{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NNEEBC6MNLTJFFST3PZ52AXYOP","short_pith_number":"pith:NNEEBC6M","canonical_record":{"source":{"id":"2406.10995","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T16:15:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8743576bc2ff330debc6123b95c568e775ed493f3703e488c69fca57fe2c50d4","abstract_canon_sha256":"a989c245a9987be6d0b311f124e165f47a66bff359b261fffada9fb003231e05"},"schema_version":"1.0"},"canonical_sha256":"6b48408bcc6ae6929653dbf3dd02f873da577f53015ee083b816bbee0daab48b","source":{"kind":"arxiv","id":"2406.10995","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10995","created_at":"2026-07-05T09:14:34Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10995v2","created_at":"2026-07-05T09:14:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10995","created_at":"2026-07-05T09:14:34Z"},{"alias_kind":"pith_short_12","alias_value":"NNEEBC6MNLTJ","created_at":"2026-07-05T09:14:34Z"},{"alias_kind":"pith_short_16","alias_value":"NNEEBC6MNLTJFFST","created_at":"2026-07-05T09:14:34Z"},{"alias_kind":"pith_short_8","alias_value":"NNEEBC6M","created_at":"2026-07-05T09:14:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NNEEBC6MNLTJFFST3PZ52AXYOP","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10995","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T16:15:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8743576bc2ff330debc6123b95c568e775ed493f3703e488c69fca57fe2c50d4","abstract_canon_sha256":"a989c245a9987be6d0b311f124e165f47a66bff359b261fffada9fb003231e05"},"schema_version":"1.0"},"canonical_sha256":"6b48408bcc6ae6929653dbf3dd02f873da577f53015ee083b816bbee0daab48b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:34.652868Z","signature_b64":"bVBb0fZDpkAAu8bLeEJ6Byf92Dd5mEUylvfXgbLWoN2VQc7Q8MkNXN7Z8XbMAbMuTUTmEwBuaoeVB1T0M/sKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b48408bcc6ae6929653dbf3dd02f873da577f53015ee083b816bbee0daab48b","last_reissued_at":"2026-07-05T09:14:34.652451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:34.652451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10995","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":"2026-07-05T09:14:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SGbnvQGoMucspt6ZGJqlrUzcvaCUHZOyt4ngSh7aItdtPv4SorZFUH9dnHrEMh/P17s30mxGssSZ09jWq0FJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:55:07.661065Z"},"content_sha256":"98006b852dedb5e4f11ad12c7c1b0c23380d797a1e69acbffaf845c1b8c8c452","schema_version":"1.0","event_id":"sha256:98006b852dedb5e4f11ad12c7c1b0c23380d797a1e69acbffaf845c1b8c8c452"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NNEEBC6MNLTJFFST3PZ52AXYOP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Concept-skill Transferability-based Data Selection for Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Boyang Li, Jaewoo Lee, Sung Ju Hwang","submitted_at":"2024-06-16T16:15:20Z","abstract_excerpt":"Instruction tuning, or supervised finetuning on extensive task-specific data, is necessary for Large Vision-Language Models (LVLMs) to generalize well across a broad range of vision-language (VL) tasks. However, training on large VL datasets can become prohibitively expensive. In this work, we introduce COINCIDE, an effective and scalable data selection technique that uses a small model as a reference model to select visual instruction tuning data for efficient finetuning of a target LVLM, focusing on diversity and transferability. Specifically, we cluster the training data using internal acti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10995","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/2406.10995/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":"2026-07-05T09:14:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nTDayx1luR58d6FcTm1jHSbCUIZCJ0IsmyQU/9BCOEzeViPnqr26mlgo1cZpts/RTRms8YrtLZKBNtVNrBTNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:55:07.661564Z"},"content_sha256":"7cffff018e1cc3c6dc0b29f83da4f2f02ea0681dd52c7f71ae885257796c41b2","schema_version":"1.0","event_id":"sha256:7cffff018e1cc3c6dc0b29f83da4f2f02ea0681dd52c7f71ae885257796c41b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NNEEBC6MNLTJFFST3PZ52AXYOP/bundle.json","state_url":"https://pith.science