{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PQ3BWVKXI4JO7ZY4HLAJZWC7UW","short_pith_number":"pith:PQ3BWVKX","canonical_record":{"source":{"id":"2607.14497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T02:22:26Z","cross_cats_sorted":[],"title_canon_sha256":"e5fc529d0867899907a3b295bc6ca6256329148296b25ac84072ba19242ab176","abstract_canon_sha256":"95e6550278d647f3d6c26876792a06d6d7b7e2eea45c9557d887bc73ae220111"},"schema_version":"1.0"},"canonical_sha256":"7c361b55574712efe71c3ac09cd85fa5a1a2e52e1da088d01495e086c1d39f1c","source":{"kind":"arxiv","id":"2607.14497","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14497","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14497v1","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14497","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"pith_short_12","alias_value":"PQ3BWVKXI4JO","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"pith_short_16","alias_value":"PQ3BWVKXI4JO7ZY4","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"pith_short_8","alias_value":"PQ3BWVKX","created_at":"2026-07-17T00:21:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PQ3BWVKXI4JO7ZY4HLAJZWC7UW","target":"record","payload":{"canonical_record":{"source":{"id":"2607.14497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T02:22:26Z","cross_cats_sorted":[],"title_canon_sha256":"e5fc529d0867899907a3b295bc6ca6256329148296b25ac84072ba19242ab176","abstract_canon_sha256":"95e6550278d647f3d6c26876792a06d6d7b7e2eea45c9557d887bc73ae220111"},"schema_version":"1.0"},"canonical_sha256":"7c361b55574712efe71c3ac09cd85fa5a1a2e52e1da088d01495e086c1d39f1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:21:15.547520Z","signature_b64":"3ehoMJ1j7qhRw3C5vZbgy6JlFR8gAuRlPUxvjfZXJaP3lAaG7gV+sewBkgs6w+xoHRURQTIo8Lp66R5vnyBIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c361b55574712efe71c3ac09cd85fa5a1a2e52e1da088d01495e086c1d39f1c","last_reissued_at":"2026-07-17T00:21:15.546651Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:21:15.546651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.14497","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":"2026-07-17T00:21:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B5ozQw5DyLkVhityJnZIPVAiJ22Yb1UDYk8zyQR1B+o/ImYNZKzWDGDfjdChypusMTkEt6YSwKhb95I2Mh7iAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:20:46.265083Z"},"content_sha256":"c6257f2a25adb0526b28daa726af18a832edd212f339707374ff9b41ec1d95ad","schema_version":"1.0","event_id":"sha256:c6257f2a25adb0526b28daa726af18a832edd212f339707374ff9b41ec1d95ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PQ3BWVKXI4JO7ZY4HLAJZWC7UW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi Kit Wong, Huiyu Zhou, Lutao Jiang, Xuming Hu, Xu Zheng, Ye Pan, Yuanhuiyi Lyu, Zidong Cao, Zixin Zhang","submitted_at":"2026-07-16T02:22:26Z","abstract_excerpt":"Egocentric Visual Question Answering (VQA) has attracted widespread attention as an important task for enabling Multimodal Large Language Models (MLLMs) to interact with the real world. However, existing MLLMs struggle to perform effective spatial reasoning in complex egocentric scenes due to their limited spatial perception capabilities. To this end, we introduce Ego Scene Augmentation (ESA), an egocentric spatial perception framework, which actively enhances the spatial perception capabilities from the egocentric perspective, powered by the proposed Ego-element Graph. Our core insight is lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14497","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/2607.14497/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":"2026-07-17T00:21:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r+W6YxoMKpCQQyeEDnyP4bJ0P6JsLbXtRm4vSeCBMaJ3Mxd9F4rXGIwUSZxUkuBK/2eaPJjpPczKgL3Yp9qECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:20:46.265596Z"},"content_sha256":"48231b4cf4cc8990c78b596b7729f20c597c9bb75ec4e5bc546cab78da53a035","schema_version":"1.0","event_id":"sha256:48231b4cf4cc8990c78b596b7729f20c597c9bb75ec4e5bc546cab78da53a035"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQ3BWVKXI4JO7ZY4HLAJZWC7UW/bundle.json","state_url":"https://pith