{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:54FYWGP3HXZ4GMNYV3AIQ5BYUU","short_pith_number":"pith:54FYWGP3","canonical_record":{"source":{"id":"2606.01612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:01:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"33c3e76196fc37dfb96315dee59c9f69dfb9b819499e87a6b7f9c39f9b03962e","abstract_canon_sha256":"f28ebeed468f713d76d8120a26c6ca6a22eccdeed568d402d5703ab4b6f57df5"},"schema_version":"1.0"},"canonical_sha256":"ef0b8b19fb3df3c331b8aec0887438a519259bcda75a58d4f661f2822f972842","source":{"kind":"arxiv","id":"2606.01612","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01612","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01612v1","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01612","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"54FYWGP3HXZ4","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"54FYWGP3HXZ4GMNY","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"54FYWGP3","created_at":"2026-06-02T02:04:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:54FYWGP3HXZ4GMNYV3AIQ5BYUU","target":"record","payload":{"canonical_record":{"source":{"id":"2606.01612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:01:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"33c3e76196fc37dfb96315dee59c9f69dfb9b819499e87a6b7f9c39f9b03962e","abstract_canon_sha256":"f28ebeed468f713d76d8120a26c6ca6a22eccdeed568d402d5703ab4b6f57df5"},"schema_version":"1.0"},"canonical_sha256":"ef0b8b19fb3df3c331b8aec0887438a519259bcda75a58d4f661f2822f972842","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:38.026212Z","signature_b64":"Dh13gyzkHEtQs2yRI9xLRPxr83zwm03274h/jvOFzCPRbU7lppOZzRqFFdU8jPFhvndglqpL3jUAlPN0QbctDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef0b8b19fb3df3c331b8aec0887438a519259bcda75a58d4f661f2822f972842","last_reissued_at":"2026-06-02T02:04:38.025803Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:38.025803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.01612","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":"2026-06-02T02:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ig5urtnp8zW+SKcbPT3VDL/Q4Ogsx3KOPuTWz1Nbcr+MKkYDA4uGdGsPNA9/Ex85SwzT+rQTikcn+UEuHRuOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T10:01:35.406568Z"},"content_sha256":"87488cfdbb6559d3ca49d13f7c72dde5fea31ca320c888803362e81833f43cb2","schema_version":"1.0","event_id":"sha256:87488cfdbb6559d3ca49d13f7c72dde5fea31ca320c888803362e81833f43cb2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:54FYWGP3HXZ4GMNYV3AIQ5BYUU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Improving Small Object Grounding in LVLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jin Sun, Ninghao Liu, Ruitong Sun, Tianze Yang, Yucheng Shi","submitted_at":"2026-06-01T03:01:38Z","abstract_excerpt":"Can internal attention patterns in Large Vision Language Models (LVLMs) identify reliable small-object boxes without fine-tuning? In this work, we provide an affirmative answer. Attention structure in LVLMs encodes grounding quality-a lightweight IoU regressor trained solely on attention maps achieves strong IoU prediction (Pearson r > 0.67). This regressor powers the regressor-based variant of our Attention-based Candidate Selection (ACS) framework, called ACS-Learned, which selects the best box from multiple sampled candidates to improve object grounding. By analyzing what the regressor lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01612","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/2606.01612/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":"2026-06-02T02:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6pDr4HX+3TN8QSvL6giN+FUCCZ6yGTYt32NYB6uu5CWL080DeRxyKYXmDMCHyGg25LsIYyYhefNNTXAp502PAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T10:01:35.406929Z"},"content_sha256":"7dc6d803599c29b82f3d17939c7fcb7847255fc4002204959d8c0a8db6d5e67f","schema_version":"1.0","event_id":"sha256:7dc6d803599c29b82f3d17939c7fcb7847255fc4002204959d8c0a8db6d5e67f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/54FYWGP3HXZ4GMNYV3AIQ5BYUU/bundle.json","state_url":"https://pith.science