/pith/NNEEBC6MNLTJFFST3PZ52AXYOP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NNEEBC6MNLTJFFST3PZ52AXYOP/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":"2026-08-09T09:55:07Z","links":{"resolver":"https://pith.science/pith/NNEEBC6MNLTJFFST3PZ52AXYOP","bundle":"https://pith.science/pith/NNEEBC6MNLTJFFST3PZ52AXYOP/bundle.json","state":"https://pith.science/pith/NNEEBC6MNLTJFFST3PZ52AXYOP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NNEEBC6MNLTJFFST3PZ52AXYOP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NNEEBC6MNLTJFFST3PZ52AXYOP","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":"a989c245a9987be6d0b311f124e165f47a66bff359b261fffada9fb003231e05","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T16:15:20Z","title_canon_sha256":"8743576bc2ff330debc6123b95c568e775ed493f3703e488c69fca57fe2c50d4"},"schema_version":"1.0","source":{"id":"2406.10995","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10995","created_at":"2026-07-05T09:14:34Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10995v2","created_at":"2026-07-05T09:14:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10995","created_at":"2026-07-05T09:14:34Z"},{"alias_kind":"pith_short_12","alias_value":"NNEEBC6MNLTJ","created_at":"2026-07-05T09:14:34Z"},{"alias_kind":"pith_short_16","alias_value":"NNEEBC6MNLTJFFST","created_at":"2026-07-05T09:14:34Z"},{"alias_kind":"pith_short_8","alias_value":"NNEEBC6M","created_at":"2026-07-05T09:14:34Z"}],"graph_snapshots":[{"event_id":"sha256:7cffff018e1cc3c6dc0b29f83da4f2f02ea0681dd52c7f71ae885257796c41b2","target":"graph","created_at":"2026-07-05T09:14:34Z","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/2406.10995/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning, or supervised finetuning on extensive task-specific data, is necessary for Large Vision-Language Models (LVLMs) to generalize well across a broad range of vision-language (VL) tasks. However, training on large VL datasets can become prohibitively expensive. In this work, we introduce COINCIDE, an effective and scalable data selection technique that uses a small model as a reference model to select visual instruction tuning data for efficient finetuning of a target LVLM, focusing on diversity and transferability. Specifically, we cluster the training data using internal acti","authors_text":"Boyang Li, Jaewoo Lee, Sung Ju Hwang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T16:15:20Z","title":"Concept-skill Transferability-based Data Selection for Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10995","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":"sha256:98006b852dedb5e4f11ad12c7c1b0c23380d797a1e69acbffaf845c1b8c8c452","target":"record","created_at":"2026-07-05T09:14:34Z","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":"a989c245a9987be6d0b311f124e165f47a66bff359b261fffada9fb003231e05","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T16:15:20Z","title_canon_sha256":"8743576bc2ff330debc6123b95c568e775ed493f3703e488c69fca57fe2c50d4"},"schema_version":"1.0","source":{"id":"2406.10995","kind":"arxiv","version":2}},"canonical_sha256":"6b48408bcc6ae6929653dbf3dd02f873da577f53015ee083b816bbee0daab48b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b48408bcc6ae6929653dbf3dd02f873da577f53015ee083b816bbee0daab48b","first_computed_at":"2026-07-05T09:14:34.652451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:34.652451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bVBb0fZDpkAAu8bLeEJ6Byf92Dd5mEUylvfXgbLWoN2VQc7Q8MkNXN7Z8XbMAbMuTUTmEwBuaoeVB1T0M/sKBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:34.652868Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10995","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98006b852dedb5e4f11ad12c7c1b0c23380d797a1e69acbffaf845c1b8c8c452","sha256:7cffff018e1cc3c6dc0b29f83da4f2f02ea0681dd52c7f71ae885257796c41b2"],"state_sha256":"1f9c9ec22ed5e689ee694d33808edbe1fddeb228215ec6621cb528f47747e514"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vTab/A+tcVdMxMlEcVGjfmtks3/C4DdL009UyZdbVLeTgOwyoqmkicAQngwifl1PUhmpTtuhLUmeyXk68YIDDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:55:07.665012Z","bundle_sha256":"2c4146e27d5913ea50ab973d753238d45f7681942e20c100b6f7e6295daf886c"}}