.science/pith/PQ3BWVKXI4JO7ZY4HLAJZWC7UW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQ3BWVKXI4JO7ZY4HLAJZWC7UW/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":"2026-08-21T15:20:46Z","links":{"resolver":"https://pith.science/pith/PQ3BWVKXI4JO7ZY4HLAJZWC7UW","bundle":"https://pith.science/pith/PQ3BWVKXI4JO7ZY4HLAJZWC7UW/bundle.json","state":"https://pith.science/pith/PQ3BWVKXI4JO7ZY4HLAJZWC7UW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQ3BWVKXI4JO7ZY4HLAJZWC7UW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PQ3BWVKXI4JO7ZY4HLAJZWC7UW","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":"95e6550278d647f3d6c26876792a06d6d7b7e2eea45c9557d887bc73ae220111","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T02:22:26Z","title_canon_sha256":"e5fc529d0867899907a3b295bc6ca6256329148296b25ac84072ba19242ab176"},"schema_version":"1.0","source":{"id":"2607.14497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14497","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14497v1","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14497","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"pith_short_12","alias_value":"PQ3BWVKXI4JO","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"pith_short_16","alias_value":"PQ3BWVKXI4JO7ZY4","created_at":"2026-07-17T00:21:15Z"},{"alias_kind":"pith_short_8","alias_value":"PQ3BWVKX","created_at":"2026-07-17T00:21:15Z"}],"graph_snapshots":[{"event_id":"sha256:48231b4cf4cc8990c78b596b7729f20c597c9bb75ec4e5bc546cab78da53a035","target":"graph","created_at":"2026-07-17T00:21:15Z","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/2607.14497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Egocentric Visual Question Answering (VQA) has attracted widespread attention as an important task for enabling Multimodal Large Language Models (MLLMs) to interact with the real world. However, existing MLLMs struggle to perform effective spatial reasoning in complex egocentric scenes due to their limited spatial perception capabilities. To this end, we introduce Ego Scene Augmentation (ESA), an egocentric spatial perception framework, which actively enhances the spatial perception capabilities from the egocentric perspective, powered by the proposed Ego-element Graph. Our core insight is lev","authors_text":"Chi Kit Wong, Huiyu Zhou, Lutao Jiang, Xuming Hu, Xu Zheng, Ye Pan, Yuanhuiyi Lyu, Zidong Cao, Zixin Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T02:22:26Z","title":"Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14497","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:c6257f2a25adb0526b28daa726af18a832edd212f339707374ff9b41ec1d95ad","target":"record","created_at":"2026-07-17T00:21:15Z","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":"95e6550278d647f3d6c26876792a06d6d7b7e2eea45c9557d887bc73ae220111","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T02:22:26Z","title_canon_sha256":"e5fc529d0867899907a3b295bc6ca6256329148296b25ac84072ba19242ab176"},"schema_version":"1.0","source":{"id":"2607.14497","kind":"arxiv","version":1}},"canonical_sha256":"7c361b55574712efe71c3ac09cd85fa5a1a2e52e1da088d01495e086c1d39f1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c361b55574712efe71c3ac09cd85fa5a1a2e52e1da088d01495e086c1d39f1c","first_computed_at":"2026-07-17T00:21:15.546651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T00:21:15.546651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ehoMJ1j7qhRw3C5vZbgy6JlFR8gAuRlPUxvjfZXJaP3lAaG7gV+sewBkgs6w+xoHRURQTIo8Lp66R5vnyBIAg==","signature_status":"signed_v1","signed_at":"2026-07-17T00:21:15.547520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6257f2a25adb0526b28daa726af18a832edd212f339707374ff9b41ec1d95ad","sha256:48231b4cf4cc8990c78b596b7729f20c597c9bb75ec4e5bc546cab78da53a035"],"state_sha256":"64ecc0c18f0def24803b3cdb3cfd91745950ecbcd224b3d8b0d27ab0b3df585b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qr2ARuCac2W9cgxfJpDQuMb+6H1Y+1y5YsHaTSmuwjiT2aO5V6qFkr823Jtvv2KUGFjpRtLmcyA5wJZ2QfXaDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T15:20:46.270421Z","bundle_sha256":"293beaac345099f1c2c868db511c2dcb688c51240ad0e64aa6b090fd415edfd6"}}