{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OGQWIBWMF4TLRQTVSZNQ5MP7KS","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":"717b348c7baa77d13599f9ee0d5cc73ad9ad3ac227fe06d9e815ce4ca9f739c7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T17:28:00Z","title_canon_sha256":"b06ae509808cf75faac24868d9257d6373e7c0c921f5579cb592a2c44d8e401f"},"schema_version":"1.0","source":{"id":"2506.03097","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03097","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03097v1","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03097","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"OGQWIBWMF4TL","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"OGQWIBWMF4TLRQTV","created_at":"2026-07-05T11:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"OGQWIBWM","created_at":"2026-07-05T11:15:14Z"}],"graph_snapshots":[{"event_id":"sha256:0db5f0b6eccfbbd304332bf128e14d20cbcea69ccb575a8027bf2b1fc838a100","target":"graph","created_at":"2026-07-05T11:15:14Z","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/2506.03097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Emerging embodied AI applications, such as wearable cameras and autonomous agents, have underscored the need for robust reasoning from first person video streams. We introduce EgoVLM, a vision-language model specifically designed to integrate visual comprehension and spatial-temporal reasoning within egocentric video contexts. EgoVLM is fine-tuned via Group Relative Policy Optimization (GRPO), a reinforcement learning method adapted to align model outputs with human-like reasoning steps. Following DeepSeek R1-Zero's approach, we directly tune using RL without any supervised fine-tuning phase o","authors_text":"Aditya Vavre, Ashwin Vinod, Linshen Liu, Shrey Pandit","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T17:28:00Z","title":"EgoVLM: Policy Optimization for Egocentric Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03097","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:f55780568f1c5a26eed94f5d0719cdf5dc3b37be9ff8f3d2588b3383feb99c76","target":"record","created_at":"2026-07-05T11:15:14Z","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":"717b348c7baa77d13599f9ee0d5cc73ad9ad3ac227fe06d9e815ce4ca9f739c7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T17:28:00Z","title_canon_sha256":"b06ae509808cf75faac24868d9257d6373e7c0c921f5579cb592a2c44d8e401f"},"schema_version":"1.0","source":{"id":"2506.03097","kind":"arxiv","version":1}},"canonical_sha256":"71a16406cc2f26b8c275965b0eb1ff54999aec9f1b72c9fcc91e48f665e0bd10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71a16406cc2f26b8c275965b0eb1ff54999aec9f1b72c9fcc91e48f665e0bd10","first_computed_at":"2026-07-05T11:15:14.827590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:14.827590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CfcL+1hgd/XLtKvAytl3uvxejAaaIhU1Ja7hUG1dWI1XPPHy+sUFF0AQjADidALum56WFNZTR9p5MUnxe5TeAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:14.828094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03097","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f55780568f1c5a26eed94f5d0719cdf5dc3b37be9ff8f3d2588b3383feb99c76","sha256:0db5f0b6eccfbbd304332bf128e14d20cbcea69ccb575a8027bf2b1fc838a100"],"state_sha256":"b95a4821b0e4e04967bbc9e274c5312639404107e5880748e1733e1f1e1f055a"}