{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5TY7QNU5G2WCCMC5BOM4EAQQHN","short_pith_number":"pith:5TY7QNU5","canonical_record":{"source":{"id":"2504.07867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T15:43:10Z","cross_cats_sorted":[],"title_canon_sha256":"423628647b8250e755f2a5d57a3735127334025070c388b54349ab381f4b72e9","abstract_canon_sha256":"424f63582e810cb3046ca1d58f59bb0b4d68011ee86519a761059f8e72f3499d"},"schema_version":"1.0"},"canonical_sha256":"ecf1f8369d36ac21305d0b99c202103b7d6a232de4d192558427712f4555f8d5","source":{"kind":"arxiv","id":"2504.07867","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07867","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07867v1","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07867","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_12","alias_value":"5TY7QNU5G2WC","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_16","alias_value":"5TY7QNU5G2WCCMC5","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_8","alias_value":"5TY7QNU5","created_at":"2026-07-05T10:47:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5TY7QNU5G2WCCMC5BOM4EAQQHN","target":"record","payload":{"canonical_record":{"source":{"id":"2504.07867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T15:43:10Z","cross_cats_sorted":[],"title_canon_sha256":"423628647b8250e755f2a5d57a3735127334025070c388b54349ab381f4b72e9","abstract_canon_sha256":"424f63582e810cb3046ca1d58f59bb0b4d68011ee86519a761059f8e72f3499d"},"schema_version":"1.0"},"canonical_sha256":"ecf1f8369d36ac21305d0b99c202103b7d6a232de4d192558427712f4555f8d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:15.961237Z","signature_b64":"OCqD4dhvV6h9d/opK/Hcof//LBCIQm0X6693u7eG7oSaPt0Vi/M6qR7mR36w9AA4bUGTQVpPAyI7A71B7KQjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecf1f8369d36ac21305d0b99c202103b7d6a232de4d192558427712f4555f8d5","last_reissued_at":"2026-07-05T10:47:15.960807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:15.960807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.07867","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":"2026-07-05T10:47:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E4IPpRcUnApQpOWXWWC64B9rimfL1yl+CpWNFWv4g/yCDOCsgSoZMp3UwTAxwAONAQDObBhym5svGFE0PGJ/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:25:47.726653Z"},"content_sha256":"8b49822c3267ad874876c547d52aa2afb197a7899d300e73efabfd768132dad3","schema_version":"1.0","event_id":"sha256:8b49822c3267ad874876c547d52aa2afb197a7899d300e73efabfd768132dad3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5TY7QNU5G2WCCMC5BOM4EAQQHN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SAMJAM: Zero-Shot Video Scene Graph Generation for Egocentric Kitchen Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Wong, Emily Yu, Fernando Jose Pena Cantu, Joshua Li, Yuchen Cui, Yuhao Chen","submitted_at":"2025-04-10T15:43:10Z","abstract_excerpt":"Video Scene Graph Generation (VidSGG) is an important topic in understanding dynamic kitchen environments. Current models for VidSGG require extensive training to produce scene graphs. Recently, Vision Language Models (VLM) and Vision Foundation Models (VFM) have demonstrated impressive zero-shot capabilities in a variety of tasks. However, VLMs like Gemini struggle with the dynamics for VidSGG, failing to maintain stable object identities across frames. To overcome this limitation, we propose SAMJAM, a zero-shot pipeline that combines SAM2's temporal tracking with Gemini's semantic understand"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07867","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/2504.07867/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":"2026-07-05T10:47:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hdp3ozi+zwCCemfXFRQrc83WysHIFrmydlih82Ftg6k3a9M282XESzVZMGIHIJBbt0phViieQjQoJcKEhUDkAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:25:47.727214Z"},"content_sha256":"f4264cb95c6b70de78e393954b650ab4e21badaa536cb01846a610dcd63f2869","schema_version":"1.0","event_id":"sha256:f4264cb95c6b70de78e393954b650ab4e21badaa536cb01846a610dcd63f2869"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5TY7QNU5G2WCCMC5BOM4EAQQHN/bundle