{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XXMJ2NHHAXOHWMNFGFBXUC4CXI","short_pith_number":"pith:XXMJ2NHH","canonical_record":{"source":{"id":"2501.04001","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T18:58:54Z","cross_cats_sorted":[],"title_canon_sha256":"182fbd81701d2e83bb759bbc154509c069a63c6d97465120834f6e8e7d179ffb","abstract_canon_sha256":"af1b72fcb24f808b68a624b1c50a2756d0e0ee2cfca9157d605e2e71789746e5"},"schema_version":"1.0"},"canonical_sha256":"bdd89d34e705dc7b31a531437a0b82ba1979ecf24ec99ee74181c8f9372b81a1","source":{"kind":"arxiv","id":"2501.04001","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04001","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04001v3","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04001","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"XXMJ2NHHAXOH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XXMJ2NHHAXOHWMNF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XXMJ2NHH","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XXMJ2NHHAXOHWMNFGFBXUC4CXI","target":"record","payload":{"canonical_record":{"source":{"id":"2501.04001","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T18:58:54Z","cross_cats_sorted":[],"title_canon_sha256":"182fbd81701d2e83bb759bbc154509c069a63c6d97465120834f6e8e7d179ffb","abstract_canon_sha256":"af1b72fcb24f808b68a624b1c50a2756d0e0ee2cfca9157d605e2e71789746e5"},"schema_version":"1.0"},"canonical_sha256":"bdd89d34e705dc7b31a531437a0b82ba1979ecf24ec99ee74181c8f9372b81a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.000652Z","signature_b64":"iNC8AvmmvhT4VsBahBDAPDHVjw8yB3GQZYeLULtDlZePTUySLtRYat3Gl6t6X1V+pV99rH/BtK9SQuPxMo2nBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdd89d34e705dc7b31a531437a0b82ba1979ecf24ec99ee74181c8f9372b81a1","last_reissued_at":"2026-05-17T23:38:48.000065Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.000065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.04001","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":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ar3k+urEIqBOp/l6qZMqiD4KgdxcLzbG+3LsSl0dOVmqAH3lscW2/XtYwS0OmKhJ/w+hj/bFGiXECysnWjAmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:39:40.506173Z"},"content_sha256":"03452bb6120413c69ae6fe06e4f2f3d5d169ea1048c06b153873075c664c8722","schema_version":"1.0","event_id":"sha256:03452bb6120413c69ae6fe06e4f2f3d5d169ea1048c06b153873075c664c8722"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XXMJ2NHHAXOHWMNFGFBXUC4CXI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Sa2VA unifies segmentation and language models for referring tasks on both images and videos using minimal instruction tuning.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haobo Yuan, Jiashi Feng, Lu Qi, Ming-Hsuan Yang, Shilin Xu, Shunping Ji, Tao Zhang, Xiangtai Li, Yueyi Sun, Yunhai Tong, Zilong Huang","submitted_at":"2025-01-07T18:58:54Z","abstract_excerpt":"This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-modal large language models, which are often limited to specific modalities and tasks, Sa2VA supports a wide range of image and video tasks, including referring segmentation and conversation, with minimal one-shot instruction tuning. Sa2VA combines SAM-2, a foundation video segmentation model, with MLLM, the advanced vision-language model, and unifies text, image, and video into a shared LLM token space. Using the LLM, Sa2VA generates instruction to"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Sa2VA is the first comprehensive, unified model for dense grounded understanding of both images and videos that supports referring segmentation and conversation with minimal one-shot instruction tuning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the LLM-generated instruction tokens can reliably guide SAM-2 to produce precise masks across complex video scenes without task-specific architectural changes or heavy fine-tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Sa2VA unifies SAM-2 segmentation with MLLM reasoning into a single model for referring segmentation and conversation on images and videos, supported by a new 72k-expression Ref-SAV dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Sa2VA unifies segmentation and language models for referring tasks on both images and videos using minimal instruction tuning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e2e0c6f450bbd5a684e1cce0175ca33a6167b5f731f0c3ab33d5f25dd01d6f71"},"source":{"id":"2501.04001","kind":"arxiv","version":3},"verdict":{"id":"96ea7224-7912-48dc-ba16-361d3a3b6fc6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T11:35:57.949381Z","strongest_claim":"Sa2VA is