{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VBZXPMTME2NXYMPOGXDV4BYFLH","short_pith_number":"pith:VBZXPMTM","canonical_record":{"source":{"id":"2607.00465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T05:34:07Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"28d19cc19ce9525a5d691eede38bf9a47e3616e4d344acc5070c6012d8ea644e","abstract_canon_sha256":"adb7c4d76f36fd380c40225cd031eb51a9c045b2c69b8c41d093b161525774fb"},"schema_version":"1.0"},"canonical_sha256":"a87377b26c269b7c31ee35c75e070559ce6249c75417a6805ebf097c0b93d521","source":{"kind":"arxiv","id":"2607.00465","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00465","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00465v1","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00465","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"pith_short_12","alias_value":"VBZXPMTME2NX","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"pith_short_16","alias_value":"VBZXPMTME2NXYMPO","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"pith_short_8","alias_value":"VBZXPMTM","created_at":"2026-07-02T01:17:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VBZXPMTME2NXYMPOGXDV4BYFLH","target":"record","payload":{"canonical_record":{"source":{"id":"2607.00465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T05:34:07Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"28d19cc19ce9525a5d691eede38bf9a47e3616e4d344acc5070c6012d8ea644e","abstract_canon_sha256":"adb7c4d76f36fd380c40225cd031eb51a9c045b2c69b8c41d093b161525774fb"},"schema_version":"1.0"},"canonical_sha256":"a87377b26c269b7c31ee35c75e070559ce6249c75417a6805ebf097c0b93d521","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:44.209709Z","signature_b64":"mI4W0AIbW/76MFUAsJCxeLuEMtvnO2FEWlQ8hOrGZZu+GfZZSTLni6Nsuqypyh9W65/4q69YbcfxCneZMQqECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a87377b26c269b7c31ee35c75e070559ce6249c75417a6805ebf097c0b93d521","last_reissued_at":"2026-07-02T01:17:44.209324Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:44.209324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.00465","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":"2026-07-02T01:17:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ozdApAhqcb9w76I0C95VGa3D6qRGnmC1Wc3ehC0t0kAfAC6UB5Fc9d+8HDX7g0L0zKf0yEusi/Wt74qsK8gHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T01:23:19.108724Z"},"content_sha256":"484ad2153a61d5bc45950ff764feaf9561be2babd82e4f9a6acaeb72022d6d46","schema_version":"1.0","event_id":"sha256:484ad2153a61d5bc45950ff764feaf9561be2babd82e4f9a6acaeb72022d6d46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VBZXPMTME2NXYMPOGXDV4BYFLH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Chengzhi Mao, Yuan Qing","submitted_at":"2026-07-01T05:34:07Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) rely extensively on Visual Instruction Tuning (VIT) to elicit their multimodal reasoning capabilities. However, we find a discrepancy: VIT often packs multiple language tasks about the same image for conversational, multi-turn training, whereas existing benchmarks evaluate LVLMs in isolated, single-turn scenarios. The models can suffer from visual attention decay and contextual overfitting during multi-turn training, making it hard for them to realize their full potential in the mismatched test phase. To close the gap, we propose learning with Stochastic Tu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00465","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/2607.00465/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":"2026-07-02T01:17:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GnE9oYuwsr+2chDlqQuF1zU9/GtfKSMg8zx8KFvJpkBkj3rGwEAR6Yio6w3I4VMOFQ8zGvPAYlV0XNCFkKvSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T01:23:19.109107Z"},"content_sha256":"ca7c64e884f7930fd832a9176818d190b68f4ddf9767aab29d0b1292772569b9","schema_version":"1.0","event_id":"sha256:ca7c64e884f7930fd832a9176818d190b68f4ddf9767aab29d0b1292772569b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VBZXPMTME2NXYMPOGXDV4BYFLH/bundle.json","state_url":"https://