{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TDXIDFFTATRKCAEFGGK3VA27MG","short_pith_number":"pith:TDXIDFFT","canonical_record":{"source":{"id":"2605.14908","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T14:42:15Z","cross_cats_sorted":[],"title_canon_sha256":"9f8111af3e968d863d3e60875abe4387321a924ed29e202166b28997b3329562","abstract_canon_sha256":"5564502bc98bef97c3c14625d13a6fe933c6904ef6f4b2b1f92c30f3684a7949"},"schema_version":"1.0"},"canonical_sha256":"98ee8194b304e2a100853195ba835f618b157592be3afb60aff6bd845d45da94","source":{"kind":"arxiv","id":"2605.14908","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14908","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14908v1","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14908","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"TDXIDFFTATRK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TDXIDFFTATRKCAEF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TDXIDFFT","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TDXIDFFTATRKCAEFGGK3VA27MG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14908","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T14:42:15Z","cross_cats_sorted":[],"title_canon_sha256":"9f8111af3e968d863d3e60875abe4387321a924ed29e202166b28997b3329562","abstract_canon_sha256":"5564502bc98bef97c3c14625d13a6fe933c6904ef6f4b2b1f92c30f3684a7949"},"schema_version":"1.0"},"canonical_sha256":"98ee8194b304e2a100853195ba835f618b157592be3afb60aff6bd845d45da94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:55.795207Z","signature_b64":"aW7WytiL/+XLSPxWGg39/tvt/lZ34ckUi8e7Q/xZWfzdX8l5MTnpkdxIturV+b63qrWAZXj3PH+1tLNOy6QjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98ee8194b304e2a100853195ba835f618b157592be3afb60aff6bd845d45da94","last_reissued_at":"2026-05-17T23:38:55.794460Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:55.794460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14908","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":"2026-05-17T23:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4/4epPb09z0BveQ7xeicd1DXcGFbKOrNZ9RvOasTuZKnprhv9bbXj11xDmCesvcrWJB13Dr12iW0jtbZNP78DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:57:40.912398Z"},"content_sha256":"349bf3978e9443cebf91d7a723de44c15126fda2f4fad08c4d35319139dfe06e","schema_version":"1.0","event_id":"sha256:349bf3978e9443cebf91d7a723de44c15126fda2f4fad08c4d35319139dfe06e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TDXIDFFTATRKCAEFGGK3VA27MG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SteerSeg: Attention Steering for Reasoning Video Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelwahed Khamis, Aijun An, Ali Cheraghian, Hamidreza Dastmalchi, Lars Petersson, Morteza Saberi","submitted_at":"2026-05-14T14:42:15Z","abstract_excerpt":"Video reasoning segmentation requires localizing objects across video frames from natural language expressions, often involving spatial reasoning and implicit references. Recent approaches leverage frozen large vision-language models (LVLMs) by extracting attention maps and using them as spatial priors for segmentation, enabling training-free grounding. However, these attention maps are optimized for text generation rather than spatial localization, often resulting in diffuse and ambiguous grounding signals. In this work, we introduce SteerSeg, a lightweight framework that identifies attention"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14908","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":""},"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":"2026-05-17T23:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sFzEnRGVxNVLGuxfk+LWiFc8wUhV39rnzqRwSDcgmhTDu0yMtxta/C17lIUf5TG44JtiyrwlDdjCvy/sHZWYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:57:40.912774Z"},"content_sha256":"ca145b998b07358ec3dc518c67510972aafbca369eed56377fb697d4fdd3d5ca","schema_version":"1.0","event_id":"sha256:ca145b998b07358ec3dc518c67510972aafbca369eed56377fb697d4fdd3d5ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TDXIDFFTATRKCAEFGGK3VA27MG/bundle.json","state_url":"https://pith.science/pith/TDXIDFFTATRKCAEFGGK3VA27MG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TDXIDFFTATRKCAEFGGK3VA27MG/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":"2026-05-26T11:57:40Z","links":{"resolver":"https://pith.science/pith/TDXIDFFTATRKCAEFGGK3VA27MG","bundle":"https://pith.science/pith/TDXIDFFTATRKCAEFGGK3VA27MG/bundle.json","state":"https://pith.science/pith/TDXIDFFTATRKCAEFGGK3VA27MG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TDXIDFFTATRKCAEFGGK3VA27MG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TDXIDFFTATRKCAEFGGK3VA27MG","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":"5564502bc98bef97c3c14625d13a6fe933c6904ef6f4b2b1f92c30f3684a7949","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T14:42:15Z","title_canon_sha256":"9f8111af3e968d863d3e60875abe4387321a924ed29e202166b28997b3329562"},"schema_version":"1.0","source":{"id":"2605.14908","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14908","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14908v1","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14908","created_at":"2026-05-17T23:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"TDXIDFFTATRK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TDXIDFFTATRKCAEF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TDXIDFFT","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:ca145b998b07358ec3dc518c67510972aafbca369eed56377fb697d4fdd3d5ca","target":"graph","created_at":"2026-05-17T23:38:55Z","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"},"paper":{"abstract_excerpt":"Video reasoning segmentation requires localizing objects across video frames from natural language expressions, often involving spatial reasoning and implicit references. Recent approaches leverage frozen large vision-language models (LVLMs) by extracting attention maps and using them as spatial priors for segmentation, enabling training-free grounding. However, these attention maps are optimized for text generation rather than spatial localization, often resulting in diffuse and ambiguous grounding signals. In this work, we introduce SteerSeg, a lightweight framework that identifies attention","authors_text":"Abdelwahed Khamis, Aijun An, Ali Cheraghian, Hamidreza Dastmalchi, Lars Petersson, Morteza Saberi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T14:42:15Z","title":"SteerSeg: Attention Steering for Reasoning Video Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14908","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":"sha256:349bf3978e9443cebf91d7a723de44c15126fda2f4fad08c4d35319139dfe06e","target":"record","created_at":"2026-05-17T23:38:55Z","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":"5564502bc98bef97c3c14625d13a6fe933c6904ef6f4b2b1f92c30f3684a7949","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T14:42:15Z","title_canon_sha256":"9f8111af3e968d863d3e60875abe4387321a924ed29e202166b28997b3329562"},"schema_version":"1.0","source":{"id":"2605.14908","kind":"arxiv","version":1}},"canonical_sha256":"98ee8194b304e2a100853195ba835f618b157592be3afb60aff6bd845d45da94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98ee8194b304e2a100853195ba835f618b157592be3afb60aff6bd845d45da94","first_computed_at":"2026-05-17T23:38:55.794460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:55.794460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aW7WytiL/+XLSPxWGg39/tvt/lZ34ckUi8e7Q/xZWfzdX8l5MTnpkdxIturV+b63qrWAZXj3PH+1tLNOy6QjAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:55.795207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14908","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:349bf3978e9443cebf91d7a723de44c15126fda2f4fad08c4d35319139dfe06e","sha256:ca145b998b07358ec3dc518c67510972aafbca369eed56377fb697d4fdd3d5ca"],"state_sha256":"8bd9b798601630fd8d1a63df93ce7b835777763c183833beea37ffb79bbd34ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gy9mdvuBNi089UokYtJDwcuYu0EDzeaCZk9lv9DFvE5w1M1IOp1upiFPUIvJealq7hdXHxZDwN+ZhCJexhK/DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T11:57:40.915725Z","bundle_sha256":"1205912b1e02716f486ef1cfdd73a0783efffe50b239d9838cf1ccabb3c8b529"}}