the first comprehensive, unified model for dense grounded understanding of both images and videos that supports referring segmentation and conversation with minimal one-shot instruction tuning.","one_line_summary":"Sa2VA unifies SAM-2 segmentation with MLLM reasoning into a single model for referring segmentation and conversation on images and videos, supported by a new 72k-expression Ref-SAV dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the LLM-generated instruction tokens can reliably guide SAM-2 to produce precise masks across complex video scenes without task-specific architectural changes or heavy fine-tuning.","pith_extraction_headline":"Sa2VA unifies segmentation and language models for referring tasks on both images and videos using minimal instruction tuning."},"references":{"count":125,"sample":[{"doi":"","year":2015,"title":"Vqa: Visual question an- swering","work_id":"4f7b2ba9-84f5-40f4-8098-9380e897823d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","ref_index":2,"cited_arxiv_id":"2308.12966","is_internal_anchor":true},{"doi":"","year":2025,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","ref_index":3,"cited_arxiv_id":"2502.13923","is_internal_anchor":true},{"doi":"","year":2024,"title":"One token to seg them all: Language instructed reasoning segmentation in videos","work_id":"530daa38-715a-4558-b3a3-a6815a7b7604","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Language models are few-shot learners","work_id":"0640f028-a03b-4b3e-b61b-59f4dc45f798","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":125,"snapshot_sha256":"e92b0993659e5cb959521db9c098eb29a88fa395e46bdf26e2ead24e0756b1c3","internal_anchors":21},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c5a0eaf80ac15fff66dc43e957e0b934c253c88c53d0a75462d6131576c315cb"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"96ea7224-7912-48dc-ba16-361d3a3b6fc6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qFaTOXLI6MpuPHoVFFfoGOtAewEAnUL+41lgK/6khZJv+Ctt1naSUlHWB8Gc8WEykuvSsblpQKWvvUsYgWKhBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:39:40.507217Z"},"content_sha256":"d546cc13e0caf2be2cb60872f5e84fefb6befc2ecd434f8461739db19be221dc","schema_version":"1.0","event_id":"sha256:d546cc13e0caf2be2cb60872f5e84fefb6befc2ecd434f8461739db19be221dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI/bundle.json","state_url":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI/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":"2026-05-26T00:39:40Z","links":{"resolver":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI","bundle":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI/bundle.json","state":"https://pith.science/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XXMJ2NHHAXOHWMNFGFBXUC4CXI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XXMJ2NHHAXOHWMNFGFBXUC4CXI","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":"af1b72fcb24f808b68a624b1c50a2756d0e0ee2cfca9157d605e2e71789746e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T18:58:54Z","title_canon_sha256":"182fbd81701d2e83bb759bbc154509c069a63c6d97465120834f6e8e7d179ffb"},"schema_version":"1.0","source":{"id":"2501.04001","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04001","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04001v3","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04001","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"XXMJ2NHHAXOH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"XXMJ2NHHAXOHWMNF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"XXMJ2NHH","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d546cc13e0caf2be2cb60872f5e84fefb6befc2ecd434f8461739db19be221dc","target":"graph","created_at":"2026-05-17T23:38:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Sa2VA is the first comprehensive, unified model for dense grounded understanding of both images and videos that supports referring segmentation and conversation with minimal one-shot instruction tuning."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the LLM-generated instruction tokens can reliably guide SAM-2 to produce precise masks across complex video scenes without task-specific architectural changes or heavy fine-tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Sa2VA unifies SAM-2 segmentation with MLLM reasoning into a single model for referring segmentation and conversation on images and videos, supported by a new 72k-expression Ref-SAV dataset."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Sa2VA unifies segmentation and language models for referring tasks on both images and videos using minimal instruction tuning."