{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QXV6BBDJ7SOLBABCSKIOXKSCJZ","short_pith_number":"pith:QXV6BBDJ","canonical_record":{"source":{"id":"2504.13621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-18T10:54:52Z","cross_cats_sorted":[],"title_canon_sha256":"caae6a6d56270567c0cc0843d780f435d0e643a5c71022a0a9a39984c6b62dc9","abstract_canon_sha256":"320bbebb0a7f6cd763569d295e0057d6d6db1c87fa23ac91bfc115e8c9603675"},"schema_version":"1.0"},"canonical_sha256":"85ebe08469fc9cb080229290ebaa424e56a91a72611e44a77e2283ffc5909533","source":{"kind":"arxiv","id":"2504.13621","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13621","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13621v1","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13621","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_12","alias_value":"QXV6BBDJ7SOL","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_16","alias_value":"QXV6BBDJ7SOLBABC","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_8","alias_value":"QXV6BBDJ","created_at":"2026-07-05T10:50:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QXV6BBDJ7SOLBABCSKIOXKSCJZ","target":"record","payload":{"canonical_record":{"source":{"id":"2504.13621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-18T10:54:52Z","cross_cats_sorted":[],"title_canon_sha256":"caae6a6d56270567c0cc0843d780f435d0e643a5c71022a0a9a39984c6b62dc9","abstract_canon_sha256":"320bbebb0a7f6cd763569d295e0057d6d6db1c87fa23ac91bfc115e8c9603675"},"schema_version":"1.0"},"canonical_sha256":"85ebe08469fc9cb080229290ebaa424e56a91a72611e44a77e2283ffc5909533","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:59.211166Z","signature_b64":"l6+jpvDK3erpKztcLcNJSekjV5cJ7OrHQsexZfr2Pe2K2bIw9PQi0u/Hy5Mue2NTV5LSF18uX2wOgz+NpkJ0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85ebe08469fc9cb080229290ebaa424e56a91a72611e44a77e2283ffc5909533","last_reissued_at":"2026-07-05T10:50:59.210680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:59.210680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.13621","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":"2026-07-05T10:50:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gusts4pgMLkc8QVJNUL29XpXabqh+yb8rB8g+ELu1jcmhPoE43+Banj1XrXkGBLO5t8JtOMRvVjI69lUOoD1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:11:58.763054Z"},"content_sha256":"0271b5975b207a3258c3792177b52d2728c6d73cada5d3d163b536dd19d301fd","schema_version":"1.0","event_id":"sha256:0271b5975b207a3258c3792177b52d2728c6d73cada5d3d163b536dd19d301fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QXV6BBDJ7SOLBABCSKIOXKSCJZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Intention Grounding for Egocentric Assistants","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Yao, Arjun Akula, Junbin Xiao, Pengzhan Sun, Tze Ho Elden Tse, Yicong Li","submitted_at":"2025-04-18T10:54:52Z","abstract_excerpt":"Visual grounding associates textual descriptions with objects in an image. Conventional methods target third-person image inputs and named object queries. In applications such as AI assistants, the perspective shifts -- inputs are egocentric, and objects may be referred to implicitly through needs and intentions. To bridge this gap, we introduce EgoIntention, the first dataset for egocentric visual intention grounding. EgoIntention challenges multimodal LLMs to 1) understand and ignore unintended contextual objects and 2) reason about uncommon object functionalities. Benchmark results show tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13621","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/2504.13621/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":"2026-07-05T10:50:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KWiC6DO0SNojwBJJ50Lh7qODAyM8TUmpE9XD6+Y4DyCTxp0wDSD7w5NNy2tqaPvyciyrNAs2KGI5I44UK22uCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:11:58.763859Z"},"content_sha256":"1c9faf3262a55a8d2e6b34b5567364aaa49b1fb2e021653389ce72ccc8c0ba9b","schema_version":"1.0","event_id":"sha256:1c9faf3262a55a8d2e6b34b5567364aaa49b1fb2e021653389ce72ccc8c0ba9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXV6BBDJ7SOLBABCSKIOXKSCJZ/bundle.json","