{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EVKWSMJG7NZXF3Y7UXRFAX4YA4","short_pith_number":"pith:EVKWSMJG","canonical_record":{"source":{"id":"2306.08129","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-13T20:50:22Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6eecbe98d64c7cd93a645b15cd5edae4e9a059d1754f85452d6f5c769a37465d","abstract_canon_sha256":"9ca2f2ebf0cf852fb94ced8ae5c5c6642f6c451f77b0656e2533efe3fb3526c5"},"schema_version":"1.0"},"canonical_sha256":"2555693126fb7372ef1fa5e2505f980733a8636572a0d80bd1b6b305922467ff","source":{"kind":"arxiv","id":"2306.08129","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08129","created_at":"2026-07-05T07:08:08Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08129v3","created_at":"2026-07-05T07:08:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08129","created_at":"2026-07-05T07:08:08Z"},{"alias_kind":"pith_short_12","alias_value":"EVKWSMJG7NZX","created_at":"2026-07-05T07:08:08Z"},{"alias_kind":"pith_short_16","alias_value":"EVKWSMJG7NZXF3Y7","created_at":"2026-07-05T07:08:08Z"},{"alias_kind":"pith_short_8","alias_value":"EVKWSMJG","created_at":"2026-07-05T07:08:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EVKWSMJG7NZXF3Y7UXRFAX4YA4","target":"record","payload":{"canonical_record":{"source":{"id":"2306.08129","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-13T20:50:22Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6eecbe98d64c7cd93a645b15cd5edae4e9a059d1754f85452d6f5c769a37465d","abstract_canon_sha256":"9ca2f2ebf0cf852fb94ced8ae5c5c6642f6c451f77b0656e2533efe3fb3526c5"},"schema_version":"1.0"},"canonical_sha256":"2555693126fb7372ef1fa5e2505f980733a8636572a0d80bd1b6b305922467ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:08.506577Z","signature_b64":"pCajHDe0pV1MZU8ZZmHYLZjVoD6wW8ll1qmDl2a4LGQpZfNFTVF6NFcwyEx9x5hVjPxetT2XiebpMlOJ/PQeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2555693126fb7372ef1fa5e2505f980733a8636572a0d80bd1b6b305922467ff","last_reissued_at":"2026-07-05T07:08:08.506036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:08.506036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.08129","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:08:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"88O3ZShiHjv+gWVyoAdNjNShqebhEZDmwrk4tZjpv9+SqHPyuPpQ963IrXTW/qoSFKOawXElf6y3ZsiVDhjhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:58:28.074575Z"},"content_sha256":"a7c89f792a45ff14f59d24b49cef294687113d7886b1b64fbb38c597ccd8f352","schema_version":"1.0","event_id":"sha256:a7c89f792a45ff14f59d24b49cef294687113d7886b1b64fbb38c597ccd8f352"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EVKWSMJG7NZXF3Y7UXRFAX4YA4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AVIS: Autonomous Visual Information Seeking with Large Language Model Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Ahmet Iscen, Alireza Fathi, Chen Sun, Cordelia Schmid, David A Ross, Kai-Wei Chang, Yizhou Sun, Ziniu Hu","submitted_at":"2023-06-13T20:50:22Z","abstract_excerpt":"In this paper, we propose an autonomous information seeking visual question answering framework, AVIS. Our method leverages a Large Language Model (LLM) to dynamically strategize the utilization of external tools and to investigate their outputs, thereby acquiring the indispensable knowledge needed to provide answers to the posed questions. Responding to visual questions that necessitate external knowledge, such as \"What event is commemorated by the building depicted in this image?\", is a complex task. This task presents a combinatorial search space that demands a sequence of actions, includin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08129","kind":"arxiv","version":3},"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/2306.08129/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":"2026-07-05T07:08:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x5Uuf4/DjzkuckKtO81pOp5UHaMGyshQYupJfljoPv+GgJ53SwIKJeuyZLcdTAgKaBrF0tkQK5BNJ8PN2W6FDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:58:28.075133Z"},"content_sha256":"7a5f4fe8c0779ad35d916760cc6aac7a1e3ba781646837010215bcd0f33f980a","schema_version":"1.0","event_id":"sha256:7a5f4fe8c0779ad35d916760cc6aac7a1e3ba781646837010215bcd0f33f980a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EVKWSMJG7NZXF3Y7UXRFAX4YA4/bundle.json","state_url":"