{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KWTF3WLXKNUW2AKA6YBWB6SK4K","short_pith_number":"pith:KWTF3WLX","canonical_record":{"source":{"id":"2412.18675","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T20:28:07Z","cross_cats_sorted":[],"title_canon_sha256":"13599989a4eb31eb862088500ad7c17303b8b4027309c88f045e5957547e3728","abstract_canon_sha256":"741d0e4b41258ae74edc940124810e1fc95b1de46ca7d6f4c3e63ca35552d42c"},"schema_version":"1.0"},"canonical_sha256":"55a65dd97753696d0140f60360fa4ae290799af25ee1a2bdbebdc6aa4dfed115","source":{"kind":"arxiv","id":"2412.18675","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18675","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18675v4","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18675","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_12","alias_value":"KWTF3WLXKNUW","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_16","alias_value":"KWTF3WLXKNUW2AKA","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_8","alias_value":"KWTF3WLX","created_at":"2026-07-05T11:36:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KWTF3WLXKNUW2AKA6YBWB6SK4K","target":"record","payload":{"canonical_record":{"source":{"id":"2412.18675","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T20:28:07Z","cross_cats_sorted":[],"title_canon_sha256":"13599989a4eb31eb862088500ad7c17303b8b4027309c88f045e5957547e3728","abstract_canon_sha256":"741d0e4b41258ae74edc940124810e1fc95b1de46ca7d6f4c3e63ca35552d42c"},"schema_version":"1.0"},"canonical_sha256":"55a65dd97753696d0140f60360fa4ae290799af25ee1a2bdbebdc6aa4dfed115","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:55.161002Z","signature_b64":"mjYe/VGaLbm+/O8q9+sAC1qMCrz2Z65iRDOvfDxOEwmhMwt0kspVd3ZliBXB/2I8sOTMTMhjqtBQTTQrQoGdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55a65dd97753696d0140f60360fa4ae290799af25ee1a2bdbebdc6aa4dfed115","last_reissued_at":"2026-07-05T11:36:55.159665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:55.159665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.18675","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:36:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XRmZZpq2hbow1/CdDCJk20/8BGL+O+gOeoPIhZnuyejNXLJ98UYFbL8a/q3/+rpw+IWh4XK9WS+zw9Edv8Q2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:56:08.980602Z"},"content_sha256":"444607b21db365720958c13c7b1d107e79edba6baa0f487db3f69efdcd3329df","schema_version":"1.0","event_id":"sha256:444607b21db365720958c13c7b1d107e79edba6baa0f487db3f69efdcd3329df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KWTF3WLXKNUW2AKA6YBWB6SK4K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Totti Nguyen, Hung Huy Nguyen, Long Mai, Pooyan Rahmanzadehgervi, Rosanne Liu","submitted_at":"2024-12-24T20:28:07Z","abstract_excerpt":"Multi-head self-attention (MHSA) is a key component of Transformers, a widely popular architecture in both language and vision. Multiple heads intuitively enable different parallel processes over the same input. Yet, they also obscure the attribution of each input patch to the output of a model. We propose a novel 1-head Transformer Attention Bottleneck (TAB) layer, inserted after the traditional MHSA architecture, to serve as an attention bottleneck for interpretability and intervention. Unlike standard self-attention, TAB constrains the total attention over all patches to $\\in [0, 1]$. That "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18675","kind":"arxiv","version":4},"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/2412.18675/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":"2026-07-05T11:36:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GwpOdii0nyXy5rj3g2jvxzNpA6w3PcObG8NU6XwAqJKz2dm8nZNQWUjEbVPZCu8QA7yu3R5yUJXltkl01NqHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:56:08.981380Z"},"content_sha256":"d5f664edfa211409485f5cd5aab9f0b5044b712092128ad0fdb8c815da46bd13","schema_version":"1.0","event_id":"sha256:d5f664edfa211409485f5cd5aab9f0b5044b712092128ad0fdb8c815da46bd13"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KWTF3WLXKNUW2AKA6YBWB6SK4K/bundle.json","state_url":"https://pith.science/pith/KWTF3WLXKNUW2AKA