}],"snapshot_sha256":"e2e0c6f450bbd5a684e1cce0175ca33a6167b5f731f0c3ab33d5f25dd01d6f71"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c5a0eaf80ac15fff66dc43e957e0b934c253c88c53d0a75462d6131576c315cb"},"paper":{"abstract_excerpt":"This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-modal large language models, which are often limited to specific modalities and tasks, Sa2VA supports a wide range of image and video tasks, including referring segmentation and conversation, with minimal one-shot instruction tuning. Sa2VA combines SAM-2, a foundation video segmentation model, with MLLM, the advanced vision-language model, and unifies text, image, and video into a shared LLM token space. Using the LLM, Sa2VA generates instruction to","authors_text":"Haobo Yuan, Jiashi Feng, Lu Qi, Ming-Hsuan Yang, Shilin Xu, Shunping Ji, Tao Zhang, Xiangtai Li, Yueyi Sun, Yunhai Tong, Zilong Huang","cross_cats":[],"headline":"Sa2VA unifies segmentation and language models for referring tasks on both images and videos using minimal instruction tuning.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T18:58:54Z","title":"Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos"},"references":{"count":125,"internal_anchors":21,"resolved_work":125,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Vqa: Visual question an- swering","work_id":"4f7b2ba9-84f5-40f4-8098-9380e897823d","year":2015},{"cited_arxiv_id":"2308.12966","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","year":2023},{"cited_arxiv_id":"2502.13923","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"One token to seg them all: Language instructed reasoning segmentation in videos","work_id":"530daa38-715a-4558-b3a3-a6815a7b7604","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Language models are few-shot learners","work_id":"0640f028-a03b-4b3e-b61b-59f4dc45f798","year":2020}],"snapshot_sha256":"e92b0993659e5cb959521db9c098eb29a88fa395e46bdf26e2ead24e0756b1c3"},"source":{"id":"2501.04001","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T11:35:57.949381Z","id":"96ea7224-7912-48dc-ba16-361d3a3b6fc6","model_set":{"reader":"grok-4.3"},"one_line_summary":"Sa2VA unifies SAM-2 segmentation with MLLM reasoning into a single model for referring segmentation and conversation on images and videos, supported by a new 72k-expression Ref-SAV dataset.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Sa2VA unifies segmentation and language models for referring tasks on both images and videos using minimal instruction tuning.","strongest_claim":"Sa2VA is the first comprehensive, unified model for dense grounded understanding of both images and videos that supports referring segmentation and conversation with minimal one-shot instruction tuning.","weakest_assumption":"That the LLM-generated instruction tokens can reliably guide SAM-2 to produce precise masks across complex video scenes without task-specific architectural changes or heavy fine-tuning."}},"verdict_id":"96ea7224-7912-48dc-ba16-361d3a3b6fc6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:03452bb6120413c69ae6fe06e4f2f3d5d169ea1048c06b153873075c664c8722","target":"record","created_at":"2026-05-17T23:38:48Z","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":"af1b72fcb24f808b68a624b1c50a2756d0e0ee2cfca9157d605e2e71789746e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T18:58:54Z","title_canon_sha256":"182fbd81701d2e83bb759bbc154509c069a63c6d97465120834f6e8e7d179ffb"},"schema_version":"1.0","source":{"id":"2501.04001","kind":"arxiv","version":3}},"canonical_sha256":"bdd89d34e705dc7b31a531437a0b82ba1979ecf24ec99ee74181c8f9372b81a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdd89d34e705dc7b31a531437a0b82ba1979ecf24ec99ee74181c8f9372b81a1","first_computed_at":"2026-05-17T23:38:48.000065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.000065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iNC8AvmmvhT4VsBahBDAPDHVjw8yB3GQZYeLULtDlZePTUySLtRYat3Gl6t6X1V+pV99rH/BtK9SQuPxMo2nBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.000652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04001","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03452bb6120413c69ae6fe06e4f2f3d5d169ea1048c06b153873075c664c8722","sha256:d546cc13e0caf2be2cb60872f5e84fefb6befc2ecd434f8461739db19be221dc"],"state_sha256":"83180cdc75858415fd345936896be86561acd8cdab6b6aae4dda4a2b728e7384"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/RnsOTYraSWRlUOVCvvVxwFRgrQ1/wm6hC/VBSUcfQL463TAMZ8BUPMce1J6epUSsehd4l2hWzD796jhhL8VBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:39:40.516729Z","bundle_sha256":"055abe6ed9e0845fb4af1ef7a15f1abdee4317f1d6c5f4125897b29d768c6a91"}}