{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CR2EK73A2HNXS73YD7RPK2HYXZ","short_pith_number":"pith:CR2EK73A","canonical_record":{"source":{"id":"2410.23287","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T17:59:26Z","cross_cats_sorted":[],"title_canon_sha256":"7ae6059ece811c5ab7e666340b5de7a6aba6c387076f06728ac54fc4064afb64","abstract_canon_sha256":"850d55d1554594e6ab0ffad315ea6a6a77c13627fa6a523399034a851000a253"},"schema_version":"1.0"},"canonical_sha256":"1474457f60d1db797f781fe2f568f8be779bb3f9ef4838c845c2f9a93adde7d2","source":{"kind":"arxiv","id":"2410.23287","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23287","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23287v2","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23287","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_12","alias_value":"CR2EK73A2HNX","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_16","alias_value":"CR2EK73A2HNXS73Y","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_8","alias_value":"CR2EK73A","created_at":"2026-07-05T11:49:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CR2EK73A2HNXS73YD7RPK2HYXZ","target":"record","payload":{"canonical_record":{"source":{"id":"2410.23287","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T17:59:26Z","cross_cats_sorted":[],"title_canon_sha256":"7ae6059ece811c5ab7e666340b5de7a6aba6c387076f06728ac54fc4064afb64","abstract_canon_sha256":"850d55d1554594e6ab0ffad315ea6a6a77c13627fa6a523399034a851000a253"},"schema_version":"1.0"},"canonical_sha256":"1474457f60d1db797f781fe2f568f8be779bb3f9ef4838c845c2f9a93adde7d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:47.825824Z","signature_b64":"8V2KoOE+KJyCUrqP6CiCcN5VY7+zqQ4XIjPfgar5DJ+NjD8yfXZ0URolan1iDy8cEpR4vncq5ppbEhlwECK4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1474457f60d1db797f781fe2f568f8be779bb3f9ef4838c845c2f9a93adde7d2","last_reissued_at":"2026-07-05T11:49:47.825375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:47.825375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.23287","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VWw0ckBGCW9UUUmEcNLLMtxbuce8LccW7fCFTguQg4BE5SEF9byVB2Pz3sCpB22Wo5ytToDiOsh9NAliYccVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:27:29.759047Z"},"content_sha256":"c64e23ce2573c93a716468a820a51ba7a07a425230c0ca24081c4c4556ef3d41","schema_version":"1.0","event_id":"sha256:c64e23ce2573c93a716468a820a51ba7a07a425230c0ca24081c4c4556ef3d41"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CR2EK73A2HNXS73YD7RPK2HYXZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReferEverything: Towards Segmenting Everything We Can Speak of in Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anurag Bagchi, Martial Hebert, Pavel Tokmakov, Yu-Xiong Wang, Zhipeng Bao","submitted_at":"2024-10-30T17:59:26Z","abstract_excerpt":"We present REM, a framework for segmenting a wide range of concepts in video that can be described through natural language. Our method leverages the universal visual-language mapping learned by video diffusion models on Internet-scale data by fine-tuning them on small-scale Referring Object Segmentation datasets. Our key insight is to preserve the entirety of the generative model's architecture by shifting its objective from predicting noise to predicting mask latents. The resulting model can accurately segment rare and unseen objects, despite only being trained on a limited set of categories"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23287","kind":"arxiv","version":2},"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/2410.23287/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":"2026-07-05T11:49:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zL48cLwoFbpXghMJQAeZ3cIsCFypomjXHd7wVcrhOtWjD9d1h87Vb8RYKm08554psPaS94mqThqhz///PnieCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:27:29.759602Z"},"content_sha256":"4c9abbabbe233a9823cd3e32ccf7e1ce2d1bb9de4d2e28e072e4e6407e634923","schema_version":"1.0","event_id":"sha256:4c9abbabbe233a9823cd3e32ccf7e1ce2d1bb9de4d2e28e072e4e6407e634923"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CR2EK73A2HNXS73YD7RPK2HYXZ/bundle.json","state_url":"https://pith.science/pith/CR2EK73A2HNXS73YD7RPK2HYXZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CR2EK73A2HNXS73YD7RPK2HYXZ/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":"2026-08-10T18:27:29Z","links":{"resolver":"https://pith.science/pith/CR2EK73A2HNXS73YD7RPK2HYXZ","bundle":"https://pith.science/pith/CR2EK73A2HNXS73YD7RPK2HYXZ/bundle.json","state":"https://pith.science/pith/CR2EK73A2HNXS73YD7RPK2HYXZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CR2EK73A2HNXS73YD7RPK2HYXZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CR2EK73A2HNXS73YD7RPK2HYXZ","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":"850d55d1554594e6ab0ffad315ea6a6a77c13627fa6a523399034a851000a253","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T17:59:26Z","title_canon_sha256":"7ae6059ece811c5ab7e666340b5de7a6aba6c387076f06728ac54fc4064afb64"},"schema_version":"1.0","source":{"id":"2410.23287","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23287","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23287v2","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23287","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_12","alias_value":"CR2EK73A2HNX","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_16","alias_value":"CR2EK73A2HNXS73Y","created_at":"2026-07-05T11:49:47Z"},{"alias_kind":"pith_short_8","alias_value":"CR2EK73A","created_at":"2026-07-05T11:49:47Z"}],"graph_snapshots":[{"event_id":"sha256:4c9abbabbe233a9823cd3e32ccf7e1ce2d1bb9de4d2e28e072e4e6407e634923","target":"graph","created_at":"2026-07-05T11:49:47Z","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/2410.23287/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present REM, a framework for segmenting a wide range of concepts in video that can be described through natural language. Our method leverages the universal visual-language mapping learned by video diffusion models on Internet-scale data by fine-tuning them on small-scale Referring Object Segmentation datasets. Our key insight is to preserve the entirety of the generative model's architecture by shifting its objective from predicting noise to predicting mask latents. The resulting model can accurately segment rare and unseen objects, despite only being trained on a limited set of categories","authors_text":"Anurag Bagchi, Martial Hebert, Pavel Tokmakov, Yu-Xiong Wang, Zhipeng Bao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T17:59:26Z","title":"ReferEverything: Towards Segmenting Everything We Can Speak of in Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23287","kind":"arxiv","version":2},"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:c64e23ce2573c93a716468a820a51ba7a07a425230c0ca24081c4c4556ef3d41","target":"record","created_at":"2026-07-05T11:49:47Z","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":"850d55d1554594e6ab0ffad315ea6a6a77c13627fa6a523399034a851000a253","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T17:59:26Z","title_canon_sha256":"7ae6059ece811c5ab7e666340b5de7a6aba6c387076f06728ac54fc4064afb64"},"schema_version":"1.0","source":{"id":"2410.23287","kind":"arxiv","version":2}},"canonical_sha256":"1474457f60d1db797f781fe2f568f8be779bb3f9ef4838c845c2f9a93adde7d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1474457f60d1db797f781fe2f568f8be779bb3f9ef4838c845c2f9a93adde7d2","first_computed_at":"2026-07-05T11:49:47.825375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:47.825375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8V2KoOE+KJyCUrqP6CiCcN5VY7+zqQ4XIjPfgar5DJ+NjD8yfXZ0URolan1iDy8cEpR4vncq5ppbEhlwECK4Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:47.825824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23287","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c64e23ce2573c93a716468a820a51ba7a07a425230c0ca24081c4c4556ef3d41","sha256:4c9abbabbe233a9823cd3e32ccf7e1ce2d1bb9de4d2e28e072e4e6407e634923"],"state_sha256":"35266a8ad775a44f5cf2d915ce94a0d642d97173933da4d16efb4fa665f34c15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iwM9sab4b1dgAg4eCvqQ7VcySxNXat2rEruunLqjKP+MkZd2mD+7iJ7knHRuoHTdEmAYoBfVVAsBfBM4CPZeAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:27:29.764300Z","bundle_sha256":"03093501d5598562c71ace638942f13ebba3cbf244f22ac0de2df55d33266ac4"}}