{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3CTS2KDGA5XGHQWMR3TG6WRXE4","short_pith_number":"pith:3CTS2KDG","canonical_record":{"source":{"id":"2404.09933","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T16:59:00Z","cross_cats_sorted":[],"title_canon_sha256":"e30a48ad463439fbe69d4372754d72491804c5b89407d0d7a4f0e4f3e9d29f4a","abstract_canon_sha256":"e9c8af05361d650336d7cceae3f1b16ac5d20e5bb1d513324282e8c69c15ea8e"},"schema_version":"1.0"},"canonical_sha256":"d8a72d2866076e63c2cc8ee66f5a37273dde073aa43726aa12215bf45fff5816","source":{"kind":"arxiv","id":"2404.09933","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09933","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09933v1","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09933","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"3CTS2KDGA5XG","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_16","alias_value":"3CTS2KDGA5XGHQWM","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_8","alias_value":"3CTS2KDG","created_at":"2026-07-05T08:08:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3CTS2KDGA5XGHQWMR3TG6WRXE4","target":"record","payload":{"canonical_record":{"source":{"id":"2404.09933","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T16:59:00Z","cross_cats_sorted":[],"title_canon_sha256":"e30a48ad463439fbe69d4372754d72491804c5b89407d0d7a4f0e4f3e9d29f4a","abstract_canon_sha256":"e9c8af05361d650336d7cceae3f1b16ac5d20e5bb1d513324282e8c69c15ea8e"},"schema_version":"1.0"},"canonical_sha256":"d8a72d2866076e63c2cc8ee66f5a37273dde073aa43726aa12215bf45fff5816","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:13.327793Z","signature_b64":"XA9HxUyMfuZK7dIUCcSaYrFpoBV7CbLmovOA/9Bbpi8LNeOIcMC3HtU4QLZ0VTw1MpirsinnfsZ8EqePbzkzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8a72d2866076e63c2cc8ee66f5a37273dde073aa43726aa12215bf45fff5816","last_reissued_at":"2026-07-05T08:08:13.327399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:13.327399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.09933","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":"2026-07-05T08:08:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wqi6VAdXiELDSU7+ojChb94Qa9K9o5PGgDpcuO7LaW1AN+XpHzX3vX2tq7ZqLD1H/1pHc6J+qHb9Lb69CDomCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:45:26.650547Z"},"content_sha256":"3d092ecb0f8ac6637074f72e889ad52f2703f258caee05f23a37ce2880ccb27c","schema_version":"1.0","event_id":"sha256:3d092ecb0f8ac6637074f72e889ad52f2703f258caee05f23a37ce2880ccb27c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3CTS2KDGA5XGHQWMR3TG6WRXE4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dima Damen, Michael Wray, Siddhant Bansal","submitted_at":"2024-04-15T16:59:00Z","abstract_excerpt":"Large Vision Language Models (VLMs) are now the de facto state-of-the-art for a number of tasks including visual question answering, recognising objects, and spatial referral. In this work, we propose the HOI-Ref task for egocentric images that aims to understand interactions between hands and objects using VLMs. To enable HOI-Ref, we curate the HOI-QA dataset that consists of 3.9M question-answer pairs for training and evaluating VLMs. HOI-QA includes questions relating to locating hands, objects, and critically their interactions (e.g. referring to the object being manipulated by the hand). "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09933","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/2404.09933/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":"2026-07-05T08:08:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0PXJEb0R7vofAesQqac/vYK0yL50pc6CMCy6Kp9g+AVEq47dB7SXYg1S1ef1EO2kaJiDm23HsV0Sxl7eIntGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:45:26.651082Z"},"content_sha256":"83e180729443f908741dc8ceb304ef4b9252a2299e0c6027ec4779eec7d4ecc6","schema_version":"1.0","event_id":"sha256:83e180729443f908741dc8ceb304ef4b9252a2299e0c6027ec4779eec7d4ecc6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3CTS2KDGA5XGHQWMR3TG6WRXE4/bundle.json","state_url":"https://pith.science/pith/3CTS2KDGA5XGHQWMR3TG6WRXE4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3CTS2KDGA5XGHQWMR3TG6WRXE4/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":"2026-08-08T21:45:26Z","links":{"resolver":"https://pith.science/pith/3CTS2KDGA5XGHQWMR3TG6WRXE4","bundle":"https://pith.science/pith/3CTS2KDGA5XGHQWMR3TG6WRXE4/bundle.json","state":"https://pith.science/pith/3CTS2KDGA5XGHQWMR3TG6WRXE4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3CTS2KDGA5XGHQWMR3TG6WRXE4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3CTS2KDGA5XGHQWMR3TG6WRXE4","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":"e9c8af05361d650336d7cceae3f1b16ac5d20e5bb1d513324282e8c69c15ea8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T16:59:00Z","title_canon_sha256":"e30a48ad463439fbe69d4372754d72491804c5b89407d0d7a4f0e4f3e9d29f4a"},"schema_version":"1.0","source":{"id":"2404.09933","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09933","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09933v1","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09933","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"3CTS2KDGA5XG","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_16","alias_value":"3CTS2KDGA5XGHQWM","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_8","alias_value":"3CTS2KDG","created_at":"2026-07-05T08:08:13Z"}],"graph_snapshots":[{"event_id":"sha256:83e180729443f908741dc8ceb304ef4b9252a2299e0c6027ec4779eec7d4ecc6","target":"graph","created_at":"2026-07-05T08:08:13Z","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/2404.09933/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision Language Models (VLMs) are now the de facto state-of-the-art for a number of tasks including visual question answering, recognising objects, and spatial referral. In this work, we propose the HOI-Ref task for egocentric images that aims to understand interactions between hands and objects using VLMs. To enable HOI-Ref, we curate the HOI-QA dataset that consists of 3.9M question-answer pairs for training and evaluating VLMs. HOI-QA includes questions relating to locating hands, objects, and critically their interactions (e.g. referring to the object being manipulated by the hand). ","authors_text":"Dima Damen, Michael Wray, Siddhant Bansal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T16:59:00Z","title":"HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09933","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":"sha256:3d092ecb0f8ac6637074f72e889ad52f2703f258caee05f23a37ce2880ccb27c","target":"record","created_at":"2026-07-05T08:08:13Z","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":"e9c8af05361d650336d7cceae3f1b16ac5d20e5bb1d513324282e8c69c15ea8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T16:59:00Z","title_canon_sha256":"e30a48ad463439fbe69d4372754d72491804c5b89407d0d7a4f0e4f3e9d29f4a"},"schema_version":"1.0","source":{"id":"2404.09933","kind":"arxiv","version":1}},"canonical_sha256":"d8a72d2866076e63c2cc8ee66f5a37273dde073aa43726aa12215bf45fff5816","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8a72d2866076e63c2cc8ee66f5a37273dde073aa43726aa12215bf45fff5816","first_computed_at":"2026-07-05T08:08:13.327399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:13.327399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XA9HxUyMfuZK7dIUCcSaYrFpoBV7CbLmovOA/9Bbpi8LNeOIcMC3HtU4QLZ0VTw1MpirsinnfsZ8EqePbzkzAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:13.327793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09933","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d092ecb0f8ac6637074f72e889ad52f2703f258caee05f23a37ce2880ccb27c","sha256:83e180729443f908741dc8ceb304ef4b9252a2299e0c6027ec4779eec7d4ecc6"],"state_sha256":"1aa1085bbd30814537e90b0714cb427d57e41f9e90d8656bce29faa261f941c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AmVhkVNEDn7uoPjshjQpMlPwrAmhDrwpAwjMeJdKvLWep853eECCsrcRjGjcx8kx60iejzHqbkClkWpARCquBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:45:26.655630Z","bundle_sha256":"2bc82ade01a718e5a04f1d3557f62d2adba5406f083dd8d5a710151b564f518b"}}