6YBWB6SK4K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KWTF3WLXKNUW2AKA6YBWB6SK4K/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":"2026-08-22T00:56:08Z","links":{"resolver":"https://pith.science/pith/KWTF3WLXKNUW2AKA6YBWB6SK4K","bundle":"https://pith.science/pith/KWTF3WLXKNUW2AKA6YBWB6SK4K/bundle.json","state":"https://pith.science/pith/KWTF3WLXKNUW2AKA6YBWB6SK4K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KWTF3WLXKNUW2AKA6YBWB6SK4K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KWTF3WLXKNUW2AKA6YBWB6SK4K","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":"741d0e4b41258ae74edc940124810e1fc95b1de46ca7d6f4c3e63ca35552d42c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T20:28:07Z","title_canon_sha256":"13599989a4eb31eb862088500ad7c17303b8b4027309c88f045e5957547e3728"},"schema_version":"1.0","source":{"id":"2412.18675","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18675","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18675v4","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18675","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_12","alias_value":"KWTF3WLXKNUW","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_16","alias_value":"KWTF3WLXKNUW2AKA","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_8","alias_value":"KWTF3WLX","created_at":"2026-07-05T11:36:55Z"}],"graph_snapshots":[{"event_id":"sha256:d5f664edfa211409485f5cd5aab9f0b5044b712092128ad0fdb8c815da46bd13","target":"graph","created_at":"2026-07-05T11:36:55Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.18675/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-head self-attention (MHSA) is a key component of Transformers, a widely popular architecture in both language and vision. Multiple heads intuitively enable different parallel processes over the same input. Yet, they also obscure the attribution of each input patch to the output of a model. We propose a novel 1-head Transformer Attention Bottleneck (TAB) layer, inserted after the traditional MHSA architecture, to serve as an attention bottleneck for interpretability and intervention. Unlike standard self-attention, TAB constrains the total attention over all patches to $\\in [0, 1]$. That ","authors_text":"Anh Totti Nguyen, Hung Huy Nguyen, Long Mai, Pooyan Rahmanzadehgervi, Rosanne Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T20:28:07Z","title":"TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18675","kind":"arxiv","version":4},"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":"sha256:444607b21db365720958c13c7b1d107e79edba6baa0f487db3f69efdcd3329df","target":"record","created_at":"2026-07-05T11:36:55Z","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":"741d0e4b41258ae74edc940124810e1fc95b1de46ca7d6f4c3e63ca35552d42c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T20:28:07Z","title_canon_sha256":"13599989a4eb31eb862088500ad7c17303b8b4027309c88f045e5957547e3728"},"schema_version":"1.0","source":{"id":"2412.18675","kind":"arxiv","version":4}},"canonical_sha256":"55a65dd97753696d0140f60360fa4ae290799af25ee1a2bdbebdc6aa4dfed115","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55a65dd97753696d0140f60360fa4ae290799af25ee1a2bdbebdc6aa4dfed115","first_computed_at":"2026-07-05T11:36:55.159665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:55.159665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mjYe/VGaLbm+/O8q9+sAC1qMCrz2Z65iRDOvfDxOEwmhMwt0kspVd3ZliBXB/2I8sOTMTMhjqtBQTTQrQoGdCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:55.161002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18675","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:444607b21db365720958c13c7b1d107e79edba6baa0f487db3f69efdcd3329df","sha256:d5f664edfa211409485f5cd5aab9f0b5044b712092128ad0fdb8c815da46bd13"],"state_sha256":"dd4284046c7076ce4d1acec2273fa8b3a7bd5265aabd039de148afbd21394b71"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JVbpFdq+9TYm577yp+sGs8Wcehs7jrBhVOCOaBbAMafR30OFY93JN0Z5GDtBe/c456mZCYX2ofR0yosnJpc6Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T00:56:08.991375Z","bundle_sha256":"2bd7c1fe481ed089cfda2097eea60919d658787b10e0265b0574b10161eaf84c"}}