https://pith.science/pith/EVKWSMJG7NZXF3Y7UXRFAX4YA4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EVKWSMJG7NZXF3Y7UXRFAX4YA4/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":"2026-08-09T02:58:28Z","links":{"resolver":"https://pith.science/pith/EVKWSMJG7NZXF3Y7UXRFAX4YA4","bundle":"https://pith.science/pith/EVKWSMJG7NZXF3Y7UXRFAX4YA4/bundle.json","state":"https://pith.science/pith/EVKWSMJG7NZXF3Y7UXRFAX4YA4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EVKWSMJG7NZXF3Y7UXRFAX4YA4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EVKWSMJG7NZXF3Y7UXRFAX4YA4","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":"9ca2f2ebf0cf852fb94ced8ae5c5c6642f6c451f77b0656e2533efe3fb3526c5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-13T20:50:22Z","title_canon_sha256":"6eecbe98d64c7cd93a645b15cd5edae4e9a059d1754f85452d6f5c769a37465d"},"schema_version":"1.0","source":{"id":"2306.08129","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08129","created_at":"2026-07-05T07:08:08Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08129v3","created_at":"2026-07-05T07:08:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08129","created_at":"2026-07-05T07:08:08Z"},{"alias_kind":"pith_short_12","alias_value":"EVKWSMJG7NZX","created_at":"2026-07-05T07:08:08Z"},{"alias_kind":"pith_short_16","alias_value":"EVKWSMJG7NZXF3Y7","created_at":"2026-07-05T07:08:08Z"},{"alias_kind":"pith_short_8","alias_value":"EVKWSMJG","created_at":"2026-07-05T07:08:08Z"}],"graph_snapshots":[{"event_id":"sha256:7a5f4fe8c0779ad35d916760cc6aac7a1e3ba781646837010215bcd0f33f980a","target":"graph","created_at":"2026-07-05T07:08:08Z","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/2306.08129/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose an autonomous information seeking visual question answering framework, AVIS. Our method leverages a Large Language Model (LLM) to dynamically strategize the utilization of external tools and to investigate their outputs, thereby acquiring the indispensable knowledge needed to provide answers to the posed questions. Responding to visual questions that necessitate external knowledge, such as \"What event is commemorated by the building depicted in this image?\", is a complex task. This task presents a combinatorial search space that demands a sequence of actions, includin","authors_text":"Ahmet Iscen, Alireza Fathi, Chen Sun, Cordelia Schmid, David A Ross, Kai-Wei Chang, Yizhou Sun, Ziniu Hu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-13T20:50:22Z","title":"AVIS: Autonomous Visual Information Seeking with Large Language Model Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08129","kind":"arxiv","version":3},"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:a7c89f792a45ff14f59d24b49cef294687113d7886b1b64fbb38c597ccd8f352","target":"record","created_at":"2026-07-05T07:08:08Z","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":"9ca2f2ebf0cf852fb94ced8ae5c5c6642f6c451f77b0656e2533efe3fb3526c5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-13T20:50:22Z","title_canon_sha256":"6eecbe98d64c7cd93a645b15cd5edae4e9a059d1754f85452d6f5c769a37465d"},"schema_version":"1.0","source":{"id":"2306.08129","kind":"arxiv","version":3}},"canonical_sha256":"2555693126fb7372ef1fa5e2505f980733a8636572a0d80bd1b6b305922467ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2555693126fb7372ef1fa5e2505f980733a8636572a0d80bd1b6b305922467ff","first_computed_at":"2026-07-05T07:08:08.506036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:08.506036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pCajHDe0pV1MZU8ZZmHYLZjVoD6wW8ll1qmDl2a4LGQpZfNFTVF6NFcwyEx9x5hVjPxetT2XiebpMlOJ/PQeBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:08.506577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08129","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7c89f792a45ff14f59d24b49cef294687113d7886b1b64fbb38c597ccd8f352","sha256:7a5f4fe8c0779ad35d916760cc6aac7a1e3ba781646837010215bcd0f33f980a"],"state_sha256":"ca2b6cb42dc62a90b2109b2fe285a9530e71acf5b73f6691bc1291283154b55a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nQedOV28DS2PimBt06N640H2tmyzkohoU49p8s/Oo7/GHhBqbNeMJ19XSXBQsHhq+mA7r0Ec9Q9UixYz1tppAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:58:28.079212Z","bundle_sha256":"47fcff34447f5f7d97ded7e85006b3ec991248ac3eeadef9e7623bef0de6d823"}}