state_url":"https://pith.science/pith/QXV6BBDJ7SOLBABCSKIOXKSCJZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXV6BBDJ7SOLBABCSKIOXKSCJZ/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":"2026-08-05T13:11:58Z","links":{"resolver":"https://pith.science/pith/QXV6BBDJ7SOLBABCSKIOXKSCJZ","bundle":"https://pith.science/pith/QXV6BBDJ7SOLBABCSKIOXKSCJZ/bundle.json","state":"https://pith.science/pith/QXV6BBDJ7SOLBABCSKIOXKSCJZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXV6BBDJ7SOLBABCSKIOXKSCJZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QXV6BBDJ7SOLBABCSKIOXKSCJZ","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":"320bbebb0a7f6cd763569d295e0057d6d6db1c87fa23ac91bfc115e8c9603675","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-18T10:54:52Z","title_canon_sha256":"caae6a6d56270567c0cc0843d780f435d0e643a5c71022a0a9a39984c6b62dc9"},"schema_version":"1.0","source":{"id":"2504.13621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13621","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13621v1","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13621","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_12","alias_value":"QXV6BBDJ7SOL","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_16","alias_value":"QXV6BBDJ7SOLBABC","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_8","alias_value":"QXV6BBDJ","created_at":"2026-07-05T10:50:59Z"}],"graph_snapshots":[{"event_id":"sha256:1c9faf3262a55a8d2e6b34b5567364aaa49b1fb2e021653389ce72ccc8c0ba9b","target":"graph","created_at":"2026-07-05T10:50:59Z","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/2504.13621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding associates textual descriptions with objects in an image. Conventional methods target third-person image inputs and named object queries. In applications such as AI assistants, the perspective shifts -- inputs are egocentric, and objects may be referred to implicitly through needs and intentions. To bridge this gap, we introduce EgoIntention, the first dataset for egocentric visual intention grounding. EgoIntention challenges multimodal LLMs to 1) understand and ignore unintended contextual objects and 2) reason about uncommon object functionalities. Benchmark results show tha","authors_text":"Angela Yao, Arjun Akula, Junbin Xiao, Pengzhan Sun, Tze Ho Elden Tse, Yicong Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-18T10:54:52Z","title":"Visual Intention Grounding for Egocentric Assistants"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13621","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":"sha256:0271b5975b207a3258c3792177b52d2728c6d73cada5d3d163b536dd19d301fd","target":"record","created_at":"2026-07-05T10:50:59Z","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":"320bbebb0a7f6cd763569d295e0057d6d6db1c87fa23ac91bfc115e8c9603675","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-18T10:54:52Z","title_canon_sha256":"caae6a6d56270567c0cc0843d780f435d0e643a5c71022a0a9a39984c6b62dc9"},"schema_version":"1.0","source":{"id":"2504.13621","kind":"arxiv","version":1}},"canonical_sha256":"85ebe08469fc9cb080229290ebaa424e56a91a72611e44a77e2283ffc5909533","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85ebe08469fc9cb080229290ebaa424e56a91a72611e44a77e2283ffc5909533","first_computed_at":"2026-07-05T10:50:59.210680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:59.210680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l6+jpvDK3erpKztcLcNJSekjV5cJ7OrHQsexZfr2Pe2K2bIw9PQi0u/Hy5Mue2NTV5LSF18uX2wOgz+NpkJ0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:59.211166Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0271b5975b207a3258c3792177b52d2728c6d73cada5d3d163b536dd19d301fd","sha256:1c9faf3262a55a8d2e6b34b5567364aaa49b1fb2e021653389ce72ccc8c0ba9b"],"state_sha256":"b35e7b478d72266d277cb66b78da8425d78247cbd3003bc6aed6f5f3518fd212"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GymcF8vPbSDqNOOfERrHmwqMKkvge5D+Vm7A67GkzjFuENo0ON5YPYrqJFY1aZWj/wcQHPN72YddAT1JDKipDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:11:58.769095Z","bundle_sha256":"b8de29e8d394418e9772523023bdad310596a25cfca6f0f7abeec2b8c0d8ad3a"}}