{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AQ3OWJ7ANL4VN6AOF6JGGZRJ25","short_pith_number":"pith:AQ3OWJ7A","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"},"canonical_sha256":"0436eb27e06af956f80e2f92636629d7434811c9c19f955cfb75cac26109c3c4","source":{"kind":"arxiv","id":"2606.08031","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08031","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08031v1","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08031","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"pith_short_12","alias_value":"AQ3OWJ7ANL4V","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"pith_short_16","alias_value":"AQ3OWJ7ANL4VN6AO","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"pith_short_8","alias_value":"AQ3OWJ7A","created_at":"2026-06-09T01:05:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AQ3OWJ7ANL4VN6AOF6JGGZRJ25","target":"record","payload":{"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"},"canonical_sha256":"0436eb27e06af956f80e2f92636629d7434811c9c19f955cfb75cac26109c3c4","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"},"source_kind":"arxiv","source_id":"2606.08031","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":"2026-06-09T01:05:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U96UPW0bZsCFYeNKp6o6/9CEuXNiia5FwFVwVrIbbenv9ehIRTrPLEY5OYAsUY4pvBDxND+yolOvlyZUgveyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:34:32.400561Z"},"content_sha256":"b34d4749b47886e349a8c96f790568f30f0627147ca922a8c0d5d0343d813f50","schema_version":"1.0","event_id":"sha256:b34d4749b47886e349a8c96f790568f30f0627147ca922a8c0d5d0343d813f50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AQ3OWJ7ANL4VN6AOF6JGGZRJ25","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:05:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0yFVHWZySlxi3mnd1h3VdekRh1d9Ll/k5atJ3oc3UX+C1KFYAd9j061s1JIJdrmbmNptDSIXViJkfTUzmWhfCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:34:32.401072Z"},"content_sha256":"c2a3fd34312b07308e9dc2b054a105affd2277e0d4b27e17a2d55823178087ea","schema_version":"1.0","event_id":"sha256:c2a3fd34312b07308e9dc2b054a105affd2277e0d4b27e17a2d55823178087ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/bundle.json","state_url":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/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":"2026-08-06T04:34:32Z","links":{"resolver":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25","bundle":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/bundle.json","state":"https://pith.science/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AQ3OWJ7ANL4VN6AOF6JGGZRJ25/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AQ3OWJ7ANL4VN6AOF6JGGZRJ25","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":"723e352cc7f0295672649ffb63c1f22943131fe58ff47d1596a724536f66f8be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-06T07:48:25Z","title_canon_sha256":"b3fe783349680760320ef4621450b4a23c202614bb481a840cd8bd08501d2327"},"schema_version":"1.0","source":{"id":"2606.08031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08031","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08031v1","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08031","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"pith_short_12","alias_value":"AQ3OWJ7ANL4V","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"pith_short_16","alias_value":"AQ3OWJ7ANL4VN6AO","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"pith_short_8","alias_value":"AQ3OWJ7A","created_at":"2026-06-09T01:05:23Z"}],"graph_snapshots":[{"event_id":"sha256:c2a3fd34312b07308e9dc2b054a105affd2277e0d4b27e17a2d55823178087ea","target":"graph","created_at":"2026-06-09T01:05:23Z","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/2606.08031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arohan Agate","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-06T07:48:25Z","title":"Vision-Language Asymmetry in Bistable Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08031","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:b34d4749b47886e349a8c96f790568f30f0627147ca922a8c0d5d0343d813f50","target":"record","created_at":"2026-06-09T01:05:23Z","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":"723e352cc7f0295672649ffb63c1f22943131fe58ff47d1596a724536f66f8be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-06T07:48:25Z","title_canon_sha256":"b3fe783349680760320ef4621450b4a23c202614bb481a840cd8bd08501d2327"},"schema_version":"1.0","source":{"id":"2606.08031","kind":"arxiv","version":1}},"canonical_sha256":"0436eb27e06af956f80e2f92636629d7434811c9c19f955cfb75cac26109c3c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0436eb27e06af956f80e2f92636629d7434811c9c19f955cfb75cac26109c3c4","first_computed_at":"2026-06-09T01:05:23.641419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:23.641419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VkLn3YWNGNc2NJUaTvhF19XKdAw3odn9g8EG3jeFr4uo37RXo3fW0OWa5D0zkBrCH/lHVRi5wrccy7guUcVyAA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:23.641903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b34d4749b47886e349a8c96f790568f30f0627147ca922a8c0d5d0343d813f50","sha256:c2a3fd34312b07308e9dc2b054a105affd2277e0d4b27e17a2d55823178087ea"],"state_sha256":"af2617805f678d291bc24f5fd0f24c14186ea8cffaab9cedf4a3f0dc59e97fc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"znLjJ8H9U42uKnDt3dQ02d5rgjBtNo/Lh8PV495LFCd9hjWMVcEDi7l5029iDJq/BxbhrnwAhZ/PfBsPMOfeDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:34:32.404636Z","bundle_sha256":"961a43b4aaeb89b79b3253a85280255cb503ca04196a5264359a6b52c4c32b9b"}}