{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AQ3OWJ7ANL4VN6AOF6JGGZRJ25","short_pith_number":"pith:AQ3OWJ7A","schema_version":"1.0","canonical_sha256":"0436eb27e06af956f80e2f92636629d7434811c9c19f955cfb75cac26109c3c4","source":{"kind":"arxiv","id":"2606.08031","version":1},"attestation_state":"computed","paper":{"title":"Vision-Language Asymmetry in Bistable Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arohan Agate","submitted_at":"2026-06-06T07:48:25Z","abstract_excerpt":"Wittgenstein's duck-rabbit poses a question for vision-language models: when a model captions an ambiguous image, where in the model is the commitment to one aspect made? We address this with a 3,320-generation behavioral baseline over 83 bistable stimuli that surfaces three regimes (default-dominant, force-dominant, force-balanced) under neutral vs forced-choice prompting, then probe the underlying representations using a TopK sparse autoencoder we train on the CLIP layer that LLaVA-1.6-7B actually consumes (validation EV 0.93). Across 69 bistable stimuli with both per-aspect feature pools av"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.08031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-06T07:48:25Z","cross_cats_sorted":[],"title_canon_sha256":"b3fe783349680760320ef4621450b4a23c202614bb481a840cd8bd08501d2327","abstract_canon_sha256":"723e352cc7f0295672649ffb63c1f22943131fe58ff47d1596a724536f66f8be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:23.641903Z","signature_b64":"VkLn3YWNGNc2NJUaTvhF19XKdAw3odn9g8EG3jeFr4uo37RXo3fW0OWa5D0zkBrCH/lHVRi5wrccy7guUcVyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0436eb27e06af956f80e2f92636629d7434811c9c19f955cfb75cac26109c3c4","last_reissued_at":"2026-06-09T01:05:23.641419Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:23.641419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language Asymmetry in Bistable Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arohan Agate","submitted_at":"2026-06-06T07:48:25Z","abstract_excerpt":"Wittgenstein's duck-rabbit poses a question for vision-language models: when a model captions an ambiguous image, where in the model is the commitment to one aspect made? We address this with a 3,320-generation behavioral baseline over 83 bistable stimuli that surfaces three regimes (default-dominant, force-dominant, force-balanced) under neutral vs forced-choice prompting, then probe the underlying representations using a TopK sparse autoencoder we train on the CLIP layer that LLaVA-1.6-7B actually consumes (validation EV 0.93). Across 69 bistable stimuli with both per-aspect feature pools av"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08031","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/2606.08031/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.08031","created_at":"2026-06-09T01:05:23.641491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08031v1","created_at":"2026-06-09T01:05:23.641491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08031","created_at":"2026-06-09T01:05:23.641491+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQ3OWJ7ANL4V","created_at":"2026-06-09T01:05:23.641491+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQ3OWJ7ANL4VN6AO","created_at":"2026-06-09T01:05:23.641491+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQ3OWJ7A","created_at":"2026-06-09T01:05:23.641491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25","json":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25.json","graph_json":"https://pith.science/api/pith-number/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/graph.json","events_json":"https://pith.science/api/pith-number/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/events.json","paper":"https://pith.science/paper/AQ3OWJ7A"},"agent_actions":{"view_html":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25","download_json":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25.json","view_paper":"https://pith.science/paper/AQ3OWJ7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08031&json=true","fetch_graph":"https://pith.science/api/pith-number/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/graph.json","fetch_events":"https://pith.science/api/pith-number/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/action/storage_attestation","attest_author":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/action/author_attestation","sign_citation":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/action/citation_signature","submit_replication":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/action/replication_record"}},"created_at":"2026-06-09T01:05:23.641491+00:00","updated_at":"2026-06-09T01:05:23.641491+00:00"}