pith.science/pith/VBZXPMTME2NXYMPOGXDV4BYFLH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VBZXPMTME2NXYMPOGXDV4BYFLH/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":"2026-07-03T01:23:19Z","links":{"resolver":"https://pith.science/pith/VBZXPMTME2NXYMPOGXDV4BYFLH","bundle":"https://pith.science/pith/VBZXPMTME2NXYMPOGXDV4BYFLH/bundle.json","state":"https://pith.science/pith/VBZXPMTME2NXYMPOGXDV4BYFLH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VBZXPMTME2NXYMPOGXDV4BYFLH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VBZXPMTME2NXYMPOGXDV4BYFLH","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":"adb7c4d76f36fd380c40225cd031eb51a9c045b2c69b8c41d093b161525774fb","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T05:34:07Z","title_canon_sha256":"28d19cc19ce9525a5d691eede38bf9a47e3616e4d344acc5070c6012d8ea644e"},"schema_version":"1.0","source":{"id":"2607.00465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00465","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00465v1","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00465","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"pith_short_12","alias_value":"VBZXPMTME2NX","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"pith_short_16","alias_value":"VBZXPMTME2NXYMPO","created_at":"2026-07-02T01:17:44Z"},{"alias_kind":"pith_short_8","alias_value":"VBZXPMTM","created_at":"2026-07-02T01:17:44Z"}],"graph_snapshots":[{"event_id":"sha256:ca7c64e884f7930fd832a9176818d190b68f4ddf9767aab29d0b1292772569b9","target":"graph","created_at":"2026-07-02T01:17:44Z","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/2607.00465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) rely extensively on Visual Instruction Tuning (VIT) to elicit their multimodal reasoning capabilities. However, we find a discrepancy: VIT often packs multiple language tasks about the same image for conversational, multi-turn training, whereas existing benchmarks evaluate LVLMs in isolated, single-turn scenarios. The models can suffer from visual attention decay and contextual overfitting during multi-turn training, making it hard for them to realize their full potential in the mismatched test phase. To close the gap, we propose learning with Stochastic Tu","authors_text":"Boqing Gong, Chengzhi Mao, Yuan Qing","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T05:34:07Z","title":"StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00465","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":"sha256:484ad2153a61d5bc45950ff764feaf9561be2babd82e4f9a6acaeb72022d6d46","target":"record","created_at":"2026-07-02T01:17:44Z","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":"adb7c4d76f36fd380c40225cd031eb51a9c045b2c69b8c41d093b161525774fb","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T05:34:07Z","title_canon_sha256":"28d19cc19ce9525a5d691eede38bf9a47e3616e4d344acc5070c6012d8ea644e"},"schema_version":"1.0","source":{"id":"2607.00465","kind":"arxiv","version":1}},"canonical_sha256":"a87377b26c269b7c31ee35c75e070559ce6249c75417a6805ebf097c0b93d521","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a87377b26c269b7c31ee35c75e070559ce6249c75417a6805ebf097c0b93d521","first_computed_at":"2026-07-02T01:17:44.209324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:17:44.209324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mI4W0AIbW/76MFUAsJCxeLuEMtvnO2FEWlQ8hOrGZZu+GfZZSTLni6Nsuqypyh9W65/4q69YbcfxCneZMQqECg==","signature_status":"signed_v1","signed_at":"2026-07-02T01:17:44.209709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:484ad2153a61d5bc45950ff764feaf9561be2babd82e4f9a6acaeb72022d6d46","sha256:ca7c64e884f7930fd832a9176818d190b68f4ddf9767aab29d0b1292772569b9"],"state_sha256":"2617854b84b8882f63740625fdcdfe7dd1c7047499bd4a1cbc452eae3aae470e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HNrVqnVzXp2OgjtzUD1jTiE4qImcFH9QPY2QjUTt6By4pE9MyEqrBssujsS8I5ILRLVOKvKHMrj6MiM7XmfaAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T01:23:19.111305Z","bundle_sha256":"92e3e527d23727b25871b3e62b865a3419a391ea0f56eeb1ea0a0e29579ca98c"}}