/pith/54FYWGP3HXZ4GMNYV3AIQ5BYUU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/54FYWGP3HXZ4GMNYV3AIQ5BYUU/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":"2026-07-05T10:01:35Z","links":{"resolver":"https://pith.science/pith/54FYWGP3HXZ4GMNYV3AIQ5BYUU","bundle":"https://pith.science/pith/54FYWGP3HXZ4GMNYV3AIQ5BYUU/bundle.json","state":"https://pith.science/pith/54FYWGP3HXZ4GMNYV3AIQ5BYUU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/54FYWGP3HXZ4GMNYV3AIQ5BYUU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:54FYWGP3HXZ4GMNYV3AIQ5BYUU","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":"f28ebeed468f713d76d8120a26c6ca6a22eccdeed568d402d5703ab4b6f57df5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:01:38Z","title_canon_sha256":"33c3e76196fc37dfb96315dee59c9f69dfb9b819499e87a6b7f9c39f9b03962e"},"schema_version":"1.0","source":{"id":"2606.01612","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01612","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01612v1","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01612","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"54FYWGP3HXZ4","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"54FYWGP3HXZ4GMNY","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"54FYWGP3","created_at":"2026-06-02T02:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:7dc6d803599c29b82f3d17939c7fcb7847255fc4002204959d8c0a8db6d5e67f","target":"graph","created_at":"2026-06-02T02:04:38Z","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/2606.01612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can internal attention patterns in Large Vision Language Models (LVLMs) identify reliable small-object boxes without fine-tuning? In this work, we provide an affirmative answer. Attention structure in LVLMs encodes grounding quality-a lightweight IoU regressor trained solely on attention maps achieves strong IoU prediction (Pearson r > 0.67). This regressor powers the regressor-based variant of our Attention-based Candidate Selection (ACS) framework, called ACS-Learned, which selects the best box from multiple sampled candidates to improve object grounding. By analyzing what the regressor lear","authors_text":"Jin Sun, Ninghao Liu, Ruitong Sun, Tianze Yang, Yucheng Shi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:01:38Z","title":"Self-Improving Small Object Grounding in LVLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01612","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":"sha256:87488cfdbb6559d3ca49d13f7c72dde5fea31ca320c888803362e81833f43cb2","target":"record","created_at":"2026-06-02T02:04:38Z","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":"f28ebeed468f713d76d8120a26c6ca6a22eccdeed568d402d5703ab4b6f57df5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:01:38Z","title_canon_sha256":"33c3e76196fc37dfb96315dee59c9f69dfb9b819499e87a6b7f9c39f9b03962e"},"schema_version":"1.0","source":{"id":"2606.01612","kind":"arxiv","version":1}},"canonical_sha256":"ef0b8b19fb3df3c331b8aec0887438a519259bcda75a58d4f661f2822f972842","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef0b8b19fb3df3c331b8aec0887438a519259bcda75a58d4f661f2822f972842","first_computed_at":"2026-06-02T02:04:38.025803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:38.025803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dh13gyzkHEtQs2yRI9xLRPxr83zwm03274h/jvOFzCPRbU7lppOZzRqFFdU8jPFhvndglqpL3jUAlPN0QbctDw==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:38.026212Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01612","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87488cfdbb6559d3ca49d13f7c72dde5fea31ca320c888803362e81833f43cb2","sha256:7dc6d803599c29b82f3d17939c7fcb7847255fc4002204959d8c0a8db6d5e67f"],"state_sha256":"0a99b58b583cc1fe12e5275d68efa25b2ef9dea5553c6cf9133dc7482e0c5702"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PGc80fGOldDKL610sprj/OCP+F+rxQx7gZt8QgvTCztvTEbRUzfu6q2pZZbUAWnivW/UDrSShvHXdVYFtw/kBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T10:01:35.408840Z","bundle_sha256":"8fb041045ea4c3ea3dfe318374f0f3c436b25dfe5badafe09d14f75d60964886"}}