{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:C6WNMBQNV363JA7FYUQBZNRGT2","short_pith_number":"pith:C6WNMBQN","canonical_record":{"source":{"id":"2506.07886","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:59:25Z","cross_cats_sorted":[],"title_canon_sha256":"360d3714ad5a36624714fc82c6100ee72b7cf5524f9c4c1439f99a903d3a70f1","abstract_canon_sha256":"eee56ceca267400a0296623bdf6b6dcf8aef26d0c3840850482ccdb91c27b2c9"},"schema_version":"1.0"},"canonical_sha256":"17acd6060daefdb483e5c5201cb6269ea7f20276a94c0102891fcb43aaf754d6","source":{"kind":"arxiv","id":"2506.07886","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07886","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07886v3","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07886","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"C6WNMBQNV363","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_16","alias_value":"C6WNMBQNV363JA7F","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_8","alias_value":"C6WNMBQN","created_at":"2026-07-05T11:39:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:C6WNMBQNV363JA7FYUQBZNRGT2","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07886","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:59:25Z","cross_cats_sorted":[],"title_canon_sha256":"360d3714ad5a36624714fc82c6100ee72b7cf5524f9c4c1439f99a903d3a70f1","abstract_canon_sha256":"eee56ceca267400a0296623bdf6b6dcf8aef26d0c3840850482ccdb91c27b2c9"},"schema_version":"1.0"},"canonical_sha256":"17acd6060daefdb483e5c5201cb6269ea7f20276a94c0102891fcb43aaf754d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:54.926661Z","signature_b64":"EX0OllfkKhl9dtGFy0JnAUs1j974DtSfjiURtXqjEkxxoJDid/svreEv975DJV0q1NUmplawDF4fT0Qo7V8TBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17acd6060daefdb483e5c5201cb6269ea7f20276a94c0102891fcb43aaf754d6","last_reissued_at":"2026-07-05T11:39:54.926245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:54.926245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07886","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8TYFJQLVT4MtO96R0DIovh9K3Zd544VQRBLfuJmC/wMh1bNc6ZceaRwBb+IyloDv7O3jXCA6U2QbFzrBGIoTDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:29:06.819599Z"},"content_sha256":"9eecad4e98c327c82ff42f673410bf9322b5c279b84d23e79ae5d54d1178075e","schema_version":"1.0","event_id":"sha256:9eecad4e98c327c82ff42f673410bf9322b5c279b84d23e79ae5d54d1178075e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:C6WNMBQNV363JA7FYUQBZNRGT2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EgoM2P: Egocentric Multimodal Multitask Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gen Li, Kaifeng Zhao, Marc Pollefeys, Siyu Tang, Yiqian Wu, Yutong Chen","submitted_at":"2025-06-09T15:59:25Z","abstract_excerpt":"Understanding multimodal signals in egocentric vision, such as RGB video, depth, camera poses, and gaze, is essential for applications in augmented reality, robotics, and human-computer interaction, enabling systems to better interpret the camera wearer's actions, intentions, and surrounding environment. However, building large-scale egocentric multimodal and multitask models presents unique challenges. Egocentric data are inherently heterogeneous, with large variations in modality coverage across devices and settings. Generating pseudo-labels for missing modalities, such as gaze or head-mount"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07886","kind":"arxiv","version":3},"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/2506.07886/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":"2026-07-05T11:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nMpIOEgCCrvckmcLTCbwFL21/I9jnzg9uskO1iwxR7dRlOitO/AqHlMgHilZTPFYwdXASzPffJ4JtP1C4gX0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:29:06.820255Z"},"content_sha256":"1763d61833db1540786ca6fe1e17ed2fb3c0dd136493909ae053bbcff181f787","schema_version":"1.0","event_id":"sha256:1763d61833db1540786ca6fe1e17ed2fb3c0dd136493909ae053bbcff181f787"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C6WNMBQNV363JA7FYUQBZNRGT2/bundle.json","state_url":"https://pith.science/pith/C6WNMBQNV363JA7FYUQBZNRGT2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C6WNMBQNV363JA7FYUQBZNRGT2/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":"2026-08-17T05:29:06Z","links":{"resolver":"https://pith.science/pith/C6WNMBQNV363JA7FYUQBZNRGT2","bundle":"https://pith.science/pith/C6WNMBQNV363JA7FYUQBZNRGT2/bundle.json","state":"https://pith.science/pith/C6WNMBQNV363JA7FYUQBZNRGT2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C6WNMBQNV363JA7FYUQBZNRGT2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C6WNMBQNV363JA7FYUQBZNRGT2","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":"eee56ceca267400a0296623bdf6b6dcf8aef26d0c3840850482ccdb91c27b2c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:59:25Z","title_canon_sha256":"360d3714ad5a36624714fc82c6100ee72b7cf5524f9c4c1439f99a903d3a70f1"},"schema_version":"1.0","source":{"id":"2506.07886","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07886","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07886v3","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07886","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"C6WNMBQNV363","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_16","alias_value":"C6WNMBQNV363JA7F","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_8","alias_value":"C6WNMBQN","created_at":"2026-07-05T11:39:54Z"}],"graph_snapshots":[{"event_id":"sha256:1763d61833db1540786ca6fe1e17ed2fb3c0dd136493909ae053bbcff181f787","target":"graph","created_at":"2026-07-05T11:39:54Z","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/2506.07886/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding multimodal signals in egocentric vision, such as RGB video, depth, camera poses, and gaze, is essential for applications in augmented reality, robotics, and human-computer interaction, enabling systems to better interpret the camera wearer's actions, intentions, and surrounding environment. However, building large-scale egocentric multimodal and multitask models presents unique challenges. Egocentric data are inherently heterogeneous, with large variations in modality coverage across devices and settings. Generating pseudo-labels for missing modalities, such as gaze or head-mount","authors_text":"Gen Li, Kaifeng Zhao, Marc Pollefeys, Siyu Tang, Yiqian Wu, Yutong Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:59:25Z","title":"EgoM2P: Egocentric Multimodal Multitask Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07886","kind":"arxiv","version":3},"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":"sha256:9eecad4e98c327c82ff42f673410bf9322b5c279b84d23e79ae5d54d1178075e","target":"record","created_at":"2026-07-05T11:39:54Z","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":"eee56ceca267400a0296623bdf6b6dcf8aef26d0c3840850482ccdb91c27b2c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:59:25Z","title_canon_sha256":"360d3714ad5a36624714fc82c6100ee72b7cf5524f9c4c1439f99a903d3a70f1"},"schema_version":"1.0","source":{"id":"2506.07886","kind":"arxiv","version":3}},"canonical_sha256":"17acd6060daefdb483e5c5201cb6269ea7f20276a94c0102891fcb43aaf754d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17acd6060daefdb483e5c5201cb6269ea7f20276a94c0102891fcb43aaf754d6","first_computed_at":"2026-07-05T11:39:54.926245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:54.926245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EX0OllfkKhl9dtGFy0JnAUs1j974DtSfjiURtXqjEkxxoJDid/svreEv975DJV0q1NUmplawDF4fT0Qo7V8TBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:54.926661Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07886","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9eecad4e98c327c82ff42f673410bf9322b5c279b84d23e79ae5d54d1178075e","sha256:1763d61833db1540786ca6fe1e17ed2fb3c0dd136493909ae053bbcff181f787"],"state_sha256":"c26bf71e5ef81245418b990165d5475a4213f35491d666a83ded1cd1fcf5bb9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RNCjwnzK79ZSX4UOZt8RtKy/oIzdGN03Smlxuv27HYgKlHZv/F+Pajnj6zXQzNh1ZSL42A2qzMe0yTQG1vtvDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T05:29:06.825128Z","bundle_sha256":"ec1d5d1b87c447d54f3d07da3cee2732a7bfc98a7b3690145306108c944bf81b"}}