{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TWGNFPZJIZVN2YP33CIJSFMULQ","short_pith_number":"pith:TWGNFPZJ","canonical_record":{"source":{"id":"2511.18242","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-23T01:25:17Z","cross_cats_sorted":[],"title_canon_sha256":"ddfd0dd649c517d51573193deb45819d5ab72728b4eeb4828fbfc7f69a08713c","abstract_canon_sha256":"b5e32004b9bad0cebd772b7c4ca61bc2f6224b1a675c25f56df4ffb5386959cc"},"schema_version":"1.0"},"canonical_sha256":"9d8cd2bf29466add61fbd8909915945c3ff45ef8e7065bbde3ee86793788fc95","source":{"kind":"arxiv","id":"2511.18242","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.18242","created_at":"2026-07-01T01:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2511.18242v3","created_at":"2026-07-01T01:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.18242","created_at":"2026-07-01T01:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"TWGNFPZJIZVN","created_at":"2026-07-01T01:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"TWGNFPZJIZVN2YP3","created_at":"2026-07-01T01:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"TWGNFPZJ","created_at":"2026-07-01T01:17:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TWGNFPZJIZVN2YP33CIJSFMULQ","target":"record","payload":{"canonical_record":{"source":{"id":"2511.18242","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-23T01:25:17Z","cross_cats_sorted":[],"title_canon_sha256":"ddfd0dd649c517d51573193deb45819d5ab72728b4eeb4828fbfc7f69a08713c","abstract_canon_sha256":"b5e32004b9bad0cebd772b7c4ca61bc2f6224b1a675c25f56df4ffb5386959cc"},"schema_version":"1.0"},"canonical_sha256":"9d8cd2bf29466add61fbd8909915945c3ff45ef8e7065bbde3ee86793788fc95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:11.900198Z","signature_b64":"sIingQK1xb0pFCN7Xl/P8ZbblJGN5TnR2r/qQ7KTHo2Ad/qCRHt73RAOQj/OU4A74qKrkh9xbDOmdGiPKaj+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d8cd2bf29466add61fbd8909915945c3ff45ef8e7065bbde3ee86793788fc95","last_reissued_at":"2026-07-01T01:17:11.899677Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:11.899677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.18242","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":"2026-07-01T01:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ykEjM/7mTFehkRNT1W5NEWhU1/4TfdEqW5CQONR5sBQITqLPrXGFhShKra9OJnJuGBiLWN+ORCwTQHeD5rw6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:28:27.416119Z"},"content_sha256":"476337f245caeba20445b9963de093dd005ef0a1b8539c27479f4f27fb1394d1","schema_version":"1.0","event_id":"sha256:476337f245caeba20445b9963de093dd005ef0a1b8539c27479f4f27fb1394d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TWGNFPZJIZVN2YP33CIJSFMULQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pooyan Fazli, Yogesh Kulkarni","submitted_at":"2025-11-23T01:25:17Z","abstract_excerpt":"Egocentric video understanding requires procedural reasoning under partial observability and continuously shifting viewpoints. Current multimodal large language models (MLLMs) struggle with this setting, often generating plausible but visually inconsistent or weakly grounded responses. We introduce $\\textbf{EgoVITA}$, a framework that decomposes egocentric video reasoning into a structured $\\textit{plan-then-verify}$ process. The model first generates an $\\textbf{egocentric plan}$: a causal sequence of anticipated actions from a first-person perspective. This plan is then evaluated by an $\\tex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.18242","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/2511.18242/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":"2026-07-01T01:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BVMYxbSHigIFGIjFA91vk6x4bDEOdTSRwnzWwftCWkdvzFz4IDjJaxykFIAnFKzcwubIUkxAPaNiMGDeCaNCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:28:27.416611Z"},"content_sha256":"a961a02f4ace4fe9c0cb524514afaa2331ca3ca2c37c761fae408e6e1488bc56","schema_version":"1.0","event_id":"sha256:a961a02f4ace4fe9c0cb524514afaa2331ca3ca2c37c761fae408e6e1488bc56"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TWGNFPZJIZVN2YP33CIJSFMULQ/bundle.json","state_url":"https://pith.science/pith/TWGNFPZJIZVN2YP33CIJSFMULQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TWGNFPZJIZVN2YP33CIJSFMULQ/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":"2026-08-04T23:28:27Z","links":{"resolver":"https://pith.science/pith/TWGNFPZJIZVN2YP33CIJSFMULQ","bundle":"https://pith.science/pith/TWGNFPZJIZVN2YP33CIJSFMULQ/bundle.json","state":"https://pith.science/pith/TWGNFPZJIZVN2YP33CIJSFMULQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TWGNFPZJIZVN2YP33CIJSFMULQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TWGNFPZJIZVN2YP33CIJSFMULQ","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":"b5e32004b9bad0cebd772b7c4ca61bc2f6224b1a675c25f56df4ffb5386959cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-23T01:25:17Z","title_canon_sha256":"ddfd0dd649c517d51573193deb45819d5ab72728b4eeb4828fbfc7f69a08713c"},"schema_version":"1.0","source":{"id":"2511.18242","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.18242","created_at":"2026-07-01T01:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2511.18242v3","created_at":"2026-07-01T01:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.18242","created_at":"2026-07-01T01:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"TWGNFPZJIZVN","created_at":"2026-07-01T01:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"TWGNFPZJIZVN2YP3","created_at":"2026-07-01T01:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"TWGNFPZJ","created_at":"2026-07-01T01:17:11Z"}],"graph_snapshots":[{"event_id":"sha256:a961a02f4ace4fe9c0cb524514afaa2331ca3ca2c37c761fae408e6e1488bc56","target":"graph","created_at":"2026-07-01T01:17:11Z","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/2511.18242/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Egocentric video understanding requires procedural reasoning under partial observability and continuously shifting viewpoints. Current multimodal large language models (MLLMs) struggle with this setting, often generating plausible but visually inconsistent or weakly grounded responses. We introduce $\\textbf{EgoVITA}$, a framework that decomposes egocentric video reasoning into a structured $\\textit{plan-then-verify}$ process. The model first generates an $\\textbf{egocentric plan}$: a causal sequence of anticipated actions from a first-person perspective. This plan is then evaluated by an $\\tex","authors_text":"Pooyan Fazli, Yogesh Kulkarni","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-23T01:25:17Z","title":"EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.18242","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":"sha256:476337f245caeba20445b9963de093dd005ef0a1b8539c27479f4f27fb1394d1","target":"record","created_at":"2026-07-01T01:17:11Z","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":"b5e32004b9bad0cebd772b7c4ca61bc2f6224b1a675c25f56df4ffb5386959cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-23T01:25:17Z","title_canon_sha256":"ddfd0dd649c517d51573193deb45819d5ab72728b4eeb4828fbfc7f69a08713c"},"schema_version":"1.0","source":{"id":"2511.18242","kind":"arxiv","version":3}},"canonical_sha256":"9d8cd2bf29466add61fbd8909915945c3ff45ef8e7065bbde3ee86793788fc95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d8cd2bf29466add61fbd8909915945c3ff45ef8e7065bbde3ee86793788fc95","first_computed_at":"2026-07-01T01:17:11.899677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:11.899677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sIingQK1xb0pFCN7Xl/P8ZbblJGN5TnR2r/qQ7KTHo2Ad/qCRHt73RAOQj/OU4A74qKrkh9xbDOmdGiPKaj+Cg==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:11.900198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.18242","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:476337f245caeba20445b9963de093dd005ef0a1b8539c27479f4f27fb1394d1","sha256:a961a02f4ace4fe9c0cb524514afaa2331ca3ca2c37c761fae408e6e1488bc56"],"state_sha256":"645858b7436291f914a485a9d12edd4867ec33a8dee155fb37e79921072450d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z3ufDIxMFYk7qebeDqXzvNRnArzrti/gjw2StRXmcQOR8H9U7rCdS2xMZ4LFgGWyWZA8TNm2YSM0HLcOOK+LDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:28:27.420056Z","bundle_sha256":"fd2c457af2dc95ea6570bf54edb43504cc56c66b9eab3ffa3a315b972f3462ec"}}