.json","state_url":"https://pith.science/pith/5TY7QNU5G2WCCMC5BOM4EAQQHN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5TY7QNU5G2WCCMC5BOM4EAQQHN/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":"2026-08-08T11:25:47Z","links":{"resolver":"https://pith.science/pith/5TY7QNU5G2WCCMC5BOM4EAQQHN","bundle":"https://pith.science/pith/5TY7QNU5G2WCCMC5BOM4EAQQHN/bundle.json","state":"https://pith.science/pith/5TY7QNU5G2WCCMC5BOM4EAQQHN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5TY7QNU5G2WCCMC5BOM4EAQQHN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5TY7QNU5G2WCCMC5BOM4EAQQHN","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":"424f63582e810cb3046ca1d58f59bb0b4d68011ee86519a761059f8e72f3499d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T15:43:10Z","title_canon_sha256":"423628647b8250e755f2a5d57a3735127334025070c388b54349ab381f4b72e9"},"schema_version":"1.0","source":{"id":"2504.07867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07867","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07867v1","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07867","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_12","alias_value":"5TY7QNU5G2WC","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_16","alias_value":"5TY7QNU5G2WCCMC5","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_8","alias_value":"5TY7QNU5","created_at":"2026-07-05T10:47:15Z"}],"graph_snapshots":[{"event_id":"sha256:f4264cb95c6b70de78e393954b650ab4e21badaa536cb01846a610dcd63f2869","target":"graph","created_at":"2026-07-05T10:47:15Z","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/2504.07867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Scene Graph Generation (VidSGG) is an important topic in understanding dynamic kitchen environments. Current models for VidSGG require extensive training to produce scene graphs. Recently, Vision Language Models (VLM) and Vision Foundation Models (VFM) have demonstrated impressive zero-shot capabilities in a variety of tasks. However, VLMs like Gemini struggle with the dynamics for VidSGG, failing to maintain stable object identities across frames. To overcome this limitation, we propose SAMJAM, a zero-shot pipeline that combines SAM2's temporal tracking with Gemini's semantic understand","authors_text":"Alexander Wong, Emily Yu, Fernando Jose Pena Cantu, Joshua Li, Yuchen Cui, Yuhao Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T15:43:10Z","title":"SAMJAM: Zero-Shot Video Scene Graph Generation for Egocentric Kitchen Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07867","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":"sha256:8b49822c3267ad874876c547d52aa2afb197a7899d300e73efabfd768132dad3","target":"record","created_at":"2026-07-05T10:47:15Z","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":"424f63582e810cb3046ca1d58f59bb0b4d68011ee86519a761059f8e72f3499d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T15:43:10Z","title_canon_sha256":"423628647b8250e755f2a5d57a3735127334025070c388b54349ab381f4b72e9"},"schema_version":"1.0","source":{"id":"2504.07867","kind":"arxiv","version":1}},"canonical_sha256":"ecf1f8369d36ac21305d0b99c202103b7d6a232de4d192558427712f4555f8d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecf1f8369d36ac21305d0b99c202103b7d6a232de4d192558427712f4555f8d5","first_computed_at":"2026-07-05T10:47:15.960807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:15.960807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OCqD4dhvV6h9d/opK/Hcof//LBCIQm0X6693u7eG7oSaPt0Vi/M6qR7mR36w9AA4bUGTQVpPAyI7A71B7KQjBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:15.961237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b49822c3267ad874876c547d52aa2afb197a7899d300e73efabfd768132dad3","sha256:f4264cb95c6b70de78e393954b650ab4e21badaa536cb01846a610dcd63f2869"],"state_sha256":"4626b56653427b34339638ca2f0f65ea179482a06928316149448c8c809878cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x6qS2A6jAHkuqYBoPWhyXsW/1ZR2DHM3QiW4rMnwAg6fm4tr+vX8Z+auam5oUOZJ+FM9pdfH1OoNGtKUqts1Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:25:47.732425Z","bundle_sha256":"30b6369137cc7e128e9b0d0d475603f122c280b5893e0389411495ac822aaeb1"}}