":"arxiv","id":"2506.16450","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16450","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16450v1","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16450","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"pith_short_12","alias_value":"2NHOXSZADZCR","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"pith_short_16","alias_value":"2NHOXSZADZCROBT6","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"pith_short_8","alias_value":"2NHOXSZA","created_at":"2026-07-05T11:24:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2NHOXSZADZCROBT6CVZXRSBMVM","target":"record","payload":{"canonical_record":{"source":{"id":"2506.16450","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T16:35:49Z","cross_cats_sorted":[],"title_canon_sha256":"b6d089d2858f31bc0b8e3902f02ad24d8117d26b07bea28d5c2192bcd784b5d2","abstract_canon_sha256":"132c84e2257416bd66e765c7d65d709e6eb6c4126e0369574155272b27a5ea4d"},"schema_version":"1.0"},"canonical_sha256":"d34eebcb201e4517067e157378c82cab26a2f8c4f193f1e3a5d730ec74c711b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:36.672128Z","signature_b64":"PeFMEIblRxNSUc2s+tRvPshF4ogTAj8Zi28GYwWHrVzsNzkCfMZl7+3jebbsxSXI0iuGkgP4XoFpdsdvpINaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d34eebcb201e4517067e157378c82cab26a2f8c4f193f1e3a5d730ec74c711b0","last_reissued_at":"2026-07-05T11:24:36.671622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:36.671622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.16450","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":"2026-07-05T11:24:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zLYPMkTHG0NCaAixajSoi8Iig1nxruVTqKtLUAorKprfeyPgx1MF0oumgYZ2jl6rzI9LGBkJFcDJ3+aXEszrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:51:42.882643Z"},"content_sha256":"9ed366e42cacb5d472084cec4cc9e21428636049db67490c8b55fd61fb7b4269","schema_version":"1.0","event_id":"sha256:9ed366e42cacb5d472084cec4cc9e21428636049db67490c8b55fd61fb7b4269"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2NHOXSZADZCROBT6CVZXRSBMVM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonino Furnari, Giovanni Maria Farinella, Giuseppe Lando, Rosario Forte","submitted_at":"2025-06-19T16:35:49Z","abstract_excerpt":"We investigate whether off-the-shelf Multimodal Large Language Models (MLLMs) can tackle Online Episodic-Memory Video Question Answering (OEM-VQA) without additional training. Our pipeline converts a streaming egocentric video into a lightweight textual memory, only a few kilobytes per minute, via an MLLM descriptor module, and answers multiple-choice questions by querying this memory with an LLM reasoner module. On the QAEgo4D-Closed benchmark, our best configuration attains 56.0% accuracy with 3.6 kB per minute storage, matching the performance of dedicated state-of-the-art systems while bei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16450","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/2506.16450/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":"2026-07-05T11:24:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ld51IJzGjjTwDrrkuVTgx7JGKTC26A4ywEVYnIkBev+rQZg59+10CXgvMDC5STSbW3TSfBcF6rPsYhBQzwkOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:51:42.883134Z"},"content_sha256":"276abb48336b8f69c20f8da72c4d328d5c8969c79de82cd7ff9549c84f4a0ca1","schema_version":"1.0","event_id":"sha256:276abb48336b8f69c20f8da72c4d328d5c8969c79de82cd7ff9549c84f4a0ca1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2NHOXSZADZCROBT6CVZXRSBMVM/bundle.json","state_url":"https://pith.science/pith/2NHOXSZADZCROBT6CVZXRSBMVM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2NHOXSZADZCROBT6CVZXRSBMVM/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":"2026-08-07T23:51:42Z","links":{"resolver":"https://pith.science/pith/2NHOXSZADZCROBT6CVZXRSBMVM","bundle":"https://pith.science/pith/2NHOXSZADZCROBT6CVZXRSBMVM/bundle.json","state":"https://pith.science/pith/2NHOXSZADZCROBT6CVZXRSBMVM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2NHOXSZADZCROBT6CVZXRSBMVM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2NHOXSZADZCROBT6CVZXRSBMVM","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":"132c84e2257416bd66e765c7d65d709e6eb6c4126e0369574155272b27a5ea4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T16:35:49Z","title_canon_sha256":"b6d089d2858f31bc0b8e3902f02ad24d8117d26b07bea28d5c2192bcd784b5d2"},"schema_version":"1.0","source":{"id":"2506.16450","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16450","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16450v1","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16450","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"pith_short_12","alias_value":"2NHOXSZADZCR","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"pith_short_16","alias_value":"2NHOXSZADZCROBT6","created_at":"2026-07-05T11:24:36Z"},{"alias_kind":"pith_short_8","alias_value":"2NHOXSZA","created_at":"2026-07-05T11:24:36Z"}],"graph_snapshots":[{"event_id":"sha256:276abb48336b8f69c20f8da72c4d328d5c8969c79de82cd7ff9549c84f4a0ca1","target":"graph","created_at":"2026-07-05T11:24:36Z","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/2506.16450/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate whether off-the-shelf Multimodal Large Language Models (MLLMs) can tackle Online Episodic-Memory Video Question Answering (OEM-VQA) without additional training. Our pipeline converts a streaming egocentric video into a lightweight textual memory, only a few kilobytes per minute, via an MLLM descriptor module, and answers multiple-choice questions by querying this memory with an LLM reasoner module. On the QAEgo4D-Closed benchmark, our best configuration attains 56.0% accuracy with 3.6 kB per minute storage, matching the performance of dedicated state-of-the-art systems while bei","authors_text":"Antonino Furnari, Giovanni Maria Farinella, Giuseppe Lando, Rosario Forte","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T16:35:49Z","title":"How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16450","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":"sha256:9ed366e42cacb5d472084cec4cc9e21428636049db67490c8b55fd61fb7b4269","target":"record","created_at":"2026-07-05T11:24:36Z","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":"132c84e2257416bd66e765c7d65d709e6eb6c4126e0369574155272b27a5ea4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-19T16:35:49Z","title_canon_sha256":"b6d089d2858f31bc0b8e3902f02ad24d8117d26b07bea28d5c2192bcd784b5d2"},"schema_version":"1.0","source":{"id":"2506.16450","kind":"arxiv","version":1}},"canonical_sha256":"d34eebcb201e4517067e157378c82cab26a2f8c4f193f1e3a5d730ec74c711b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d34eebcb201e4517067e157378c82cab26a2f8c4f193f1e3a5d730ec74c711b0","first_computed_at":"2026-07-05T11:24:36.671622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:36.671622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PeFMEIblRxNSUc2s+tRvPshF4ogTAj8Zi28GYwWHrVzsNzkCfMZl7+3jebbsxSXI0iuGkgP4XoFpdsdvpINaDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:36.672128Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16450","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ed366e42cacb5d472084cec4cc9e21428636049db67490c8b55fd61fb7b4269","sha256:276abb48336b8f69c20f8da72c4d328d5c8969c79de82cd7ff9549c84f4a0ca1"],"state_sha256":"5674b01ec5ec669ba5332ad1ce19a7145f6f65ed5778c704a8c4144067c74acc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"57N3Vitv+4V/PGFx8MIRB49w+OmxPnZtCKS52uvyPTXCBP9p5erfJgsON3eE3qoFxRdKJRKRvtFZuUEaLGUbAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:51:42.886983Z","bundle_sha256":"bac1adac5c311c3ffffcbc7a598dc348c8afbed356d4b1d32ebde395ce195701"}}